Search

Your search keyword '"A. Avram"' showing total 24,616 results
Start Over Author "A. Avram"
24,616 results on '"A. Avram"'

1. RoQLlama: A Lightweight Romanian Adapted Language Model

Author

Dima, George-Andrei, Avram, Andrei-Marius, Crăciun, Cristian-George, and Cercel, Dumitru-Clementin

Subjects
Computer Science - Computation and Language
Abstract

The remarkable achievements obtained by open-source large language models (LLMs) in recent years have predominantly been concentrated on tasks involving the English language. In this paper, we aim to advance the performance of Llama2 models on Romanian tasks. We tackle the problem of reduced computing resources by using QLoRA for training. We release RoQLlama-7b, a quantized LLM, which shows equal or improved results compared to its full-sized counterpart when tested on seven Romanian downstream tasks in the zero-shot setup. Also, it consistently achieves higher average scores across all few-shot prompts. Additionally, we introduce a novel Romanian dataset, namely RoMedQA, which contains single-choice medical questions in Romanian., Comment: Accepted at EMNLP Findings 2024 (short papers)

Published
2024

2. Groundwater erosion of coastal gullies along the Canterbury coast (New Zealand): a rapid and episodic process controlled by rainfall intensity and substrate variability

Author

A. Micallef, R. Marchis, N. Saadatkhah, P. Pondthai, M. E. Everett, A. Avram, A. Timar-Gabor, D. Cohen, R. Preca Trapani, B. A. Weymer, and P. Wernette

Subjects
Dynamic and structural geology, QE500-639.5
Abstract

Gully formation has been associated to groundwater seepage in unconsolidated sand- to gravel-sized sediments. Our understanding of gully evolution by groundwater seepage mostly relies on experiments and numerical simulations, and these rarely take into consideration contrasts in lithology and permeability. In addition, process-based observations and detailed instrumental analyses are rare. As a result, we have a poor understanding of the temporal scale of gully formation by groundwater seepage and the influence of geological heterogeneity on their formation. This is particularly the case for coastal gullies, where the role of groundwater in their formation and evolution has rarely been assessed. We address these knowledge gaps along the Canterbury coast of the South Island (New Zealand) by integrating field observations, luminescence dating, multi-temporal unoccupied aerial vehicle and satellite data, time domain electromagnetic data and slope stability modelling. We show that gully formation is a key process shaping the sandy gravel cliffs of the Canterbury coastline. It is an episodic process associated to groundwater flow that occurs once every 227 d on average, when rainfall intensities exceed 40 mm d−1. The majority of the gullies in a study area southeast (SE) of Ashburton have undergone erosion, predominantly by elongation, during the last 11 years, with the most recent episode occurring 3 years ago. Gullies longer than 200 m are relict features formed by higher groundwater flow and surface erosion > 2 ka ago. Gullies can form at rates of up to 30 m d−1 via two processes, namely the formation of alcoves and tunnels by groundwater seepage, followed by retrogressive slope failure due to undermining and a decrease in shear strength driven by excess pore pressure development. The location of gullies is determined by the occurrence of hydraulically conductive zones, such as relict braided river channels and possibly tunnels, and of sand lenses exposed across sandy gravel cliffs. We also show that the gully planform shape is generally geometrically similar at consecutive stages of evolution. These outcomes will facilitate the reconstruction and prediction of a prevalent erosive process and overlooked geohazard along the Canterbury coastline.

Published
2021
Full Text
View/download PDF

3. Tunable 24-GHz Antenna Arrays Based on Nanocrystalline Graphite

Author

M. Aldrigo, M. Dragoman, S. Iordanescu, A. Avram, O.-G. Simionescu, C. Parvulescu, H. El Ghannudi, S. Montori, L. Nicchi, S. Xavier, and A. Ziaei

Subjects
Carbon compounds, patch antennas, microwave antenna arrays, tuning, Electrical engineering. Electronics. Nuclear engineering, TK1-9971
Abstract

In this work, we present a tunable 24-GHz antenna array based on a CMOS-compatible 110-nm-thick nanocrystalline graphite film grown by plasma enhanced chemical vapor deposition. The film has a nominal bulk conductivity exceeding 16000 S/m (hence, greater than any graphene monolayer or industrially available graphene multilayer) but still able to show an outstanding modulation of its charge carrier density in the upper microwave spectrum. The manufactured layer was used to design, simulate, fabricate, and test a 24-GHz patch antenna array, with each radiating element having overall dimensions of just $\lambda _{0}/8\times \lambda _{0}$ /7. The fabricated array exhibits a measured maximum gain of about 3 dBi around 24 GHz (unbiased state), with a half-power beam width of only 14.5° (suitable