Search

Your search keyword '"Lu, Han"' showing total 5,424 results
Start Over Author "Lu, Han"

Refine your results

more »

more »

more »

more »

more »
5,424 results on '"Lu, Han"'

1. Clustering and Mining Accented Speech for Inclusive and Fair Speech Recognition

Author

Kim, Jaeyoung, Lu, Han, Khorram, Soheil, Tripathi, Anshuman, Zhang, Qian, and Sak, Hasim

Subjects
Computer Science - Sound, Computer Science - Artificial Intelligence, Electrical Engineering and Systems Science - Audio and Speech Processing
Abstract

Modern automatic speech recognition (ASR) systems are typically trained on more than tens of thousands hours of speech data, which is one of the main factors for their great success. However, the distribution of such data is typically biased towards common accents or typical speech patterns. As a result, those systems often poorly perform on atypical accented speech. In this paper, we present accent clustering and mining schemes for fair speech recognition systems which can perform equally well on under-represented accented speech. For accent recognition, we applied three schemes to overcome limited size of supervised accent data: supervised or unsupervised pre-training, distributionally robust optimization (DRO) and unsupervised clustering. Three schemes can significantly improve the accent recognition model especially for unbalanced and small accented speech. Fine-tuning ASR on the mined Indian accent speech using the proposed supervised or unsupervised clustering schemes showed 10.0% and 5.3% relative improvements compared to fine-tuning on the randomly sampled speech, respectively.

Published
2024

2. Fuzzy K-Means Clustering without Cluster Centroids

Author

Lu, Han, Li, Fangfang, Gao, Quanxue, Deng, Cheng, Ding, Chris, and Wang, Qianqian

Subjects
Computer Science - Machine Learning
Abstract

Fuzzy K-Means clustering is a critical technique in unsupervised data analysis. However, the performance of popular Fuzzy K-Means algorithms is sensitive to the selection of initial cluster centroids and is also affected by noise when updating mean cluster centroids. To address these challenges, this paper proposes a novel Fuzzy K-Means clustering algorithm that entirely eliminates the reliance on cluster centroids, obtaining membership matrices solely through distance matrix computation. This innovation enhances flexibility in distance measurement between sample points, thus improving the algorithm's performance and robustness. The paper also establishes theoretical connections between the proposed model and popular Fuzzy K-Means clustering techniques. Experimental results on several real datasets demonstrate the effectiveness of the algorithm.

Published
2024

3. YNetr: Dual-Encoder architecture on Plain Scan Liver Tumors (PSLT)

Author

Sheng, Wen, Zheng, Zhong, Liu, Jiajun, Lu, Han, Zhang, Hanyuan, Jiang, Zhengyong, Zhang, Zhihong, and Zhu, Daoping

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning
Abstract

Background: Liver tumors are abnormal growths in the liver that can be either benign or malignant, with liver cancer being a significant health concern worldwide. However, there is no dataset for plain scan segmentation of liver tumors, nor any related algorithms. To fill this gap, we propose Plain Scan Liver Tumors(PSLT) and YNetr. Methods: A collection of 40 liver tumor plain scan segmentation datasets was assembled and annotated. Concurrently, we utilized Dice coefficient as the metric for assessing the segmentation outcomes produced by YNetr, having advantage of capturing different frequency information. Results: The YNetr model achieved a Dice coefficient of 62.63% on the PSLT dataset, surpassing the other publicly available model by an accuracy margin of 1.22%. Comparative evaluations were conducted against a range of models including UNet 3+, XNet, UNetr, Swin UNetr, Trans-BTS, COTr, nnUNetv2 (2D), nnUNetv2 (3D fullres), MedNext (2D) and MedNext(3D fullres). Conclusions: We not only proposed a dataset named PSLT(Plain Scan Liver Tumors), but also explored a structure called YNetr that utilizes wavelet transform to extract different frequency information, which having the SOTA in PSLT by experiments., Comment: My academic research interests have undergone significant changes. I believe that continuing to retain the paper is no longer in line with my academic development path, and may also mislead readers. And some of the content may involve the boundaries of personal privacy. To respect and protect the privacy of relevant personnel, I decided to withdraw it to avoid any unnecessary controversy or harm

Published
2024

4. Boundary Matters: A Bi-Level Active Finetuning Framework

Author

Lu, Han, Xie, Yichen, Yang, Xiaokang, and Yan, Junchi

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence
Abstract

The pretraining-finetuning paradigm has gained widespread adoption in vision tasks and other fields, yet it faces the significant challenge of high sample annotation costs. To mitigate this, the concept of active finetuning has emerged, aiming to select the most appropriate samples for model finetuning within a limited budget. Traditional active learning methods often struggle in this setting due to their inherent bias in batch selection. Furthermore, the recent active finetuning approach has primarily concentrated on aligning the distribution of selected subsets with the overall data pool, focusing solely on diversity. In this paper, we propose a Bi-Level Active Finetuning framework to select the samples for annotation in one shot, which includes two stages: core sample selection for diversity, and boundary sample selection for uncertainty. The process begins with the identification of pseudo-class centers, followed by an innovative denoising method and an iterative strategy for boundary sample selection in the high-dimensional feature space, all without relying on ground-truth labels. Our comprehensive experiments provide both qualitative and quantitative evidence of our method's efficacy, outperforming all the existing baselines.

Published
2024

5. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Author

Gemini Team, Georgiev, Petko, Lei, Ving Ian, Burnell, Ryan, Bai, Libin, Gulati, Anmol, Tanzer, Garrett, Vincent, Damien, Pan, Zhufeng, Wang, Shibo, Mariooryad, Soroosh, Ding, Yifan, Geng, Xinyang, Alcober, Fred, Frostig, Roy, Omernick, Mark, Walker, Lexi, Paduraru, Cosmin, Sorokin, Christina, Tacchetti, Andrea, Gaffney, Colin, Daruki, Samira, Sercinoglu, Olcan, Gleicher, Zach, Love, Juliette, Voigtlaender, Paul, Jain, Rohan, Surita, Gabriela, Mohamed, Kareem, Blevins, Rory, Ahn, Junwhan, Zhu, Tao, Kawintiranon, Kornraphop, Firat, Orhan, Gu, Yiming, Zhang, Yujing, Rahtz, Matthew, Faruqui, Manaal, Clay, Natalie, Gilmer, Justin, Co-Reyes, JD, Penchev, Ivo, Zhu, Rui, Morioka, Nobuyuki, Hui, Kevin, Haridasan, Krishna, Campos, Victor, Mahdieh, Mahdis, Guo, Mandy, Hassan, Samer, Kilgour, Kevin, Vezer, Arpi, Cheng, Heng-Tze, de Liedekerke, Raoul, Goyal, Siddharth, Barham, Paul, Strouse, DJ, Noury, Seb, Adler, Jonas, Sundararajan, Mukund, Vikram, Sharad, Lepikhin, Dmitry, Paganini, Michela, Garcia, Xavier, Yang, Fan, Valter, Dasha, Trebacz, Maja, Vodrahalli, Kiran, Asawaroengchai, Chulayuth, Ring, Roman, Kalb, Norbert, Soares, Livio Baldini, Brahma, Siddhartha, Steiner, David, Yu, Tianhe, Mentzer, Fabian, He, Antoine, Gonzalez, Lucas, Xu, Bibo, Kaufman, Raphael Lopez, Shafey, Laurent El, Oh, Junhyuk, Hennigan, Tom, Driessche, George van den, Odoom, Seth, Lucic, Mario, Roelofs, Becca, Lall, Sid, Marathe, Amit, Chan, Betty, Ontanon, Santiago, He, Luheng, Teplyashin, Denis, Lai, Jonathan, Crone, Phil, Damoc, Bogdan, Ho, Lewis, Riedel, Sebastian, Lenc, Karel, Yeh, Chih-Kuan, Chowdhery, Aakanksha, Xu, Yang, Kazemi, Mehran, Amid, Ehsan, Petrushkina, Anastasia, Swersky, Kevin, Khodaei, Ali, Chen, Gowoon, Larkin, Chris, Pinto, Mario, Yan, Geng, Badia, Adria Puigdomenech, Patil, Piyush, Hansen, Steven, Orr, Dave, Arnold, Sebastien M. R., Grimstad, Jordan, Dai, Andrew, Douglas, Sholto, Sinha, Rishika, Yadav, Vikas, Chen, Xi, Gribovskaya, Elena, Austin, Jacob, Zhao, Jeffrey, Patel, Kaushal, Komarek, Paul, Austin, Sophia, Borgeaud, Sebastian, Friso, Linda, Goyal, Abhimanyu, Caine, Ben, Cao, Kris, Chung, Da-Woon, Lamm, Matthew, Barth-Maron, Gabe, Kagohara, Thais, Olszewska, Kate, Chen, Mia, Shivakumar, Kaushik, Agarwal, Rishabh, Godhia, Harshal, Rajwar, Ravi, Snaider, Javier, Dotiwalla, Xerxes, Liu, Yuan, Barua, Aditya, Ungureanu, Victor, Zhang, Yuan, Batsaikhan, Bat-Orgil, Wirth, Mateo, Qin, James, Danihelka, Ivo, Doshi, Tulsee, Chadwick, Martin, Chen, Jilin, Jain, Sanil, Le, Quoc, Kar, Arjun, Gurumurthy, Madhu, Li, Cheng, Sang, Ruoxin, Liu, Fangyu, Lamprou, Lampros, Munoz, Rich, Lintz, Nathan, Mehta, Harsh, Howard, Heidi, Reynolds, Malcolm, Aroyo, Lora, Wang, Quan, Blanco, Lorenzo, Cassirer, Albin, Griffith, Jordan, Das, Dipanjan, Lee, Stephan, Sygnowski, Jakub, Fisher, Zach, Besley, James, Powell, Richard, Ahmed, Zafarali, Paulus, Dominik, Reitter, David, Borsos, Zalan, Joshi, Rishabh, Pope, Aedan, Hand, Steven, Selo, Vittorio, Jain, Vihan, Sethi, Nikhil, Goel, Megha, Makino, Takaki, May, Rhys, Yang, Zhen, Schalkwyk, Johan, Butterfield, Christina, Hauth, Anja, Goldin, Alex, Hawkins, Will, Senter, Evan, Brin, Sergey, Woodman, Oliver, Ritter, Marvin, Noland, Eric, Giang, Minh, Bolina, Vijay, Lee, Lisa, Blyth, Tim, Mackinnon, Ian, Reid, Machel, Sarvana, Obaid, Silver, David, Chen, Alexander, Wang, Lily, Maggiore, Loren, Chang, Oscar, Attaluri, Nithya, Thornton, Gregory, Chiu, Chung-Cheng, Bunyan, Oskar, Levine, Nir, Chung, Timothy, Eltyshev, Evgenii, Si, Xiance, Lillicrap, Timothy, Brady, Demetra, Aggarwal, Vaibhav, Wu, Boxi, Xu, Yuanzhong, McIlroy, Ross, Badola, Kartikeya, Sandhu, Paramjit, Moreira, Erica, Stokowiec, Wojciech, Hemsley, Ross, Li, Dong, Tudor, Alex, Shyam, Pranav, Rahimtoroghi, Elahe, Haykal, Salem, Sprechmann, Pablo, Zhou, Xiang, Mincu, Diana, Li, Yujia, Addanki, Ravi, Krishna, Kalpesh, Wu, Xiao, Frechette, Alexandre, Eyal, Matan, Dafoe, Allan, Lacey, Dave, Whang, Jay, Avrahami, Thi, Zhang, Ye, Taropa, Emanuel, Lin, Hanzhao, Toyama, Daniel, Rutherford, Eliza, Sano, Motoki, Choe, HyunJeong, Tomala, Alex, Safranek-Shrader, Chalence, Kassner, Nora, Pajarskas, Mantas, Harvey, Matt, Sechrist, Sean, Fortunato, Meire, Lyu, Christina, Elsayed, Gamaleldin, Kuang, Chenkai, Lottes, James, Chu, Eric, Jia, Chao, Chen, Chih-Wei, Humphreys, Peter, Baumli, Kate, Tao, Connie, Samuel, Rajkumar, Santos, Cicero Nogueira dos, Andreassen, Anders, Rakićević, Nemanja, Grewe, Dominik, Kumar, Aviral, Winkler, Stephanie, Caton, Jonathan, Brock, Andrew, Dalmia, Sid, Sheahan, Hannah, Barr, Iain, Miao, Yingjie, Natsev, Paul, Devlin, Jacob, Behbahani, Feryal, Prost, Flavien, Sun, Yanhua, Myaskovsky, Artiom, Pillai, Thanumalayan Sankaranarayana, Hurt, Dan, Lazaridou, Angeliki, Xiong, Xi, Zheng, Ce, Pardo, Fabio, Li, Xiaowei, Horgan, Dan, Stanton, Joe, Ambar, Moran, Xia, Fei, Lince, Alejandro, Wang, Mingqiu, Mustafa, Basil, Webson, Albert, Lee, Hyo, Anil, Rohan, Wicke, Martin, Dozat, Timothy, Sinha, Abhishek, Piqueras, Enrique, Dabir, Elahe, Upadhyay, Shyam, Boral, Anudhyan, Hendricks, Lisa Anne, Fry, Corey, Djolonga, Josip, Su, Yi, Walker, Jake, Labanowski, Jane, Huang, Ronny, Misra, Vedant, Chen, Jeremy, Skerry-Ryan, RJ, Singh, Avi, Rijhwani, Shruti, Yu, Dian, Castro-Ros, Alex, Changpinyo, Beer, Datta, Romina, Bagri, Sumit, Hrafnkelsson, Arnar Mar, Maggioni, Marcello, Zheng, Daniel, Sulsky, Yury, Hou, Shaobo, Paine, Tom Le, Yang, Antoine, Riesa, Jason, Rogozinska, Dominika, Marcus, Dror, Badawy, Dalia El, Zhang, Qiao, Wang, Luyu, Miller, Helen, Greer, Jeremy, Sjos, Lars Lowe, Nova, Azade, Zen, Heiga, Chaabouni, Rahma, Rosca, Mihaela, Jiang, Jiepu, Chen, Charlie, Liu, Ruibo, Sainath, Tara, Krikun, Maxim, Polozov, Alex, Lespiau, Jean-Baptiste, Newlan, Josh, Cankara, Zeyncep, Kwak, Soo, Xu, Yunhan, Chen, Phil, Coenen, Andy, Meyer, Clemens, Tsihlas, Katerina, Ma, Ada, Gottweis, Juraj, Xing, Jinwei, Gu, Chenjie, Miao, Jin, Frank, Christian, Cankara, Zeynep, Ganapathy, Sanjay, Dasgupta, Ishita, Hughes-Fitt, Steph, Chen, Heng, Reid, David, Rong, Keran, Fan, Hongmin, van Amersfoort, Joost, Zhuang, Vincent, Cohen, Aaron, Gu, Shixiang Shane, Mohananey, Anhad, Ilic, Anastasija, Tobin, Taylor, Wieting, John, Bortsova, Anna, Thacker, Phoebe, Wang, Emma, Caveness, Emily, Chiu, Justin, Sezener, Eren, Kaskasoli, Alex, Baker, Steven, Millican, Katie, Elhawaty, Mohamed, Aisopos, Kostas, Lebsack, Carl, Byrd, Nathan, Dai, Hanjun, Jia, Wenhao, Wiethoff, Matthew, Davoodi, Elnaz, Weston, Albert, Yagati, Lakshman, Ahuja, Arun, Gao, Isabel, Pundak, Golan, Zhang, Susan, Azzam, Michael, Sim, Khe Chai, Caelles, Sergi, Keeling, James, Sharma, Abhanshu, Swing, Andy, Li, YaGuang, Liu, Chenxi, Bostock, Carrie Grimes, Bansal, Yamini, Nado, Zachary, Anand, Ankesh, Lipschultz, Josh, Karmarkar, Abhijit, Proleev, Lev, Ittycheriah, Abe, Yeganeh, Soheil Hassas, Polovets, George, Faust, Aleksandra, Sun, Jiao, Rrustemi, Alban, Li, Pen, Shivanna, Rakesh, Liu, Jeremiah, Welty, Chris, Lebron, Federico, Baddepudi, Anirudh, Krause, Sebastian, Parisotto, Emilio, Soricut, Radu, Xu, Zheng, Bloxwich, Dawn, Johnson, Melvin, Neyshabur, Behnam, Mao-Jones, Justin, Wang, Renshen, Ramasesh, Vinay, Abbas, Zaheer, Guez, Arthur, Segal, Constant, Nguyen, Duc Dung, Svensson, James, Hou, Le, York, Sarah, Milan, Kieran, Bridgers, Sophie, Gworek, Wiktor, Tagliasacchi, Marco, Lee-Thorp, James, Chang, Michael, Guseynov, Alexey, Hartman, Ale Jakse, Kwong, Michael, Zhao, Ruizhe, Kashem, Sheleem, Cole, Elizabeth, Miech, Antoine, Tanburn, Richard, Phuong, Mary, Pavetic, Filip, Cevey, Sebastien, Comanescu, Ramona, Ives, Richard, Yang, Sherry, Du, Cosmo, Li, Bo, Zhang, Zizhao, Iinuma, Mariko, Hu, Clara Huiyi, Roy, Aurko, Bijwadia, Shaan, Zhu, Zhenkai, Martins, Danilo, Saputro, Rachel, Gergely, Anita, Zheng, Steven, Jia, Dawei, Antonoglou, Ioannis, Sadovsky, Adam, Gu, Shane, Bi, Yingying, Andreev, Alek, Samangooei, Sina, Khan, Mina, Kocisky, Tomas, Filos, Angelos, Kumar, Chintu, Bishop, Colton, Yu, Adams, Hodkinson, Sarah, Mittal, Sid, Shah, Premal, Moufarek, Alexandre, Cheng, Yong, Bloniarz, Adam, Lee, Jaehoon, Pejman, Pedram, Michel, Paul, Spencer, Stephen, Feinberg, Vladimir, Xiong, Xuehan, Savinov, Nikolay, Smith, Charlotte, Shakeri, Siamak, Tran, Dustin, Chesus, Mary, Bohnet, Bernd, Tucker, George, von Glehn, Tamara, Muir, Carrie, Mao, Yiran, Kazawa, Hideto, Slone, Ambrose, Soparkar, Kedar, Shrivastava, Disha, Cobon-Kerr, James, Sharman, Michael, Pavagadhi, Jay, Araya, Carlos, Misiunas, Karolis, Ghelani, Nimesh, Laskin, Michael, Barker, David, Li, Qiujia, Briukhov, Anton, Houlsby, Neil, Glaese, Mia, Lakshminarayanan, Balaji, Schucher, Nathan, Tang, Yunhao, Collins, Eli, Lim, Hyeontaek, Feng, Fangxiaoyu, Recasens, Adria, Lai, Guangda, Magni, Alberto, De Cao, Nicola, Siddhant, Aditya, Ashwood, Zoe, Orbay, Jordi, Dehghani, Mostafa, Brennan, Jenny, He, Yifan, Xu, Kelvin, Gao, Yang, Saroufim, Carl, Molloy, James, Wu, Xinyi, Arnold, Seb, Chang, Solomon, Schrittwieser, Julian, Buchatskaya, Elena, Radpour, Soroush, Polacek, Martin, Giordano, Skye, Bapna, Ankur, Tokumine, Simon, Hellendoorn, Vincent, Sottiaux, Thibault, Cogan, Sarah, Severyn, Aliaksei, Saleh, Mohammad, Thakoor, Shantanu, Shefey, Laurent, Qiao, Siyuan, Gaba, Meenu, Chang, Shuo-yiin, Swanson, Craig, Zhang, Biao, Lee, Benjamin, Rubenstein, Paul Kishan, Song, Gan, Kwiatkowski, Tom, Koop, Anna, Kannan, Ajay, Kao, David, Schuh, Parker, Stjerngren, Axel, Ghiasi, Golnaz, Gibson, Gena, Vilnis, Luke, Yuan, Ye, Ferreira, Felipe Tiengo, Kamath, Aishwarya, Klimenko, Ted, Franko, Ken, Xiao, Kefan, Bhattacharya, Indro, Patel, Miteyan, Wang, Rui, Morris, Alex, Strudel, Robin, Sharma, Vivek, Choy, Peter, Hashemi, Sayed Hadi, Landon, Jessica, Finkelstein, Mara, Jhakra, Priya, Frye, Justin, Barnes, Megan, Mauger, Matthew, Daun, Dennis, Baatarsukh, Khuslen, Tung, Matthew, Farhan, Wael, Michalewski, Henryk, Viola, Fabio, Quitry, Felix de Chaumont, Lan, Charline Le, Hudson, Tom, Wang, Qingze, Fischer, Felix, Zheng, Ivy, White, Elspeth, Dragan, Anca, Alayrac, Jean-baptiste, Ni, Eric, Pritzel, Alexander, Iwanicki, Adam, Isard, Michael, Bulanova, Anna, Zilka, Lukas, Dyer, Ethan, Sachan, Devendra, Srinivasan, Srivatsan, Muckenhirn, Hannah, Cai, Honglong, Mandhane, Amol, Tariq, Mukarram, Rae, Jack W., Wang, Gary, Ayoub, Kareem, FitzGerald, Nicholas, Zhao, Yao, Han, Woohyun, Alberti, Chris, Garrette, Dan, Krishnakumar, Kashyap, Gimenez, Mai, Levskaya, Anselm, Sohn, Daniel, Matak, Josip, Iturrate, Inaki, Chang, Michael B., Xiang, Jackie, Cao, Yuan, Ranka, Nishant, Brown, Geoff, Hutter, Adrian, Mirrokni, Vahab, Chen, Nanxin, Yao, Kaisheng, Egyed, Zoltan, Galilee, Francois, Liechty, Tyler, Kallakuri, Praveen, Palmer, Evan, Ghemawat, Sanjay, Liu, Jasmine, Tao, David, Thornton, Chloe, Green, Tim, Jasarevic, Mimi, Lin, Sharon, Cotruta, Victor, Tan, Yi-Xuan, Fiedel, Noah, Yu, Hongkun, Chi, Ed, Neitz, Alexander, Heitkaemper, Jens, Sinha, Anu, Zhou, Denny, Sun, Yi, Kaed, Charbel, Hulse, Brice, Mishra, Swaroop, Georgaki, Maria, Kudugunta, Sneha, Farabet, Clement, Shafran, Izhak, Vlasic, Daniel, Tsitsulin, Anton, Ananthanarayanan, Rajagopal, Carin, Alen, Su, Guolong, Sun, Pei, V, Shashank, Carvajal, Gabriel, Broder, Josef, Comsa, Iulia, Repina, Alena, Wong, William, Chen, Warren Weilun, Hawkins, Peter, Filonov, Egor, Loher, Lucia, Hirnschall, Christoph, Wang, Weiyi, Ye, Jingchen, Burns, Andrea, Cate, Hardie, Wright, Diana Gage, Piccinini, Federico, Zhang, Lei, Lin, Chu-Cheng, Gog, Ionel, Kulizhskaya, Yana, Sreevatsa, Ashwin, Song, Shuang, Cobo, Luis C., Iyer, Anand, Tekur, Chetan, Garrido, Guillermo, Xiao, Zhuyun, Kemp, Rupert, Zheng, Huaixiu Steven, Li, Hui, Agarwal, Ananth, Ngani, Christel, Goshvadi, Kati, Santamaria-Fernandez, Rebeca, Fica, Wojciech, Chen, Xinyun, Gorgolewski, Chris, Sun, Sean, Garg, Roopal, Ye, Xinyu, Eslami, S. M. Ali, Hua, Nan, Simon, Jon, Joshi, Pratik, Kim, Yelin, Tenney, Ian, Potluri, Sahitya, Thiet, Lam Nguyen, Yuan, Quan, Luisier, Florian, Chronopoulou, Alexandra, Scellato, Salvatore, Srinivasan, Praveen, Chen, Minmin, Koverkathu, Vinod, Dalibard, Valentin, Xu, Yaming, Saeta, Brennan, Anderson, Keith, Sellam, Thibault, Fernando, Nick, Huot, Fantine, Jung, Junehyuk, Varadarajan, Mani, Quinn, Michael, Raul, Amit, Le, Maigo, Habalov, Ruslan, Clark, Jon, Jalan, Komal, Bullard, Kalesha, Singhal, Achintya, Luong, Thang, Wang, Boyu, Rajayogam, Sujeevan, Eisenschlos, Julian, Jia, Johnson, Finchelstein, Daniel, Yakubovich, Alex, Balle, Daniel, Fink, Michael, Agarwal, Sameer, Li, Jing, Dvijotham, Dj, Pal, Shalini, Kang, Kai, Konzelmann, Jaclyn, Beattie, Jennifer, Dousse, Olivier, Wu, Diane, Crocker, Remi, Elkind, Chen, Jonnalagadda, Siddhartha Reddy, Lee, Jong, Holtmann-Rice, Dan, Kallarackal, Krystal, Liu, Rosanne, Vnukov, Denis, Vats, Neera, Invernizzi, Luca, Jafari, Mohsen, Zhou, Huanjie, Taylor, Lilly, Prendki, Jennifer, Wu, Marcus, Eccles, Tom, Liu, Tianqi, Kopparapu, Kavya, Beaufays, Francoise, Angermueller, Christof, Marzoca, Andreea, Sarcar, Shourya, Dib, Hilal, Stanway, Jeff, Perbet, Frank, Trdin, Nejc, Sterneck, Rachel, Khorlin, Andrey, Li, Dinghua, Wu, Xihui, Goenka, Sonam, Madras, David, Goldshtein, Sasha, Gierke, Willi, Zhou, Tong, Liu, Yaxin, Liang, Yannie, White, Anais, Li, Yunjie, Singh, Shreya, Bahargam, Sanaz, Epstein, Mark, Basu, Sujoy, Lao, Li, Ozturel, Adnan, Crous, Carl, Zhai, Alex, Lu, Han, Tung, Zora, Gaur, Neeraj, Walton, Alanna, Dixon, Lucas, Zhang, Ming, Globerson, Amir, Uy, Grant, Bolt, Andrew, Wiles, Olivia, Nasr, Milad, Shumailov, Ilia, Selvi, Marco, Piccinno, Francesco, Aguilar, Ricardo, McCarthy, Sara, Khalman, Misha, Shukla, Mrinal, Galic, Vlado, Carpenter, John, Villela, Kevin, Zhang, Haibin, Richardson, Harry, Martens, James, Bosnjak, Matko, Belle, Shreyas Rammohan, Seibert, Jeff, Alnahlawi, Mahmoud, McWilliams, Brian, Singh, Sankalp, Louis, Annie, Ding, Wen, Popovici, Dan, Simicich, Lenin, Knight, Laura, Mehta, Pulkit, Gupta, Nishesh, Shi, Chongyang, Fatehi, Saaber, Mitrovic, Jovana, Grills, Alex, Pagadora, Joseph, Petrova, Dessie, Eisenbud, Danielle, Zhang, Zhishuai, Yates, Damion, Mittal, Bhavishya, Tripuraneni, Nilesh, Assael, Yannis, Brovelli, Thomas, Jain, Prateek, Velimirovic, Mihajlo, Akbulut, Canfer, Mu, Jiaqi, Macherey, Wolfgang, Kumar, Ravin, Xu, Jun, Qureshi, Haroon, Comanici, Gheorghe, Wiesner, Jeremy, Gong, Zhitao, Ruddock, Anton, Bauer, Matthias, Felt, Nick, GP, Anirudh, Arnab, Anurag, Zelle, Dustin, Rothfuss, Jonas, Rosgen, Bill, Shenoy, Ashish, Seybold, Bryan, Li, Xinjian, Mudigonda, Jayaram, Erdogan, Goker, Xia, Jiawei, Simsa, Jiri, Michi, Andrea, Yao, Yi, Yew, Christopher, Kan, Steven, Caswell, Isaac, Radebaugh, Carey, Elisseeff, Andre, Valenzuela, Pedro, McKinney, Kay, Paterson, Kim, Cui, Albert, Latorre-Chimoto, Eri, Kim, Solomon, Zeng, William, Durden, Ken, Ponnapalli, Priya, Sosea, Tiberiu, Choquette-Choo, Christopher A., Manyika, James, Robenek, Brona, Vashisht, Harsha, Pereira, Sebastien, Lam, Hoi, Velic, Marko, Owusu-Afriyie, Denese, Lee, Katherine, Bolukbasi, Tolga, Parrish, Alicia, Lu, Shawn, Park, Jane, Venkatraman, Balaji, Talbert, Alice, Rosique, Lambert, Cheng, Yuchung, Sozanschi, Andrei, Paszke, Adam, Kumar, Praveen, Austin, Jessica, Li, Lu, Salama, Khalid, Kim, Wooyeol, Dukkipati, Nandita, Baryshnikov, Anthony, Kaplanis, Christos, Sheng, XiangHai, Chervonyi, Yuri, Unlu, Caglar, Casas, Diego de Las, Askham, Harry, Tunyasuvunakool, Kathryn, Gimeno, Felix, Poder, Siim, Kwak, Chester, Miecnikowski, Matt, Dimitriev, Alek, Parisi, Aaron, Liu, Dangyi, Tsai, Tomy, Shevlane, Toby, Kouridi, Christina, Garmon, Drew, Goedeckemeyer, Adrian, Brown, Adam R., Vijayakumar, Anitha, Elqursh, Ali, Jazayeri, Sadegh, Huang, Jin, Carthy, Sara Mc, Hoover, Jay, Kim, Lucy, Kumar, Sandeep, Chen, Wei, Biles, Courtney, Bingham, Garrett, Rosen, Evan, Wang, Lisa, Tan, Qijun, Engel, David, Pongetti, Francesco, de Cesare, Dario, Hwang, Dongseong, Yu, Lily, Pullman, Jennifer, Narayanan, Srini, Levin, Kyle, Gopal, Siddharth, Li, Megan, Aharoni, Asaf, Trinh, Trieu, Lo, Jessica, Casagrande, Norman, Vij, Roopali, Matthey, Loic, Ramadhana, Bramandia, Matthews, Austin, Carey, CJ, Johnson, Matthew, Goranova, Kremena, Shah, Rohin, Ashraf, Shereen, Dasgupta, Kingshuk, Larsen, Rasmus, Wang, Yicheng, Vuyyuru, Manish Reddy, Jiang, Chong, Ijazi, Joana, Osawa, Kazuki, Smith, Celine, Boppana, Ramya Sree, Bilal, Taylan, Koizumi, Yuma, Xu, Ying, Altun, Yasemin, Shabat, Nir, Bariach, Ben, Korchemniy, Alex, Choo, Kiam, Ronneberger, Olaf, Iwuanyanwu, Chimezie, Zhao, Shubin, Soergel, David, Hsieh, Cho-Jui, Cai, Irene, Iqbal, Shariq, Sundermeyer, Martin, Chen, Zhe, Bursztein, Elie, Malaviya, Chaitanya, Biadsy, Fadi, Shroff, Prakash, Dhillon, Inderjit, Latkar, Tejasi, Dyer, Chris, Forbes, Hannah, Nicosia, Massimo, Nikolaev, Vitaly, Greene, Somer, Georgiev, Marin, Wang, Pidong, Martin, Nina, Sedghi, Hanie, Zhang, John, Banzal, Praseem, Fritz, Doug, Rao, Vikram, Wang, Xuezhi, Zhang, Jiageng, Patraucean, Viorica, Du, Dayou, Mordatch, Igor, Jurin, Ivan, Liu, Lewis, Dubey, Ayush, Mohan, Abhi, Nowakowski, Janek, Ion, Vlad-Doru, Wei, Nan, Tojo, Reiko, Raad, Maria Abi, Hudson, Drew A., Keshava, Vaishakh, Agrawal, Shubham, Ramirez, Kevin, Wu, Zhichun, Nguyen, Hoang, Liu, Ji, Sewak, Madhavi, Petrini, Bryce, Choi, DongHyun, Philips, Ivan, Wang, Ziyue, Bica, Ioana, Garg, Ankush, Wilkiewicz, Jarek, Agrawal, Priyanka, Guo, Danhao, Xue, Emily, Shaik, Naseer, Leach, Andrew, Khan, Sadh MNM, Wiesinger, Julia, Jerome, Sammy, Chakladar, Abhishek, Wang, Alek Wenjiao, Ornduff, Tina, Abu, Folake, Ghaffarkhah, Alireza, Wainwright, Marcus, Cortes, Mario, Liu, Frederick, Maynez, Joshua, Terzis, Andreas, Samangouei, Pouya, Mansour, Riham, Kępa, Tomasz, Aubet, François-Xavier, Algymr, Anton, Banica, Dan, Weisz, Agoston, Orban, Andras, Senges, Alexandre, Andrejczuk, Ewa, Geller, Mark, Santo, Niccolo Dal, Anklin, Valentin, Merey, Majd Al, Baeuml, Martin, Strohman, Trevor, Bai, Junwen, Petrov, Slav, Wu, Yonghui, Hassabis, Demis, Kavukcuoglu, Koray, Dean, Jeffrey, and Vinyals, Oriol

Subjects
Computer Science - Computation and Language, Computer Science - Artificial Intelligence
Abstract

In this report, we introduce the Gemini 1.5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over fine-grained information from millions of tokens of context, including multiple long documents and hours of video and audio. The family includes two new models: (1) an updated Gemini 1.5 Pro, which exceeds the February version on the great majority of capabilities and benchmarks; (2) Gemini 1.5 Flash, a more lightweight variant designed for efficiency with minimal regression in quality. Gemini 1.5 models achieve near-perfect recall on long-context retrieval tasks across modalities, improve the state-of-the-art in long-document QA, long-video QA and long-context ASR, and match or surpass Gemini 1.0 Ultra's state-of-the-art performance across a broad set of benchmarks. Studying the limits of Gemini 1.5's long-context ability, we find continued improvement in next-token prediction and near-perfect retrieval (>99%) up to at least 10M tokens, a generational leap over existing models such as Claude 3.0 (200k) and GPT-4 Turbo (128k). Finally, we highlight real-world use cases, such as Gemini 1.5 collaborating with professionals on completing their tasks achieving 26 to 75% time savings across 10 different job categories, as well as surprising new capabilities of large language models at the frontier; when given a grammar manual for Kalamang, a language with fewer than 200 speakers worldwide, the model learns to translate English to Kalamang at a similar level to a person who learned from the same content.

Published
2024

6. ActiveAD: Planning-Oriented Active Learning for End-to-End Autonomous Driving

Author

Lu, Han, Jia, Xiaosong, Xie, Yichen, Liao, Wenlong, Yang, Xiaokang, and Yan, Junchi

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence, Computer Science - Robotics
Abstract

End-to-end differentiable learning for autonomous driving (AD) has recently become a prominent paradigm. One main bottleneck lies in its voracious appetite for high-quality labeled data e.g. 3D bounding boxes and semantic segmentation, which are notoriously expensive to manually annotate. The difficulty is further pronounced due to the prominent fact that the behaviors within samples in AD often suffer from long tailed distribution. In other words, a large part of collected data can be trivial (e.g. simply driving forward in a straight road) and only a few cases are safety-critical. In this paper, we explore a practically important yet under-explored problem about how to achieve sample and label efficiency for end-to-end AD. Specifically, we design a planning-oriented active learning method which progressively annotates part of collected raw data according to the proposed diversity and usefulness criteria for planning routes. Empirically, we show that our planning-oriented approach could outperform general active learning methods by a large margin. Notably, our method achieves comparable performance with state-of-the-art end-to-end AD methods - by using only 30% nuScenes data. We hope our work could inspire future works to explore end-to-end AD from a data-centric perspective in addition to methodology efforts.

Published
2024

7. Rethinking Classifier Re-Training in Long-Tailed Recognition: A Simple Logits Retargeting Approach

Author

Lu, Han, Sun, Siyu, Xie, Yichen, Zhang, Liqing, Yang, Xiaokang, and Yan, Junchi

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence
Abstract

In the long-tailed recognition field, the Decoupled Training paradigm has demonstrated remarkable capabilities among various methods. This paradigm decouples the training process into separate representation learning and classifier re-training. Previous works have attempted to improve both stages simultaneously, making it difficult to isolate the effect of classifier re-training. Furthermore, recent empirical studies have demonstrated that simple regularization can yield strong feature representations, emphasizing the need to reassess existing classifier re-training methods. In this study, we revisit classifier re-training methods based on a unified feature representation and re-evaluate their performances. We propose a new metric called Logits Magnitude as a superior measure of model performance, replacing the commonly used Weight Norm. However, since it is hard to directly optimize the new metric during training, we introduce a suitable approximate invariant called Regularized Standard Deviation. Based on the two newly proposed metrics, we prove that reducing the absolute value of Logits Magnitude when it is nearly balanced can effectively decrease errors and disturbances during training, leading to better model performance. Motivated by these findings, we develop a simple logits retargeting approach (LORT) without the requirement of prior knowledge of the number of samples per class. LORT divides the original one-hot label into small true label probabilities and large negative label probabilities distributed across each class. Our method achieves state-of-the-art performance on various imbalanced datasets, including CIFAR100-LT, ImageNet-LT, and iNaturalist2018.

Published
2024

8. Inducing Generalization across Languages and Tasks using Featurized Low-Rank Mixtures

Author

Lin, Chu-Cheng, Wang, Xinyi, Clark, Jonathan H., Lu, Han, Zhu, Yun, Whitehouse, Chenxi, and Yu, Hongkun

Subjects
Computer Science - Computation and Language, Computer Science - Artificial Intelligence
Abstract

Adapting pretrained large language models (LLMs) to various downstream tasks in tens or hundreds of human languages is computationally expensive. Parameter-efficient fine-tuning (PEFT) significantly reduces the adaptation cost, by tuning only a small amount of parameters. However, common PEFT methods LoRA (Hu et al., 2022) suffer from suboptimal performance on diverse dataset mixtures, due to aggressive parameter tying and negative interference among different datasets. In this work, we propose Featurized Low-rank Mixtures (FLix), a novel PEFT method designed for effective multitask multilingual adaptation. FLix associates each unique dataset feature, such as the dataset's language or task, with its own low-rank weight update parameters. By composing feature-specific parameters for each dataset, FLix can accommodate diverse dataset mixtures and generalize better to unseen datasets. Our experiments show that FLix leads to significant improvements over a variety of tasks for both supervised learning and zero-shot settings with gains of up to $14.2$ inexact match points in zero-shot semantic parsing., Comment: Revised version

Published
2024

10. Gemini: A Family of Highly Capable Multimodal Models

Author

Gemini Team, Anil, Rohan, Borgeaud, Sebastian, Alayrac, Jean-Baptiste, Yu, Jiahui, Soricut, Radu, Schalkwyk, Johan, Dai, Andrew M., Hauth, Anja, Millican, Katie, Silver, David, Johnson, Melvin, Antonoglou, Ioannis, Schrittwieser, Julian, Glaese, Amelia, Chen, Jilin, Pitler, Emily, Lillicrap, Timothy, Lazaridou, Angeliki, Firat, Orhan, Molloy, James, Isard, Michael, Barham, Paul R., Hennigan, Tom, Lee, Benjamin, Viola, Fabio, Reynolds, Malcolm, Xu, Yuanzhong, Doherty, Ryan, Collins, Eli, Meyer, Clemens, Rutherford, Eliza, Moreira, Erica, Ayoub, Kareem, Goel, Megha, Krawczyk, Jack, Du, Cosmo, Chi, Ed, Cheng, Heng-Tze, Ni, Eric, Shah, Purvi, Kane, Patrick, Chan, Betty, Faruqui, Manaal, Severyn, Aliaksei, Lin, Hanzhao, Li, YaGuang, Cheng, Yong, Ittycheriah, Abe, Mahdieh, Mahdis, Chen, Mia, Sun, Pei, Tran, Dustin, Bagri, Sumit, Lakshminarayanan, Balaji, Liu, Jeremiah, Orban, Andras, Güra, Fabian, Zhou, Hao, Song, Xinying, Boffy, Aurelien, Ganapathy, Harish, Zheng, Steven, Choe, HyunJeong, Weisz, Ágoston, Zhu, Tao, Lu, Yifeng, Gopal, Siddharth, Kahn, Jarrod, Kula, Maciej, Pitman, Jeff, Shah, Rushin, Taropa, Emanuel, Merey, Majd Al, Baeuml, Martin, Chen, Zhifeng, Shafey, Laurent El, Zhang, Yujing, Sercinoglu, Olcan, Tucker, George, Piqueras, Enrique, Krikun, Maxim, Barr, Iain, Savinov, Nikolay, Danihelka, Ivo, Roelofs, Becca, White, Anaïs, Andreassen, Anders, von Glehn, Tamara, Yagati, Lakshman, Kazemi, Mehran, Gonzalez, Lucas, Khalman, Misha, Sygnowski, Jakub, Frechette, Alexandre, Smith, Charlotte, Culp, Laura, Proleev, Lev, Luan, Yi, Chen, Xi, Lottes, James, Schucher, Nathan, Lebron, Federico, Rrustemi, Alban, Clay, Natalie, Crone, Phil, Kocisky, Tomas, Zhao, Jeffrey, Perz, Bartek, Yu, Dian, Howard, Heidi, Bloniarz, Adam, Rae, Jack W., Lu, Han, Sifre, Laurent, Maggioni, Marcello, Alcober, Fred, Garrette, Dan, Barnes, Megan, Thakoor, Shantanu, Austin, Jacob, Barth-Maron, Gabriel, Wong, William, Joshi, Rishabh, Chaabouni, Rahma, Fatiha, Deeni, Ahuja, Arun, Tomar, Gaurav Singh, Senter, Evan, Chadwick, Martin, Kornakov, Ilya, Attaluri, Nithya, Iturrate, Iñaki, Liu, Ruibo, Li, Yunxuan, Cogan, Sarah, Chen, Jeremy, Jia, Chao, Gu, Chenjie, Zhang, Qiao, Grimstad, Jordan, Hartman, Ale Jakse, Garcia, Xavier, Pillai, Thanumalayan Sankaranarayana, Devlin, Jacob, Laskin, Michael, Casas, Diego de Las, Valter, Dasha, Tao, Connie, Blanco, Lorenzo, Badia, Adrià Puigdomènech, Reitter, David, Chen, Mianna, Brennan, Jenny, Rivera, Clara, Brin, Sergey, Iqbal, Shariq, Surita, Gabriela, Labanowski, Jane, Rao, Abhi, Winkler, Stephanie, Parisotto, Emilio, Gu, Yiming, Olszewska, Kate, Addanki, Ravi, Miech, Antoine, Louis, Annie, Teplyashin, Denis, Brown, Geoff, Catt, Elliot, Balaguer, Jan, Xiang, Jackie, Wang, Pidong, Ashwood, Zoe, Briukhov, Anton, Webson, Albert, Ganapathy, Sanjay, Sanghavi, Smit, Kannan, Ajay, Chang, Ming-Wei, Stjerngren, Axel, Djolonga, Josip, Sun, Yuting, Bapna, Ankur, Aitchison, Matthew, Pejman, Pedram, Michalewski, Henryk, Yu, Tianhe, Wang, Cindy, Love, Juliette, Ahn, Junwhan, Bloxwich, Dawn, Han, Kehang, Humphreys, Peter, Sellam, Thibault, Bradbury, James, Godbole, Varun, Samangooei, Sina, Damoc, Bogdan, Kaskasoli, Alex, Arnold, Sébastien M. R., Vasudevan, Vijay, Agrawal, Shubham, Riesa, Jason, Lepikhin, Dmitry, Tanburn, Richard, Srinivasan, Srivatsan, Lim, Hyeontaek, Hodkinson, Sarah, Shyam, Pranav, Ferret, Johan, Hand, Steven, Garg, Ankush, Paine, Tom Le, Li, Jian, Li, Yujia, Giang, Minh, Neitz, Alexander, Abbas, Zaheer, York, Sarah, Reid, Machel, Cole, Elizabeth, Chowdhery, Aakanksha, Das, Dipanjan, Rogozińska, Dominika, Nikolaev, Vitaliy, Sprechmann, Pablo, Nado, Zachary, Zilka, Lukas, Prost, Flavien, He, Luheng, Monteiro, Marianne, Mishra, Gaurav, Welty, Chris, Newlan, Josh, Jia, Dawei, Allamanis, Miltiadis, Hu, Clara Huiyi, de Liedekerke, Raoul, Gilmer, Justin, Saroufim, Carl, Rijhwani, Shruti, Hou, Shaobo, Shrivastava, Disha, Baddepudi, Anirudh, Goldin, Alex, Ozturel, Adnan, Cassirer, Albin, Xu, Yunhan, Sohn, Daniel, Sachan, Devendra, Amplayo, Reinald Kim, Swanson, Craig, Petrova, Dessie, Narayan, Shashi, Guez, Arthur, Brahma, Siddhartha, Landon, Jessica, Patel, Miteyan, Zhao, Ruizhe, Villela, Kevin, Wang, Luyu, Jia, Wenhao, Rahtz, Matthew, Giménez, Mai, Yeung, Legg, Keeling, James, Georgiev, Petko, Mincu, Diana, Wu, Boxi, Haykal, Salem, Saputro, Rachel, Vodrahalli, Kiran, Qin, James, Cankara, Zeynep, Sharma, Abhanshu, Fernando, Nick, Hawkins, Will, Neyshabur, Behnam, Kim, Solomon, Hutter, Adrian, Agrawal, Priyanka, Castro-Ros, Alex, Driessche, George van den, Wang, Tao, Yang, Fan, Chang, Shuo-yiin, Komarek, Paul, McIlroy, Ross, Lučić, Mario, Zhang, Guodong, Farhan, Wael, Sharman, Michael, Natsev, Paul, Michel, Paul, Bansal, Yamini, Qiao, Siyuan, Cao, Kris, Shakeri, Siamak, Butterfield, Christina, Chung, Justin, Rubenstein, Paul Kishan, Agrawal, Shivani, Mensch, Arthur, Soparkar, Kedar, Lenc, Karel, Chung, Timothy, Pope, Aedan, Maggiore, Loren, Kay, Jackie, Jhakra, Priya, Wang, Shibo, Maynez, Joshua, Phuong, Mary, Tobin, Taylor, Tacchetti, Andrea, Trebacz, Maja, Robinson, Kevin, Katariya, Yash, Riedel, Sebastian, Bailey, Paige, Xiao, Kefan, Ghelani, Nimesh, Aroyo, Lora, Slone, Ambrose, Houlsby, Neil, Xiong, Xuehan, Yang, Zhen, Gribovskaya, Elena, Adler, Jonas, Wirth, Mateo, Lee, Lisa, Li, Music, Kagohara, Thais, Pavagadhi, Jay, Bridgers, Sophie, Bortsova, Anna, Ghemawat, Sanjay, Ahmed, Zafarali, Liu, Tianqi, Powell, Richard, Bolina, Vijay, Iinuma, Mariko, Zablotskaia, Polina, Besley, James, Chung, Da-Woon, Dozat, Timothy, Comanescu, Ramona, Si, Xiance, Greer, Jeremy, Su, Guolong, Polacek, Martin, Kaufman, Raphaël Lopez, Tokumine, Simon, Hu, Hexiang, Buchatskaya, Elena, Miao, Yingjie, Elhawaty, Mohamed, Siddhant, Aditya, Tomasev, Nenad, Xing, Jinwei, Greer, Christina, Miller, Helen, Ashraf, Shereen, Roy, Aurko, Zhang, Zizhao, Ma, Ada, Filos, Angelos, Besta, Milos, Blevins, Rory, Klimenko, Ted, Yeh, Chih-Kuan, Changpinyo, Soravit, Mu, Jiaqi, Chang, Oscar, Pajarskas, Mantas, Muir, Carrie, Cohen, Vered, Lan, Charline Le, Haridasan, Krishna, Marathe, Amit, Hansen, Steven, Douglas, Sholto, Samuel, Rajkumar, Wang, Mingqiu, Austin, Sophia, Lan, Chang, Jiang, Jiepu, Chiu, Justin, Lorenzo, Jaime Alonso, Sjösund, Lars Lowe, Cevey, Sébastien, Gleicher, Zach, Avrahami, Thi, Boral, Anudhyan, Srinivasan, Hansa, Selo, Vittorio, May, Rhys, Aisopos, Konstantinos, Hussenot, Léonard, Soares, Livio Baldini, Baumli, Kate, Chang, Michael B., Recasens, Adrià, Caine, Ben, Pritzel, Alexander, Pavetic, Filip, Pardo, Fabio, Gergely, Anita, Frye, Justin, Ramasesh, Vinay, Horgan, Dan, Badola, Kartikeya, Kassner, Nora, Roy, Subhrajit, Dyer, Ethan, Campos, Víctor Campos, Tomala, Alex, Tang, Yunhao, Badawy, Dalia El, White, Elspeth, Mustafa, Basil, Lang, Oran, Jindal, Abhishek, Vikram, Sharad, Gong, Zhitao, Caelles, Sergi, Hemsley, Ross, Thornton, Gregory, Feng, Fangxiaoyu, Stokowiec, Wojciech, Zheng, Ce, Thacker, Phoebe, Ünlü, Çağlar, Zhang, Zhishuai, Saleh, Mohammad, Svensson, James, Bileschi, Max, Patil, Piyush, Anand, Ankesh, Ring, Roman, Tsihlas, Katerina, Vezer, Arpi, Selvi, Marco, Shevlane, Toby, Rodriguez, Mikel, Kwiatkowski, Tom, Daruki, Samira, Rong, Keran, Dafoe, Allan, FitzGerald, Nicholas, Gu-Lemberg, Keren, Khan, Mina, Hendricks, Lisa Anne, Pellat, Marie, Feinberg, Vladimir, Cobon-Kerr, James, Sainath, Tara, Rauh, Maribeth, Hashemi, Sayed Hadi, Ives, Richard, Hasson, Yana, Noland, Eric, Cao, Yuan, Byrd, Nathan, Hou, Le, Wang, Qingze, Sottiaux, Thibault, Paganini, Michela, Lespiau, Jean-Baptiste, Moufarek, Alexandre, Hassan, Samer, Shivakumar, Kaushik, van Amersfoort, Joost, Mandhane, Amol, Joshi, Pratik, Goyal, Anirudh, Tung, Matthew, Brock, Andrew, Sheahan, Hannah, Misra, Vedant, Li, Cheng, Rakićević, Nemanja, Dehghani, Mostafa, Liu, Fangyu, Mittal, Sid, Oh, Junhyuk, Noury, Seb, Sezener, Eren, Huot, Fantine, Lamm, Matthew, De Cao, Nicola, Chen, Charlie, Mudgal, Sidharth, Stella, Romina, Brooks, Kevin, Vasudevan, Gautam, Liu, Chenxi, Chain, Mainak, Melinkeri, Nivedita, Cohen, Aaron, Wang, Venus, Seymore, Kristie, Zubkov, Sergey, Goel, Rahul, Yue, Summer, Krishnakumaran, Sai, Albert, Brian, Hurley, Nate, Sano, Motoki, Mohananey, Anhad, Joughin, Jonah, Filonov, Egor, Kępa, Tomasz, Eldawy, Yomna, Lim, Jiawern, Rishi, Rahul, Badiezadegan, Shirin, Bos, Taylor, Chang, Jerry, Jain, Sanil, Padmanabhan, Sri Gayatri Sundara, Puttagunta, Subha, Krishna, Kalpesh, Baker, Leslie, Kalb, Norbert, Bedapudi, Vamsi, Kurzrok, Adam, Lei, Shuntong, Yu, Anthony, Litvin, Oren, Zhou, Xiang, Wu, Zhichun, Sobell, Sam, Siciliano, Andrea, Papir, Alan, Neale, Robby, Bragagnolo, Jonas, Toor, Tej, Chen, Tina, Anklin, Valentin, Wang, Feiran, Feng, Richie, Gholami, Milad, Ling, Kevin, Liu, Lijuan, Walter, Jules, Moghaddam, Hamid, Kishore, Arun, Adamek, Jakub, Mercado, Tyler, Mallinson, Jonathan, Wandekar, Siddhinita, Cagle, Stephen, Ofek, Eran, Garrido, Guillermo, Lombriser, Clemens, Mukha, Maksim, Sun, Botu, Mohammad, Hafeezul Rahman, Matak, Josip, Qian, Yadi, Peswani, Vikas, Janus, Pawel, Yuan, Quan, Schelin, Leif, David, Oana, Garg, Ankur, He, Yifan, Duzhyi, Oleksii, Älgmyr, Anton, Lottaz, Timothée, Li, Qi, Yadav, Vikas, Xu, Luyao, Chinien, Alex, Shivanna, Rakesh, Chuklin, Aleksandr, Li, Josie, Spadine, Carrie, Wolfe, Travis, Mohamed, Kareem, Das, Subhabrata, Dai, Zihang, He, Kyle, von Dincklage, Daniel, Upadhyay, Shyam, Maurya, Akanksha, Chi, Luyan, Krause, Sebastian, Salama, Khalid, Rabinovitch, Pam G, M, Pavan Kumar Reddy, Selvan, Aarush, Dektiarev, Mikhail, Ghiasi, Golnaz, Guven, Erdem, Gupta, Himanshu, Liu, Boyi, Sharma, Deepak, Shtacher, Idan Heimlich, Paul, Shachi, Akerlund, Oscar, Aubet, François-Xavier, Huang, Terry, Zhu, Chen, Zhu, Eric, Teixeira, Elico, Fritze, Matthew, Bertolini, Francesco, Marinescu, Liana-Eleonora, Bölle, Martin, Paulus, Dominik, Gupta, Khyatti, Latkar, Tejasi, Chang, Max, Sanders, Jason, Wilson, Roopa, Wu, Xuewei, Tan, Yi-Xuan, Thiet, Lam Nguyen, Doshi, Tulsee, Lall, Sid, Mishra, Swaroop, Chen, Wanming, Luong, Thang, Benjamin, Seth, Lee, Jasmine, Andrejczuk, Ewa, Rabiej, Dominik, Ranjan, Vipul, Styrc, Krzysztof, Yin, Pengcheng, Simon, Jon, Harriott, Malcolm Rose, Bansal, Mudit, Robsky, Alexei, Bacon, Geoff, Greene, David, Mirylenka, Daniil, Zhou, Chen, Sarvana, Obaid, Goyal, Abhimanyu, Andermatt, Samuel, Siegler, Patrick, Horn, Ben, Israel, Assaf, Pongetti, Francesco, Chen, Chih-Wei "Louis", Selvatici, Marco, Silva, Pedro, Wang, Kathie, Tolins, Jackson, Guu, Kelvin, Yogev, Roey, Cai, Xiaochen, Agostini, Alessandro, Shah, Maulik, Nguyen, Hung, Donnaile, Noah Ó, Pereira, Sébastien, Friso, Linda, Stambler, Adam, Kuang, Chenkai, Romanikhin, Yan, Geller, Mark, Yan, ZJ, Jang, Kane, Lee, Cheng-Chun, Fica, Wojciech, Malmi, Eric, Tan, Qijun, Banica, Dan, Balle, Daniel, Pham, Ryan, Huang, Yanping, Avram, Diana, Shi, Hongzhi, Singh, Jasjot, Hidey, Chris, Ahuja, Niharika, Saxena, Pranab, Dooley, Dan, Potharaju, Srividya Pranavi, O'Neill, Eileen, Gokulchandran, Anand, Foley, Ryan, Zhao, Kai, Dusenberry, Mike, Liu, Yuan, Mehta, Pulkit, Kotikalapudi, Ragha, Safranek-Shrader, Chalence, Goodman, Andrew, Kessinger, Joshua, Globen, Eran, Kolhar, Prateek, Gorgolewski, Chris, Ibrahim, Ali, Song, Yang, Eichenbaum, Ali, Brovelli, Thomas, Potluri, Sahitya, Lahoti, Preethi, Baetu, Cip, Ghorbani, Ali, Chen, Charles, Crawford, Andy, Pal, Shalini, Sridhar, Mukund, Gurita, Petru, Mujika, Asier, Petrovski, Igor, Cedoz, Pierre-Louis, Li, Chenmei, Chen, Shiyuan, Santo, Niccolò Dal, Goyal, Siddharth, Punjabi, Jitesh, Kappaganthu, Karthik, Kwak, Chester, LV, Pallavi, Velury, Sarmishta, Choudhury, Himadri, Hall, Jamie, Shah, Premal, Figueira, Ricardo, Thomas, Matt, Lu, Minjie, Zhou, Ting, Kumar, Chintu, Jurdi, Thomas, Chikkerur, Sharat, Ma, Yenai, Yu, Adams, Kwak, Soo, Ähdel, Victor, Rajayogam, Sujeevan, Choma, Travis, Liu, Fei, Barua, Aditya, Ji, Colin, Park, Ji Ho, Hellendoorn, Vincent, Bailey, Alex, Bilal, Taylan, Zhou, Huanjie, Khatir, Mehrdad, Sutton, Charles, Rzadkowski, Wojciech, Macintosh, Fiona, Shagin, Konstantin, Medina, Paul, Liang, Chen, Zhou, Jinjing, Shah, Pararth, Bi, Yingying, Dankovics, Attila, Banga, Shipra, Lehmann, Sabine, Bredesen, Marissa, Lin, Zifan, Hoffmann, John Eric, Lai, Jonathan, Chung, Raynald, Yang, Kai, Balani, Nihal, Bražinskas, Arthur, Sozanschi, Andrei, Hayes, Matthew, Alcalde, Héctor Fernández, Makarov, Peter, Chen, Will, Stella, Antonio, Snijders, Liselotte, Mandl, Michael, Kärrman, Ante, Nowak, Paweł, Wu, Xinyi, Dyck, Alex, Vaidyanathan, Krishnan, R, Raghavender, Mallet, Jessica, Rudominer, Mitch, Johnston, Eric, Mittal, Sushil, Udathu, Akhil, Christensen, Janara, Verma, Vishal, Irving, Zach, Santucci, Andreas, Elsayed, Gamaleldin, Davoodi, Elnaz, Georgiev, Marin, Tenney, Ian, Hua, Nan, Cideron, Geoffrey, Leurent, Edouard, Alnahlawi, Mahmoud, Georgescu, Ionut, Wei, Nan, Zheng, Ivy, Scandinaro, Dylan, Jiang, Heinrich, Snoek, Jasper, Sundararajan, Mukund, Wang, Xuezhi, Ontiveros, Zack, Karo, Itay, Cole, Jeremy, Rajashekhar, Vinu, Tumeh, Lara, Ben-David, Eyal, Jain, Rishub, Uesato, Jonathan, Datta, Romina, Bunyan, Oskar, Wu, Shimu, Zhang, John, Stanczyk, Piotr, Zhang, Ye, Steiner, David, Naskar, Subhajit, Azzam, Michael, Johnson, Matthew, Paszke, Adam, Chiu, Chung-Cheng, Elias, Jaume Sanchez, Mohiuddin, Afroz, Muhammad, Faizan, Miao, Jin, Lee, Andrew, Vieillard, Nino, Park, Jane, Zhang, Jiageng, Stanway, Jeff, Garmon, Drew, Karmarkar, Abhijit, Dong, Zhe, Lee, Jong, Kumar, Aviral, Zhou, Luowei, Evens, Jonathan, Isaac, William, Irving, Geoffrey, Loper, Edward, Fink, Michael, Arkatkar, Isha, Chen, Nanxin, Shafran, Izhak, Petrychenko, Ivan, Chen, Zhe, Jia, Johnson, Levskaya, Anselm, Zhu, Zhenkai, Grabowski, Peter, Mao, Yu, Magni, Alberto, Yao, Kaisheng, Snaider, Javier, Casagrande, Norman, Palmer, Evan, Suganthan, Paul, Castaño, Alfonso, Giannoumis, Irene, Kim, Wooyeol, Rybiński, Mikołaj, Sreevatsa, Ashwin, Prendki, Jennifer, Soergel, David, Goedeckemeyer, Adrian, Gierke, Willi, Jafari, Mohsen, Gaba, Meenu, Wiesner, Jeremy, Wright, Diana Gage, Wei, Yawen, Vashisht, Harsha, Kulizhskaya, Yana, Hoover, Jay, Le, Maigo, Li, Lu, Iwuanyanwu, Chimezie, Liu, Lu, Ramirez, Kevin, Khorlin, Andrey, Cui, Albert, LIN, Tian, Wu, Marcus, Aguilar, Ricardo, Pallo, Keith, Chakladar, Abhishek, Perng, Ginger, Abellan, Elena Allica, Zhang, Mingyang, Dasgupta, Ishita, Kushman, Nate, Penchev, Ivo, Repina, Alena, Wu, Xihui, van der Weide, Tom, Ponnapalli, Priya, Kaplan, Caroline, Simsa, Jiri, Li, Shuangfeng, Dousse, Olivier, Piper, Jeff, Ie, Nathan, Pasumarthi, Rama, Lintz, Nathan, Vijayakumar, Anitha, Andor, Daniel, Valenzuela, Pedro, Lui, Minnie, Paduraru, Cosmin, Peng, Daiyi, Lee, Katherine, Zhang, Shuyuan, Greene, Somer, Nguyen, Duc Dung, Kurylowicz, Paula, Hardin, Cassidy, Dixon, Lucas, Janzer, Lili, Choo, Kiam, Feng, Ziqiang, Zhang, Biao, Singhal, Achintya, Du, Dayou, McKinnon, Dan, Antropova, Natasha, Bolukbasi, Tolga, Keller, Orgad, Reid, David, Finchelstein, Daniel, Raad, Maria Abi, Crocker, Remi, Hawkins, Peter, Dadashi, Robert, Gaffney, Colin, Franko, Ken, Bulanova, Anna, Leblond, Rémi, Chung, Shirley, Askham, Harry, Cobo, Luis C., Xu, Kelvin, Fischer, Felix, Xu, Jun, Sorokin, Christina, Alberti, Chris, Lin, Chu-Cheng, Evans, Colin, Dimitriev, Alek, Forbes, Hannah, Banarse, Dylan, Tung, Zora, Omernick, Mark, Bishop, Colton, Sterneck, Rachel, Jain, Rohan, Xia, Jiawei, Amid, Ehsan, Piccinno, Francesco, Wang, Xingyu, Banzal, Praseem, Mankowitz, Daniel J., Polozov, Alex, Krakovna, Victoria, Brown, Sasha, Bateni, MohammadHossein, Duan, Dennis, Firoiu, Vlad, Thotakuri, Meghana, Natan, Tom, Geist, Matthieu, Girgin, Ser tan, Li, Hui, Ye, Jiayu, Roval, Ofir, Tojo, Reiko, Kwong, Michael, Lee-Thorp, James, Yew, Christopher, Sinopalnikov, Danila, Ramos, Sabela, Mellor, John, Sharma, Abhishek, Wu, Kathy, Miller, David, Sonnerat, Nicolas, Vnukov, Denis, Greig, Rory, Beattie, Jennifer, Caveness, Emily, Bai, Libin, Eisenschlos, Julian, Korchemniy, Alex, Tsai, Tomy, Jasarevic, Mimi, Kong, Weize, Dao, Phuong, Zheng, Zeyu, Liu, Frederick, Zhu, Rui, Teh, Tian Huey, Sanmiya, Jason, Gladchenko, Evgeny, Trdin, Nejc, Toyama, Daniel, Rosen, Evan, Tavakkol, Sasan, Xue, Linting, Elkind, Chen, Woodman, Oliver, Carpenter, John, Papamakarios, George, Kemp, Rupert, Kafle, Sushant, Grunina, Tanya, Sinha, Rishika, Talbert, Alice, Wu, Diane, Owusu-Afriyie, Denese, Thornton, Chloe, Pont-Tuset, Jordi, Narayana, Pradyumna, Li, Jing, Fatehi, Saaber, Wieting, John, Ajmeri, Omar, Uria, Benigno, Ko, Yeongil, Knight, Laura, Héliou, Amélie, Niu, Ning, Gu, Shane, Pang, Chenxi, Li, Yeqing, Levine, Nir, Stolovich, Ariel, Santamaria-Fernandez, Rebeca, Goenka, Sonam, Yustalim, Wenny, Strudel, Robin, Elqursh, Ali, Deck, Charlie, Lee, Hyo, Li, Zonglin, Levin, Kyle, Hoffmann, Raphael, Holtmann-Rice, Dan, Bachem, Olivier, Arora, Sho, Koh, Christy, Yeganeh, Soheil Hassas, Põder, Siim, Tariq, Mukarram, Sun, Yanhua, Ionita, Lucian, Seyedhosseini, Mojtaba, Tafti, Pouya, Liu, Zhiyu, Gulati, Anmol, Liu, Jasmine, Ye, Xinyu, Chrzaszcz, Bart, Wang, Lily, Sethi, Nikhil, Li, Tianrun, Brown, Ben, Singh, Shreya, Fan, Wei, Parisi, Aaron, Stanton, Joe, Koverkathu, Vinod, Choquette-Choo, Christopher A., Li, Yunjie, Lu, TJ, Shroff, Prakash, Varadarajan, Mani, Bahargam, Sanaz, Willoughby, Rob, Gaddy, David, Desjardins, Guillaume, Cornero, Marco, Robenek, Brona, Mittal, Bhavishya, Albrecht, Ben, Shenoy, Ashish, Moiseev, Fedor, Jacobsson, Henrik, Ghaffarkhah, Alireza, Rivière, Morgane, Walton, Alanna, Crepy, Clément, Parrish, Alicia, Zhou, Zongwei, Farabet, Clement, Radebaugh, Carey, Srinivasan, Praveen, van der Salm, Claudia, Fidjeland, Andreas, Scellato, Salvatore, Latorre-Chimoto, Eri, Klimczak-Plucińska, Hanna, Bridson, David, de Cesare, Dario, Hudson, Tom, Mendolicchio, Piermaria, Walker, Lexi, Morris, Alex, Mauger, Matthew, Guseynov, Alexey, Reid, Alison, Odoom, Seth, Loher, Lucia, Cotruta, Victor, Yenugula, Madhavi, Grewe, Dominik, Petrushkina, Anastasia, Duerig, Tom, Sanchez, Antonio, Yadlowsky, Steve, Shen, Amy, Globerson, Amir, Webb, Lynette, Dua, Sahil, Li, Dong, Bhupatiraju, Surya, Hurt, Dan, Qureshi, Haroon, Agarwal, Ananth, Shani, Tomer, Eyal, Matan, Khare, Anuj, Belle, Shreyas Rammohan, Wang, Lei, Tekur, Chetan, Kale, Mihir Sanjay, Wei, Jinliang, Sang, Ruoxin, Saeta, Brennan, Liechty, Tyler, Sun, Yi, Zhao, Yao, Lee, Stephan, Nayak, Pandu, Fritz, Doug, Vuyyuru, Manish Reddy, Aslanides, John, Vyas, Nidhi, Wicke, Martin, Ma, Xiao, Eltyshev, Evgenii, Martin, Nina, Cate, Hardie, Manyika, James, Amiri, Keyvan, Kim, Yelin, Xiong, Xi, Kang, Kai, Luisier, Florian, Tripuraneni, Nilesh, Madras, David, Guo, Mandy, Waters, Austin, Wang, Oliver, Ainslie, Joshua, Baldridge, Jason, Zhang, Han, Pruthi, Garima, Bauer, Jakob, Yang, Feng, Mansour, Riham, Gelman, Jason, Xu, Yang, Polovets, George, Liu, Ji, Cai, Honglong, Chen, Warren, Sheng, XiangHai, Xue, Emily, Ozair, Sherjil, Angermueller, Christof, Li, Xiaowei, Sinha, Anoop, Wang, Weiren, Wiesinger, Julia, Koukoumidis, Emmanouil, Tian, Yuan, Iyer, Anand, Gurumurthy, Madhu, Goldenson, Mark, Shah, Parashar, Blake, MK, Yu, Hongkun, Urbanowicz, Anthony, Palomaki, Jennimaria, Fernando, Chrisantha, Durden, Ken, Mehta, Harsh, Momchev, Nikola, Rahimtoroghi, Elahe, Georgaki, Maria, Raul, Amit, Ruder, Sebastian, Redshaw, Morgan, Lee, Jinhyuk, Zhou, Denny, Jalan, Komal, Li, Dinghua, Hechtman, Blake, Schuh, Parker, Nasr, Milad, Milan, Kieran, Mikulik, Vladimir, Franco, Juliana, Green, Tim, Nguyen, Nam, Kelley, Joe, Mahendru, Aroma, Hu, Andrea, Howland, Joshua, Vargas, Ben, Hui, Jeffrey, Bansal, Kshitij, Rao, Vikram, Ghiya, Rakesh, Wang, Emma, Ye, Ke, Sarr, Jean Michel, Preston, Melanie Moranski, Elish, Madeleine, Li, Steve, Kaku, Aakash, Gupta, Jigar, Pasupat, Ice, Juan, Da-Cheng, Someswar, Milan, M., Tejvi, Chen, Xinyun, Amini, Aida, Fabrikant, Alex, Chu, Eric, Dong, Xuanyi, Muthal, Amruta, Buthpitiya, Senaka, Jauhari, Sarthak, Khandelwal, Urvashi, Hitron, Ayal, Ren, Jie, Rinaldi, Larissa, Drath, Shahar, Dabush, Avigail, Jiang, Nan-Jiang, Godhia, Harshal, Sachs, Uli, Chen, Anthony, Fan, Yicheng, Taitelbaum, Hagai, Noga, Hila, Dai, Zhuyun, Wang, James, Hamer, Jenny, Ferng, Chun-Sung, Elkind, Chenel, Atias, Aviel, Lee, Paulina, Listík, Vít, Carlen, Mathias, van de Kerkhof, Jan, Pikus, Marcin, Zaher, Krunoslav, Müller, Paul, Zykova, Sasha, Stefanec, Richard, Gatsko, Vitaly, Hirnschall, Christoph, Sethi, Ashwin, Xu, Xingyu Federico, Ahuja, Chetan, Tsai, Beth, Stefanoiu, Anca, Feng, Bo, Dhandhania, Keshav, Katyal, Manish, Gupta, Akshay, Parulekar, Atharva, Pitta, Divya, Zhao, Jing, Bhatia, Vivaan, Bhavnani, Yashodha, Alhadlaq, Omar, Li, Xiaolin, Danenberg, Peter, Tu, Dennis, Pine, Alex, Filippova, Vera, Ghosh, Abhipso, Limonchik, Ben, Urala, Bhargava, Lanka, Chaitanya Krishna, Clive, Derik, Li, Edward, Wu, Hao, Hongtongsak, Kevin, Li, Ianna, Thakkar, Kalind, Omarov, Kuanysh, Majmundar, Kushal, Alverson, Michael, Kucharski, Michael, Patel, Mohak, Jain, Mudit, Zabelin, Maksim, Pelagatti, Paolo, Kohli, Rohan, Kumar, Saurabh, Kim, Joseph, Sankar, Swetha, Shah, Vineet, Ramachandruni, Lakshmi, Zeng, Xiangkai, Bariach, Ben, Weidinger, Laura, Vu, Tu, Andreev, Alek, He, Antoine, Hui, Kevin, Kashem, Sheleem, Subramanya, Amar, Hsiao, Sissie, Hassabis, Demis, Kavukcuoglu, Koray, Sadovsky, Adam, Le, Quoc, Strohman, Trevor, Wu, Yonghui, Petrov, Slav, Dean, Jeffrey, and Vinyals, Oriol

Subjects
Computer Science - Computation and Language, Computer Science - Artificial Intelligence, Computer Science - Computer Vision and Pattern Recognition
Abstract

This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding. The Gemini family consists of Ultra, Pro, and Nano sizes, suitable for applications ranging from complex reasoning tasks to on-device memory-constrained use-cases. Evaluation on a broad range of benchmarks shows that our most-capable Gemini Ultra model advances the state of the art in 30 of 32 of these benchmarks - notably being the first model to achieve human-expert performance on the well-studied exam benchmark MMLU, and improving the state of the art in every one of the 20 multimodal benchmarks we examined. We believe that the new capabilities of the Gemini family in cross-modal reasoning and language understanding will enable a wide variety of use cases. We discuss our approach toward post-training and deploying Gemini models responsibly to users through services including Gemini, Gemini Advanced, Google AI Studio, and Cloud Vertex AI.

Published
2023

11. SiRA: Sparse Mixture of Low Rank Adaptation

Author

Zhu, Yun, Wichers, Nevan, Lin, Chu-Cheng, Wang, Xinyi, Chen, Tianlong, Shu, Lei, Lu, Han, Liu, Canoee, Luo, Liangchen, Chen, Jindong, and Meng, Lei

Subjects
Computer Science - Computation and Language
Abstract

Parameter Efficient Tuning has been an prominent approach to adapt the Large Language Model to downstream tasks. Most previous works considers adding the dense trainable parameters, where all parameters are used to adapt certain task. We found this less effective empirically using the example of LoRA that introducing more trainable parameters does not help. Motivated by this we investigate the importance of leveraging "sparse" computation and propose SiRA: sparse mixture of low rank adaption. SiRA leverages the Sparse Mixture of Expert(SMoE) to boost the performance of LoRA. Specifically it enforces the top $k$ experts routing with a capacity limit restricting the maximum number of tokens each expert can process. We propose a novel and simple expert dropout on top of gating network to reduce the over-fitting issue. Through extensive experiments, we verify SiRA performs better than LoRA and other mixture of expert approaches across different single tasks and multitask settings.

Published
2023

16. USM-SCD: Multilingual Speaker Change Detection Based on Large Pretrained Foundation Models

Author

Zhao, Guanlong, Wang, Yongqiang, Pelecanos, Jason, Zhang, Yu, Liao, Hank, Huang, Yiling, Lu, Han, and Wang, Quan

Subjects
Electrical Engineering and Systems Science - Audio and Speech Processing, Computer Science - Machine Learning, Computer Science - Sound
Abstract

We introduce a multilingual speaker change detection model (USM-SCD) that can simultaneously detect speaker turns and perform ASR for 96 languages. This model is adapted from a speech foundation model trained on a large quantity of supervised and unsupervised data, demonstrating the utility of fine-tuning from a large generic foundation model for a downstream task. We analyze the performance of this multilingual speaker change detection model through a series of ablation studies. We show that the USM-SCD model can achieve more than 75% average speaker change detection F1 score across a test set that consists of data from 96 languages. On American English, the USM-SCD model can achieve an 85.8% speaker change detection F1 score across various public and internal test sets, beating the previous monolingual baseline model by 21% relative. We also show that we only need to fine-tune one-quarter of the trainable model parameters to achieve the best model performance. The USM-SCD model exhibits state-of-the-art ASR quality compared with a strong public ASR baseline, making it suitable to handle both tasks with negligible additional computational cost., Comment: 5 pages, 2 figures, 4 tables

Published
2023

17. DTAIS: Distributed trusted active identity resolution systems for the Industrial Internet

Author

Tao Huang, Renchao Xie, Yuzheng Ren, F. Richard Yu, Zhuang Zou, Lu Han, Yunjie Liu, Demin Cheng, Yinan Li, and Tian Liu

Subjects
Industrial Internet, NFT, IPFS, Trust, Identity resolution system, Information technology, T58.5-58.64
Abstract

In recent years, the Industrial Internet and Industry 4.0 came into being. With the development of modern industrial intelligent manufacturing technology, digital twins, Web3 and many other digital entity applications are also proposed. These applications apply architectures such as distributed learning, resource sharing, and arithmetic trading, which make high demands on identity authentication, asset authentication, resource addressing, and service location. Therefore, an efficient, secure, and trustworthy Industrial Internet identity resolution system is needed. However, most of the traditional identity resolution systems follow DNS architecture or tree structure, which has the risk of a single point of failure and DDoS attack. And they cannot guarantee the security and privacy of digital identity, personal assets, and device information. So we consider a decentralized approach for identity management, identity authentication, and asset verification. In this paper, we propose a distributed trusted active identity resolution system based on the inter-planetary file system (IPFS) and non-fungible token (NFT), which can provide distributed identity resolution services. And we have designed the system architecture, identity service process, load balancing strategy and smart contract service. In addition, we use Jmeter to verify the performance of the system, and the results show that the system has good high concurrent performance and robustness.

Published
2024
Full Text
View/download PDF

18. Quality characterization of tobacco flavor and tobacco leaf position identification based on homemade electronic nose

Author

Hao Li, Qiuling Wang, Lu Han, Zhifei Chen, Genfa Wang, Qingfu Wang, Shengtao Ma, Bin Ai, and Gaolei Xi

Subjects
Electronic nose, Tobacco extract, Tobacco leaf, Machine learning, Sensor, Medicine, Science
Abstract

Abstract A set of nine unique tobacco extract samples was analyzed using a self-developed electronic nose (E-nose) system, a commercial E-nose, and gas chromatography-mass spectrometry (GC–MS). The evaluation employed principal component analysis, statistical quality control, and soft independent modeling of class analogies (SIMCA). These multifaceted statistical methods scrutinized the collected data. Subsequently, a quality control model was devised to assess the stability of the sample quality. The results showed that the custom E-nose system could successfully distinguish between tobacco extracts with similar odors. After further training and the development of a quality control model for accepted tobacco extracts, it was possible to identify samples with normal and abnormal quality. To further validate our E-nose and extend its use within the tobacco industry, we collected and accurately classified the flavors of different tobacco leaf positions, with a remarkable accuracy rate of 0.9744. This finding facilitates the practical application of our E-nose system for the efficient identification of tobacco leaf positions.

Published
2024
Full Text
View/download PDF

19. White matter structure and derived network properties are used to predict the progression from mild cognitive impairment of older adults to Alzheimer’s disease

Author

Jiaxuan Peng, Guangying Zheng, Mengmeng Hu, Zihan Zhang, Zhongyu Yuan, Yuyun Xu, Yuan Shao, Yang Zhang, Xiaojun Sun, Lu Han, Xiaokai Gu, Zhenyu Shu, and for the Alzheimer’s Disease Neuroimaging Initiative

Subjects
Diffusion Tensor Imaging, White matter microstructure, Mild Cognitive Impairment, Alzheimer’s Disease, Machine learning, Geriatrics, RC952-954.6
Abstract

Abstract Objective To identify white matter fiber injury and network changes that may lead to mild cognitive impairment (MCI) progression, then a joint model was constructed based on neuropsychological scales to predict high-risk individuals for Alzheimer's disease (AD) progression among older adults with MCI. Methods A total of 173 MCI patients were included from the Alzheimer's Disease Neuroimaging Initiative(ADNI) database and randomly divided into training and testing cohorts. Forty-five progressed to AD during a 4-year follow-up period. Diffusion tensor imaging (DTI) techniques extracted relevant DTI quantitative features for each patient. In addition, brain networks were constructed based on white matter fiber bundles to extract network property features. Ensemble dimensionality reduction was applied to reduce both DTI quantitative features and network features from the training cohort, and machine learning algorithms were added to construct white matter signature. In addition, 52 patients from the National Alzheimer's Coordinating Center (NACC) database were used for external validation of white matter signature. A joint model was subsequently generated by combining with scale scores, and its performance was evaluated using data from the testing cohort. Results Based on multivariate logistic regression, clinical dementia rating and Alzheimer’s disease assessment scales (CDRS and ADAS, respectively) were selected as independent predictive factors. A joint model was constructed in combination with the white matter signature. The AUC, sensitivity, and specificity in the training cohort were 0.938, 0.937, and 0.91, respectively, and the AUC, sensitivity, and specificity in the test cohort were 0.905, 0.923, and 0.872, respectively. The Delong test showed a statistically significant difference between the joint model and CDRS or ADAS scores (P

Published
2024
Full Text
View/download PDF

20. DeepRisk: A deep learning approach for genome-wide assessment of common disease risk

Author

Jiajie Peng, Zhijie Bao, Jingyi Li, Ruijiang Han, Yuxian Wang, Lu Han, Jinghao Peng, Tao Wang, Jianye Hao, Zhongyu Wei, and Xuequn Shang

Subjects
Disease risk prediction, Deep learning, Polygenic risk score, Common disease risk, Disease prevention, Science (General), Q1-390
Abstract

The potential for being able to identify individuals at high disease risk solely based on genotype data has garnered significant interest. Although widely applied, traditional polygenic risk scoring methods fall short, as they are built on additive models that fail to capture the intricate associations among single nucleotide polymorphisms (SNPs). This presents a limitation, as genetic diseases often arise from complex interactions between multiple SNPs. To address this challenge, we developed DeepRisk, a biological knowledge-driven deep learning method for modeling these complex, nonlinear associations among SNPs, to provide a more effective method for scoring the risk of common diseases with genome-wide genotype data. Evaluations demonstrated that DeepRisk outperforms existing PRS-based methods in identifying individuals at high risk for four common diseases: Alzheimer's disease, inflammatory bowel disease, type 2 diabetes, and breast cancer.

Published
2024
Full Text
View/download PDF

21. Associations between the oxidative balance score and constipation: a cross-sectional study of the NHANES, 2005–2010

Author

Yuchao Wang, Jiao Li, Wei Sun, Yunbin Tong, Lu Han, Ziying Jiang, Weili Xu, and Daqing Sun

Subjects
Oxidative Balance Score, Constipation, Oxidative Stress, NHANES, Public aspects of medicine, RA1-1270
Abstract

Abstracts Objective The oxidative balance score (OBS) reflects the overall burden of oxidative stress in an individual, with a higher OBS indicating greater antioxidant exposure. This study aimed to explore the association between constipation and OBS. Methods Variables were extracted from participants who completed a constipation questionnaire as part of the National Health and Nutrition Examination Survey (NHANES) from 2005 to 2010. The OBS was developed based on dietary and lifestyle factors, encompassing 16 nutrients and 4 lifestyle variables. Weighted logistic regression and restricted cubic spline (RCS) analyses were employed to evaluate the association between OBS and constipation. Results After adjusting for all covariates, weighted multivariate logistic regression analysis revealed a 4% reduction in the incidence of constipation for each additional unit of OBS (OR: 0.96, 95% CI: 0.95–0.97, p

Published
2024
Full Text
View/download PDF

22. Short-term OS as a surrogate endpoint for 5-year OS in nasopharyngeal carcinoma in non-endemic area

Author

Ying Guan, Lu Han, Han-Yin Luo, Bin-Bin Yu, and Shi-Ting Huang

Subjects
Surrogate endpoint, Nasopharyngeal carcinoma, Short-term endpoints, Overall survival, SEER, Surgery, RD1-811, Neoplasms. Tumors. Oncology. Including cancer and carcinogens, RC254-282
Abstract

Abstract Purpose To address this evidence gap and validate short-term OS at less than 5 years as a reliable surrogate endpoint for 5-year OS. Methods We analyzed data from the Surveillance, Epidemiology, and End Results (SEER) database, focusing on non-metastatic NPC patients diagnosed between 2010 and 2015. Patients were categorized into radiotherapy and chemoradiotherapy groups. Results This retrospective study examined 2,047 non-metastatic NPC patients. Among them, 217 received radiotherapy, and 1,830 received chemoradiotherapy. Our analysis results indicated that the 4-year OS may serve as a reliable surrogate endpoint for patients with AJCC clinical stage I (80 vs. 78%, P = 0.250), regardless of the treatment received. Specifically, in the radiotherapy group, patients with stage I, T0-T1, and N0 NPC showed similar OS rates at 4 and 5 years (83 vs. 82%, P = 1.000; 78 vs. 76%, P = 0.250; 78 vs. 77%, P = 0.500, respectively). Similarly, patients with stage II-IV, T2-T4, and N1-3 NPC showed no significant difference in OS rates between 3 and 5 years (57 vs. 51%, P = 0.063; 52 vs. 46%, P = 0.250; 54 vs. 46%, P = 0.125, respectively) in the radiotherapy group. In the chemoradiotherapy group, only the 3-year OS rate did not significantly differ from that at 5 years in stage I patients (79vs. 72%, P = 0.063). Conclusions Our study suggests that short-term surrogate endpoints may be valuable for evaluating 5-year OS outcomes in NPC patients in non-endemic areas.

Published
2024
Full Text
View/download PDF

23. An novel effective and safe model for the diagnosis of nonalcoholic fatty liver disease in China: gene excavations, clinical validations, and mechanism elucidation

Author

Jida Wang, Beitian Jia, Jing Miao, Dun Li, Yin Wang, Lu Han, Yin Yuan, Yuan Zhang, Yiyang Wang, Liying Guo, Jianwei Jia, Fang Zheng, Sizhen Lai, Kaijun Niu, Weidong Li, Yuhong Bian, and Yaogang Wang

Subjects
Nonalcoholic fatty liver disease, Machine learning, Biomarkers, Medicine
Abstract

Abstract Background Non-alcoholic fatty liver disease (NAFLD) is one of the most common chronic liver diseases. NAFLD leads to liver fibrosis and hepatocellular carcinoma, and it also has systemic effects associated with metabolic diseases, cardiovascular diseases, chronic kidney disease, and malignant tumors. Therefore, it is important to diagnose NAFLD early to prevent these adverse effects. Methods The GSE89632 dataset was downloaded from the Gene Expression Omnibus database, and then the optimal genes were screened from the data cohort using lasso and Support Vector Machine Recursive Feature Elimination (SVM-RFE). The ROC values of the optimal genes for the diagnosis of NAFLD were calculated. The relationship between optimal genes and immune cells was determined using the DECONVOLUTION algorithm CIBERSORT. Finally, the specificity and sensitivity of the diagnostic genes were verified by detecting the expression of the diagnostic genes in blood samples from 320 NAFLD patients and liver samples from 12 mice. Results Through machine learning we identified FOSB, GPAT3, RGCC and RNF43 were the key diagnostic genes for NAFLD, and they were further demonstrated by a receiver operating characteristic curve analysis. We found that the combined diagnosis of the four genes identified NAFLD samples well from normal samples (AUC = 0.997). FOSB, GPAT3, RGCC and RNF43 were strongly associated with immune cell infiltration. We also experimentally examined the expression of these genes in NAFLD patients and NAFLD mice, and the results showed that these genes are highly specific and sensitive. Conclusions Data from both clinical and animal studies demonstrate the high sensitivity, specificity and safety of FOSB, GPAT3, RGCC and RNF43 for the diagnosis of NAFLD. The relationship between diagnostic key genes and immune cell infiltration may help to understand the development of NAFLD. The study was reviewed and approved by Ethics Committee of Tianjin Second People’s Hospital in 2021 (ChiCTR1900024415).

Published
2024
Full Text
View/download PDF

24. Rethinking k-means from manifold learning perspective

Author

Gao, Quanxue, Wang, Qianqian, Lu, Han, Xia, Wei, and Gao, Xinbo

Subjects
Computer Science - Machine Learning
Abstract

Although numerous clustering algorithms have been developed, many existing methods still leverage k-means technique to detect clusters of data points. However, the performance of k-means heavily depends on the estimation of centers of clusters, which is very difficult to achieve an optimal solution. Another major drawback is that it is sensitive to noise and outlier data. In this paper, from manifold learning perspective, we rethink k-means and present a new clustering algorithm which directly detects clusters of data without mean estimation. Specifically, we construct distance matrix between data points by Butterworth filter such that distance between any two data points in the same clusters equals to a small constant, while increasing the distance between other data pairs from different clusters. To well exploit the complementary information embedded in different views, we leverage the tensor Schatten p-norm regularization on the 3rd-order tensor which consists of indicator matrices of different views. Finally, an efficient alternating algorithm is derived to optimize our model. The constructed sequence was proved to converge to the stationary KKT point. Extensive experimental results indicate the superiority of our proposed method.

Published
2023

25. Scalable Randomized Kernel Methods for Multiview Data Integration and Prediction

Author

Safo, Sandra E. and Lu, Han

Subjects
Statistics - Methodology, Statistics - Applications, Statistics - Machine Learning
Abstract

We develop scalable randomized kernel methods for jointly associating data from multiple sources and simultaneously predicting an outcome or classifying a unit into one of two or more classes. The proposed methods model nonlinear relationships in multiview data together with predicting a clinical outcome and are capable of identifying variables or groups of variables that best contribute to the relationships among the views. We use the idea that random Fourier bases can approximate shift-invariant kernel functions to construct nonlinear mappings of each view and we use these mappings and the outcome variable to learn view-independent low-dimensional representations. Through simulation studies, we show that the proposed methods outperform several other linear and nonlinear methods for multiview data integration. When the proposed methods were applied to gene expression, metabolomics, proteomics, and lipidomics data pertaining to COVID-19, we identified several molecular signatures forCOVID-19 status and severity. Results from our real data application and simulations with small sample sizes suggest that the proposed methods may be useful for small sample size problems. Availability: Our algorithms are implemented in Pytorch and interfaced in R and would be made available at: https://github.com/lasandrall/RandMVLearn., Comment: 24 pages, 5 figures, 4 tables

Published
2023

26. Plant-inspired visible-light-driven bioenergetic hydrogels for chronic wound healing

Author

Yuping Jiang, Xiaomin Feng, Xin Qiao, Yufeng Li, Xiaozhuang Li, Jinguang Yang, and Lu Han

Subjects
Polyphenol nanoparticles, Photosynthetic thylakoid, Inflammation regulation, Diabetic wound repairing, Hydrogel, Materials of engineering and construction. Mechanics of materials, TA401-492, Biology (General), QH301-705.5
Abstract

Chronic bioenergetic imbalances and inflammation caused by hyperglycemia are obstacles that delay diabetic wound healing. However, it is difficult to directly deliver energy and metabolites to regulate intracellular energy metabolism using biomaterials. Herein, we propose a light-driven bioenergetic and oxygen-releasing hydrogel (PTKM@HG) that integrates the thylakoid membrane-encapsulated polyphenol nanoparticles (PTKM NPs) to regulate the energy metabolism and inflammatory response in diabetic wounds. Upon red light irradiation, the PTKM NPs exhibited oxygen generation and H2O2 deletion capacity through a photosynthetic effect to restore hypoxia-induced mitochondrial dysfunction. Meanwhile, the PTKM NPs could produce exogenous ATP and NADPH to enhance mitochondrial function and facilitate cellular anabolism by regulating the leucine-activated mTOR signaling pathway. Furthermore, the PTKM NPs inherited antioxidative and anti-inflammatory ability from polyphenol. Finally, the red light irradiated PTKM@HG hydrogel augmented the survival and migration of cells keratinocytes, and then accelerated angiogenesis and re-epithelialization of diabetic wounds. In short, this study provides possibilities for effectively treating diseases by delivering key metabolites and energy based on such a light-driven bioenergetic hydrogel.

Published
2024
Full Text
View/download PDF

28. Research on the Impact of Digital Business Environment on Enterprises' Innovation Capability

Author

Li, Rongping, Lu, Han, Zheng, Zheng, Editor-in-Chief, Xi, Zhiyu, Associate Editor, Gong, Siqian, Series Editor, Hong, Wei-Chiang, Series Editor, Mellal, Mohamed Arezki, Series Editor, Narayanan, Ramadas, Series Editor, Nguyen, Quang Ngoc, Series Editor, Ong, Hwai Chyuan, Series Editor, Sun, Zaicheng, Series Editor, Ullah, Sharif, Series Editor, Wu, Junwei, Series Editor, Zhang, Baochang, Series Editor, Zhang, Wei, Series Editor, Zhu, Quanxin, Series Editor, Zheng, Wei, Series Editor, Rauf, Abdul, editor, Zakuan, Norhayati, editor, Sohail, Muhammad Tayyab, editor, and Azmi, Ruzita, editor

Published
2024
Full Text
View/download PDF

31. Active Finetuning: Exploiting Annotation Budget in the Pretraining-Finetuning Paradigm

Author

Xie, Yichen, Lu, Han, Yan, Junchi, Yang, Xiaokang, Tomizuka, Masayoshi, and Zhan, Wei

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning
Abstract

Given the large-scale data and the high annotation cost, pretraining-finetuning becomes a popular paradigm in multiple computer vision tasks. Previous research has covered both the unsupervised pretraining and supervised finetuning in this paradigm, while little attention is paid to exploiting the annotation budget for finetuning. To fill in this gap, we formally define this new active finetuning task focusing on the selection of samples for annotation in the pretraining-finetuning paradigm. We propose a novel method called ActiveFT for active finetuning task to select a subset of data distributing similarly with the entire unlabeled pool and maintaining enough diversity by optimizing a parametric model in the continuous space. We prove that the Earth Mover's distance between the distributions of the selected subset and the entire data pool is also reduced in this process. Extensive experiments show the leading performance and high efficiency of ActiveFT superior to baselines on both image classification and semantic segmentation. Our code is released at https://github.com/yichen928/ActiveFT., Comment: Accepted by CVPR 2023

Published
2023

32. Interpretable Deep Learning Methods for Multiview Learning

Author

Wang, Hengkang, Lu, Han, Sun, Ju, and Safo, Sandra E

Subjects
Computer Science - Machine Learning, Statistics - Methodology, Statistics - Machine Learning
Abstract

Technological advances have enabled the generation of unique and complementary types of data or views (e.g. genomics, proteomics, metabolomics) and opened up a new era in multiview learning research with the potential to lead to new biomedical discoveries. We propose iDeepViewLearn (Interpretable Deep Learning Method for Multiview Learning) for learning nonlinear relationships in data from multiple views while achieving feature selection. iDeepViewLearn combines deep learning flexibility with the statistical benefits of data and knowledge-driven feature selection, giving interpretable results. Deep neural networks are used to learn view-independent low-dimensional embedding through an optimization problem that minimizes the difference between observed and reconstructed data, while imposing a regularization penalty on the reconstructed data. The normalized Laplacian of a graph is used to model bilateral relationships between variables in each view, therefore, encouraging selection of related variables. iDeepViewLearn is tested on simulated and two real-world data, including breast cancer-related gene expression and methylation data. iDeepViewLearn had competitive classification results and identified genes and CpG sites that differentiated between individuals who died from breast cancer and those who did not. The results of our real data application and simulations with small to moderate sample sizes suggest that iDeepViewLearn may be a useful method for small-sample-size problems compared to other deep learning methods for multiview learning., Comment: Published in BMC Bioinformatics (https://bmcbioinformatics.biomedcentral.com/articles/10.1186/s12859-024-05679-9)

Published
2023
Full Text
View/download PDF

33. Cost-effectiveness of endovascular treatment for acute ischemic stroke in China: evidence from Shandong Peninsula

Author

Lu Han, Kuixu Lan, Dejian Kou, Zehua Meng, Jin Feng, Elizabeth Maitland, Stephen Nicholas, and Jian Wang

Subjects
Cost-effectiveness, Endovascular treatment, Intravenous thrombolysis, Acute ischemic stroke, Direct treatment costs, Indirect costs, Medicine (General), R5-920
Abstract

Abstract Background Recently, the endovascular treatment (EVT) of acute ischemic stroke has made significant progress in many aspects. Intravenous thrombolysis (IVT) is usually recommended before endovascular treatment in clinical practice, but the value of the practice is controversial. The latest meta-analysis evaluation was that the effect of EVT versus EVT plus IVT did not differ significantly. The cost-effectiveness analysis of EVT plus IVT needs further analysis. This study assesses the health benefits and economic impact of EVT plus IVT in Shandong Peninsula of China. Method We followed a cross-section design using the Chinese-Shandong Peninsula public hospital database between 2013 and 2023. The real-world costs and health outcomes were collected through the Hospital Information System (HIS) and published references. We calculated incremental cost-effectiveness ratios (ICERs) from the perspective of Chinese healthcare using the complex decision model to compare the costs and effectiveness between EVT versus EVT + IVT. One-way and Monte Carlo probabilistic sensitivity analyses were performed to assess the robustness of the economic evaluation model. Results EVT alone had a lower cost compared with EVT + IVT whether short-term or long-term. Until 99% dead of AIS patients, the ICER per additional QALY was RMB696399.30 over the willingness-to-pay (WTP) threshold of 3× gross domestic product (GDP) per capita in Shandong. The probabilistic sensitivity analysis of 3 months, 1 year and long-term horizons had a 97.90%, 97.43% and 96.89% probability of cost-effective treatment under the WTP threshold (1×GDP). The results of the one-way sensitivity analysis showed that direct treatment costs for EVT alone and EVT + IVT were all sensitive to ICER. Conclusions EVT alone was more cost-effective treatment compared to EVT + IVT in the Northeast Coastal Area of China. The data of this study could be used as a reference in China, and the use of the evaluation in other regions should be carefully considered.

Published
2024
Full Text
View/download PDF

34. Marangoni-flow-assisted assembly of single-walled carbon nanotube films for human motion sensing

Author

Yuguang Chen, Yitan Li, Lu Han, Hao Sun, Min Lyu, Zeyao Zhang, Shigeo Maruyama, and Yan Li

Subjects
Single-walled carbon nanotubes, Marangoni flow, Assembly, Interfaces, Sensors, Science (General), Q1-390
Abstract

Single-walled carbon nanotubes (SWCNTs) present excellent electronic and mechanical properties desired in wearable and flexible devices. The preparation of SWCNT films is the first step for fabricating various devices. This work developed a scalable and feasible method to assemble SWCNT thin films on water surfaces based on Marangoni flow induced by surface tension gradient. The films possess a large area of 40 cm × 30 cm (extensible), a tunable thickness of 15∼150 nm, a high transparency of up to 96%, and a decent conductivity. They are ready to be directly transferred to various substrates, including flexible ones. Flexible strain sensors were fabricated with the films on flexible substrates. These sensors worked with high sensitivity and repeatability. By realizing multi-functional human motion sensing, including responding to voices, monitoring artery pulses, and detecting knuckle and muscle actions, the assembled SWCNT films demonstrated the potential for application in smart devices.

Published
2024
Full Text
View/download PDF

35. Hydraulic properties and drought response of a tropical bamboo (Cephalostachyum pergracile)

Author

Wanwalee Kongjarat, Lu Han, Amy Ny Aina Aritsara, Shu-Bin Zhang, Gao-Juan Zhao, Yong-Jiang Zhang, Phisamai Maenpuen, Ying-Mei Li, Yi-Ke Zou, Ming-Yi Li, Xue-Nan Li, Lian-Bin Tao, and Ya-Jun Chen

Subjects
Climate change, Drought, Hydraulic safety, Hydraulic vulnerability segmentation, Stable isotope, Tree mortality, Biology (General), QH301-705.5, Botany, QK1-989
Abstract

Bamboo plants are an essential component of tropical ecosystems, yet their vulnerability to climate extremes, such as drought, is poorly understood due to limited knowledge of their hydraulic properties. Cephalostachyum pergracile, a commonly used tropical bamboo species, exhibited a substantially higher mortality rate than other co-occurring bamboos during a severe drought event in 2019, but the underlying mechanisms remain unclear. This study investigated the leaf and stem hydraulic traits related to drought responses, including leaf-stem embolism resistance (P50leaf; P50stem) estimated using optical and X-ray microtomography methods, leaf pressure–volume and water-releasing curves. Additionally, we investigated the seasonal water potentials, native embolism level (PLC) and xylem water source using stable isotope. We found that C. pergracile exhibited strong resistance to embolism, showing low P50leaf, P50stem, and turgor loss point, despite its rapid leaf water loss. Interestingly, its leaves displayed greater resistance to embolism than its stem, suggesting a lack of effective hydraulic vulnerability segmentation (HVS) to protect the stem from excessive xylem tension. During the dry season, approximately 49% of the water was absorbed from the upper 20-cm-deep soil layer. Consequently, significant diurnal variation in leaf water potentials and an increase in midday PLC from 5.87 ± 2.33% in the wet season to 12.87 ± 4.09% in the dry season were observed. In summary, this study demonstrated that the rapid leaf water loss, high reliance on surface water, and a lack of effective HVS in C. pergracile accelerated water depletion and increased xylem embolism even in the typical dry season, which may explain its high mortality rate during extreme drought events in 2019.

Published
2024
Full Text
View/download PDF

36. Research Progress on the Correlation between Different Dietary Patterns and Hyperuricemia Mediated by Intestinal Flora

Author

LU Han, ZHAO Kexin, XUE Yuling, MA Xinying, WANG Shijie

Subjects
hyperuricemia, gout, intestinal flora, dietary patterns, Food processing and manufacture, TP368-456
Abstract

Hyperuricemia (HUA) is a purine metabolism disorder caused by the imbalance between uric acid production and excretion, which, when severe, can lead to gout and renal function damage. At present, the prevalence of HUA/gout is increasing yearly in China and the HUA/gout patients are becoming younger and younger. Recent studies have shown that the intestinal flora of patients with HUA/gout is imbalanced when compared with that of healthy people, and different dietary patterns can affect the level of uric acid by adjusting the intestinal flora. This paper elaborates on the characteristics of the intestinal flora in patients with HUA/gout and the effect of the intestinal flora on uric acid metabolism, which will lay a theoretical foundation for the prevention, early diagnosis and auxiliary treatment of HUA/gout. This paper also summarizes recent progress in understanding the impact of different dietary patterns on uric acid levels in order to guide patients to effectively prevent and delay the occurrence of HUA/gout by adjusting their dietary patterns.

Published
2024
Full Text
View/download PDF

37. Comparative analysis of work-related injury appraisal of 13 cases of occupational brucellosis

Author

Yifei PEI, Wenwen YUAN, Lili YANG, Huajian JU, and Lu HAN

Subjects
occupational disease, brucellosis, work-related injury, identification of labor capacity, disability level, Medicine (General), R5-920, Toxicology. Poisons, RA1190-1270
Abstract

BackgroundAccording to the Classification and Catalogue of Occupational Diseases, brucellosis is one of the notifiable occupational infectious diseases, which occurs from time to time in the occupational population. ObjectiveTo compare the work-related injury appraisal process and results of 13 cases of brucellosis at both provincial and municipal levels, analyze and summarize the bias in the practical work of labor capacity identification for occupational diseases such as brucellosis by appraisal management departments and experts, and propose suggestions for optimizing appraisal work. MethodsA comparative study was conducted on the objective examination results and labor capacity appraisal conclusions based on the occupational contact history, clinical diagnosis, occupational disease diagnosis staging, and labor capacity appraisal of 13 patients with brucellosis. The reasons for the inconsistency between the initial appraisal conclusion by institutions at the municipal level and the final appraisal conclusion by institutions at the provincial level were compared and analyzed. ResultsAll of the 13 patients with brucellosis applied for municipal-level labor capacity identification after being identified as work-related injuries, 11 of which did not receive a disability level, and 2 were rated as level 10 disability. Four of those who did not receive the disability rate applied for provincial-level labor capacity identification. As a result, 2 cases were maintained original appraisal conclusions, while the other 2 changed the conclusions to level 9 disability and level 10 disability respectively. It was the first time in Shijiangzhuang municipal-level primary labor capacity appraisal and Hebei provincial-level labor capacity re-appraisal that the work-related injury caused by occupational brucellosis was rated as level 9 disability or level 10 disability. Hence, the lessons learned from this comparative analysis are that the degree of target organ damage and (or) organ dysfunction are the direct basis for work-related injury appraisal; an objective and scientific labor capacity identification for occupational brucellosis should base on the each case of disability evaluation, identify the relevant target organ damage and the degree of dysfunction, and rate the disability level after a comprehensive appraisal.ConclusionThis analysis would be a guidance to the identification of labor capacity for occupational brucellosis in Hebei Province and the whole country. There is a hysteresis issue in the occupational disease provisions in the national standard GB/T 16180—2014 Standard for identify work ability—Gradation of disability caused by work-related injuries and occupatiaonal diseases. In current situation, appraisal experts should not only search for clauses that directly correspond to the occupational diseases and injuries, but also target conditions not covered in the clauses and conduct assessment based on the characteristics of occupational diseases, with scientific, accurate, and flexible application of the clauses in the standard and appendix, so as to make fair, just, and professional appraisal conclusions.

Published
2024
Full Text
View/download PDF

38. Rewiring of a KNOXI regulatory network mediated by UFO underlies the compound leaf development in Medicago truncatula

Author

Zhichao Lu, Juanjuan Zhang, Hongfeng Wang, Ke Zhang, Zhiqun Gu, Yiteng Xu, Jing Zhang, Min Wang, Lu Han, Fengning Xiang, and Chuanen Zhou

Subjects
Science
Abstract

Abstract Class I KNOTTED-like homeobox (KNOXI) genes are parts of the regulatory network that control the evolutionary diversification of leaf morphology. Their specific spatiotemporal expression patterns in developing leaves correlate with the degrees of leaf complexity between simple-leafed and compound-leafed species. However, KNOXI genes are not involved in compound leaf formation in several legume species. Here, we identify a pathway for dual repression of MtKNOXI function in Medicago truncatula. PINNATE-LIKE PENTAFOLIATA1 (PINNA1) represses the expression of MtKNOXI, while PINNA1 interacts with MtKNOXI and sequesters it to the cytoplasm. Further investigations reveal that UNUSUAL FLORAL ORGANS (MtUFO) is the direct target of MtKNOXI, and mediates the transition from trifoliate to pinnate-like pentafoliate leaves. These data suggest a new layer of regulation for morphological diversity in compound-leafed species, in which the conserved regulators of floral development, MtUFO, and leaf development, MtKNOXI, are involved in variation of pinnate-like compound leaves in M. truncatula.

Published
2024
Full Text
View/download PDF

39. Augmenting Transformer-Transducer Based Speaker Change Detection With Token-Level Training Loss

Author

Zhao, Guanlong, Wang, Quan, Lu, Han, Huang, Yiling, and Moreno, Ignacio Lopez

Subjects
Electrical Engineering and Systems Science - Audio and Speech Processing, Computer Science - Machine Learning, Computer Science - Sound
Abstract

In this work we propose a novel token-based training strategy that improves Transformer-Transducer (T-T) based speaker change detection (SCD) performance. The conventional T-T based SCD model loss optimizes all output tokens equally. Due to the sparsity of the speaker changes in the training data, the conventional T-T based SCD model loss leads to sub-optimal detection accuracy. To mitigate this issue, we use a customized edit-distance algorithm to estimate the token-level SCD false accept (FA) and false reject (FR) rates during training and optimize model parameters to minimize a weighted combination of the FA and FR, focusing the model on accurately predicting speaker changes. We also propose a set of evaluation metrics that align better with commercial use cases. Experiments on a group of challenging real-world datasets show that the proposed training method can significantly improve the overall performance of the SCD model with the same number of parameters.

Published
2022

40. Highly Efficient Real-Time Streaming and Fully On-Device Speaker Diarization with Multi-Stage Clustering

Author

Wang, Quan, Huang, Yiling, Lu, Han, Zhao, Guanlong, and Moreno, Ignacio Lopez

Subjects
Electrical Engineering and Systems Science - Audio and Speech Processing, Computer Science - Machine Learning, Computer Science - Sound
Abstract

While recent research advances in speaker diarization mostly focus on improving the quality of diarization results, there is also an increasing interest in improving the efficiency of diarization systems. In this paper, we demonstrate that a multi-stage clustering strategy that uses different clustering algorithms for input of different lengths can address multi-faceted challenges of on-device speaker diarization applications. Specifically, a fallback clusterer is used to handle short-form inputs; a main clusterer is used to handle medium-length inputs; and a pre-clusterer is used to compress long-form inputs before they are processed by the main clusterer. Both the main clusterer and the pre-clusterer can be configured with an upper bound of the computational complexity to adapt to devices with different resource constraints. This multi-stage clustering strategy is critical for streaming on-device speaker diarization systems, where the budgets of CPU, memory and battery are tight.

Published
2022

41. Cognitive interviewing validation of the Chinese version of the neurogenic bladder symptom score

Author

Xue Wang, Shen Gao, Ting Wang, Jun Xue, Yixuan Yang, Lu Han, Yuanjie Niu, and Li Fu

Subjects
Cognitive interviewing, Quality of life, Patient reported outcome measurement, Content validity, Neurogenic bladder, Outcome assessment, Science (General), Q1-390, Social sciences (General), H1-99
Abstract

Background: The neurogenic bladder symptom score (NBSS) has been widely used to specifically measure symptoms and consequences of neurogenic bladder (NB). The cognitive interviewing (CI) is effective in assessing item clarity and identifying key issues related to the comprehension of the instrument. We aim to translate the NBSS into Chinese and use the CI approach to explore the thought processes of patients with NB in responding the Chinese Version of the NBSS, identify and modify the factors hinder the thought processes to enhance the face validity of the NBSS. Methods: The translation of the NBSS into Chinese was conducted with the guidance of the recommended frameworks. Patients with NB were recruited by purpose sampling. CI with the combination of thinking aloud and verbal probing techniques were used to explore thought processes. The interviews were transcribed and analyzed based on Tourangeau four-stage response model. Results: Two rounds of CI were carried out. The problems of comprehension, judgement and response mapping were identified in 8 items. Four items were revised based on the results of the interview. The revised items were verified and eventually integrated into the final version. Conclusion: The Chinese Version of the NBSS was easy to comprehend and use. The use of CI methodologies can increase the comprehensibility and cultural applicability of the NBSS, providing the evidence for the development of a clearer and more appropriate questionnaire.

Published
2024
Full Text
View/download PDF

42. Association Between Particulate Matter Exposure and Preterm Birth in Women With Abnormal Preconception Thyrotropin Levels: Large Cohort Study

Author

Ting Xu, Haobo Ni, Xiaoyan Cai, Tingting Dai, Lingxi Wang, Lina Xiao, Qinghui Zeng, Xiaolin Yu, Lu Han, and Pi Guo

Subjects
Public aspects of medicine, RA1-1270
Abstract

Abstract BackgroundPrior research has linked exposure to particulate matter with an aerodynamic diameter of ≤2.5 μm (PM2.52.5 ObjectiveThis study aimed to assess whether preconception TSH levels modulate the impact of PM2.5 MethodsThis cohort study was conducted in Guangdong, China, as a part of the National Free Pre-Pregnancy Checkups Project. PM2.52.52.5 ResultsA total of 633,516 women who delivered between January 1, 2014, to December 31, 2019, were included. In total, 34,081 (5.4%) of them had abnormal preconception TSH levels. During the entire pregnancy, each 10-μg/m32.52.5 ConclusionsPM2.52.5

Published
2024
Full Text
View/download PDF

43. A bibliometric analysis of transcranial alternating current stimulation

Author

Cheng-Fan Wu, Chao Shen, Zhao-Di Wang, Yan Gong, Lu-Han Zhou, Wen-Jun Qian, and Tong Tang

Subjects
bibliometrics, transcranial alternating current stimulation, CiteSpace, oscillations, visual analysis, Neurosciences. Biological psychiatry. Neuropsychiatry, RC321-571
Abstract

BackgroundTranscranial alternating current stimulation (tACS) can apply currents of varying intensity to the scalp, modulating cortical excitability and brain activity. tACS is a relatively new neuromodulation intervention that is now widely used in clinical practice. Many papers related to tACS have been published in various journals. However, there are no articles that objectively and directly introduce the development trend and research hotspots of tACS. Therefore, the aim of this study is to use CiteSpace to visually analyze the recent tACS-related publications, systematically and in detail summarize the current research hotspots and trends in this field, and provide valuable information for future tACS-related research.Material and methodsThe database Web of Science Core Collection Science Citation Index Expanded was used and searched from build to 4 August 2023. Using the CiteSpace to analyze the authors, institutions, countries, keywords, co-cited authors, journals, and references.ResultsA total of 677 papers were obtained. From 2008 to 2023, the number of publications shows an increasing trend, albeit with some fluctuations. The most productive country in this field was Germany. The institution with the highest number of publications is Carl von Ossietzky University of Oldenburg (n = 50). According to Bradford’s law, 7 journals are considered core journals in the field. Herrmann, CS was the author with the most publications (n = 40), while Antal, A was the author with the highest number of co-citations (n = 391) and betweenness centrality (n = 0.16). Disease, neural mechanisms of the brain and electric stimulation are the major research areas in the field. The effect of tACS in different diseases, multi-site stimulation, combined treatment and evaluation are the future research hotspots and trends.ConclusiontACS has research value and research potential, and more and more researchers are paying attention to it. The findings of this bibliometric study provide the current status and trends in the clinical research of tACS and may help researchers to identify hotspots s and explore new research directions in this field.

Published
2024
Full Text
View/download PDF

44. Targeted therapy of glomerulonephritis via salvianolic acid b-loaded biomimetic hybrid nanovesicles driven by homing

Author

Zhi-xiang Yuan, Qingyong Chen, Hongmei Liu, Rongrui Zhang, Yan Jiang, Lu Han, Shuo Wang, Yu Xiong, Xianzhe Li, Qiang Liu, Wen-jing Yi, Yan Ren, Lili He, Shiwei Tang, and Yunzhu Lin

Subjects
Mesangial cells, Renal inflammation, Cellular hybrid membrane, Biomimetic drug delivery system, Salvianolic acid B, Materials of engineering and construction. Mechanics of materials, TA401-492
Abstract

Background: Mesangial cell (MC)-mediated immune inflammatory injury is a basic pathological process in glomerulonephritis. However, due to the limited drug accumulation and serious adverse effects, it remains challenging to explore a rational delivery system integrating high efficiency and low toxicity to deliver anti-inflammatory drugs to the glomerular MC region. Results: Salvianolic acid B (SAB)-loaded hybrid membrane biomimetic nanovesicles (SAB@HMVs) were developed by fusing erythrocyte membrane nanovesicles with mesenchymal stem cells biomimetic membrane nanovesicles. SAB@HMVs had a spheroidal structure, low cytotoxicity, particle size of 143.83 ± 1.33 nm and exhibited a high drug loading capacity (7.02 %±0.30 %) along with a good sustained release function. The in vitro anti-inflammatory results revealed that HMVs were effectively taken up by MCs and showed significant anti-inflammatory activity. Furthermore, in vivo pharmacodynamic studies revealed that SAB@HMVs could deliver SAB to kidney tissue and elicit an effective anti-inflammatory response to improve the pathological changes in the glomerular mesangial region, significantly reducing the levels of cytokines and alleviating kidney inflammation. Especially, noteworthy was the observation that SAB@HMVs augmented the renal delivery of SAB, downregulated the gene expression of p38 MAPK and NF-κB, inhibited the levels of MMP9 and TNF-α proteins as well as elevated the level of iκB protein, indicating that the anti-inflammatory mechanism of SAB@HMVs should be based on regulating MAPK and NF-κB signaling pathways. Conclusion: We provided a novel strategy to increase nanovesicles accumulation in MCs with the potential to exert anti-inflammatory regulatory effects in glomerulonephritis. Furthermore, this biomimetic hybrid membrane loaded with pure drugs may offer a functional platform to address multiple clinical needs.

Published
2024
Full Text
View/download PDF

45. Association between different composite dietary antioxidant indexes and constipation in American male adults: a cross-sectional study

Author

Wei Sun, Yuchao Wang, Lu Han, Yinshi Liu, Hongru Liu, Yunbing Tong, Ziying Jiang, Daqing Sun, and Chen Xu

Subjects
antioxidant, dietary complex antioxidant index, constipation, National Health and Nutrition Examination Survey, oxidative stress, Nutrition. Foods and food supply, TX341-641
Abstract

BackgroundOxidative stress is acknowledged as a pivotal factor in the intricate pathophysiological processes and pathogenesis of constipation. Modifying dietary patterns can elevate in vivo antioxidant biomarker levels, consequently mitigating oxidative stress. The Composite Dietary Antioxidant Index (CDAI) provides a dependable scoring mechanism for quantifying the potential antioxidant capacity of diets. The association between CDAI levels and the risk of constipation remains uncertain.PurposeTo investigate the potential correlation between CDAI and constipation, aiming to improve constipation management through dietary guidance.MethodsA total of 11,165 adults aged ≥20 years, drawn from the 2005–2010 National Health and Nutrition Examination Survey, were enrolled in this cross-sectional study. We evaluated the correlation between CDAI levels and the risk of constipation through three weighted logistic regression models. Restricted cubic spline (RCS) analysis was employed to assess nonlinear trends, and stratified analyses were conducted.ResultsAfter adjusting for all confounding variables, the findings revealed an association between CDAI and constipation [OR = 0.937; 95% CI (0.892, 0.984), p = 0.012]. Moreover, individuals in the highest quartile of CDAI demonstrated a 40.1% lower likelihood of experiencing constipation compared to those in the lowest quartile [OR = 0.599; 95% CI (0.382, 0.939), p = 0.027]. The RCS analysis indicated a linear relationship between CDAI and constipation (P-non-linear =0.1016). Subgroup analysis by gender revealed a negative correlation in the male population [OR = 0.871; 95% CI (0.801, 0.947), p = 0.002], with men in the highest CDAI quartile exhibiting a 59.8% lower likelihood of experiencing constipation compared to those in the lowest quartile [OR = 0.402; 95% CI (0.206, 0.787), p = 0.010]. Furthermore, alterations in selenium [OR = 0.997; 95% CI (0.995, 1.000), p = 0.039] per milligram were independently linked to constipation. In a gender subgroup analysis of a single antioxidant, changes per milligram of vitamin E [OR = 0.904; 95% CI (0.838 to 0.975), p = 0.011] among males were independently associated with constipation.ConclusionThe fully adjusted model showed a correlation between CDAI and constipation and a significant correlation in quartiles. Meanwhile, subgroup analysis by gender showed that CDAI was negatively associated with constipation in the male population. Moreover, the findings of this study imply that investigations into antioxidant diets should be contextualized within dietary patterns.

Published
2024
Full Text
View/download PDF

46. Bibliometric analysis of electroencephalogram research in Parkinson’s disease from 2004 to 2023

Author

Xiao-Yu Liao, Ya-Xin Gao, Ting-Ting Qian, Lu-Han Zhou, Li-Qin Li, Yan Gong, and Tian-Fen Ye

Subjects
bibliometrix, CiteSpace, VOSviewer, Parkinson’ disease, electroencephalogram, neural oscillations, Neurosciences. Biological psychiatry. Neuropsychiatry, RC321-571
Abstract

BackgroundParkinson’s disease (PD) is a prevalent neurodegenerative disorder affecting millions globally. It encompasses both motor and non-motor symptoms, with a notable impact on patients’ quality of life. Electroencephalogram (EEG) is a non-invasive tool that is increasingly utilized to investigate neural mechanisms in PD, identify early diagnostic markers, and assess therapeutic responses.MethodsThe data were sourced from the Science Citation Index Expanded within the Web of Science Core Collection database, focusing on publications related to EEG research in PD from 2004 to 2023. A comprehensive bibliometric analysis was conducted using CiteSpace and VOSviewer software. The analysis began with an evaluation of the selected publications, identifying leading countries, institutions, authors, and journals, as well as co-cited references, to summarize the current state of EEG research in PD. Keywords are employed to identify research topics that are currently of interest in this field through the analysis of high-frequency keyword co-occurrence and cluster analysis. Finally, burst keywords were identified to uncover emerging trends and research frontiers in the field, highlighting shifts in interest and identifying future research directions.ResultsA total of 1,559 publications on EEG research in PD were identified. The United States, Germany, and England have made notable contributions to the field. The University of London is the leading institution in terms of publication output, with the University of California closely following. The most prolific authors are Brown P, Fuhr P, and Stam C In terms of total citations and per-article citations, Stam C has the highest number of citations, while Brown P has the highest H-index. In terms of the total number of publications, Clinical Neurophysiology is the leading journal, while Brain is the most highly cited. The most frequently cited articles pertain to software toolboxes for EEG analysis, neural oscillations, and PD pathophysiology. Through analyzing the keywords, four research hotspots were identified: research on the neural oscillations and connectivity, research on the innovations in EEG Analysis, impact of therapies on EEG, and research on cognitive and emotional assessments.ConclusionThis bibliometric analysis demonstrates a growing global interest in EEG research in PD. The investigation of neural oscillations and connectivity remains a primary focus of research. The application of machine learning, deep learning, and task analysis techniques offers promising avenues for future research in EEG and PD, suggesting the potential for advancements in this field. This study offers valuable insights into the major research trends, influential contributors, and evolving themes in this field, providing a roadmap for future exploration.

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results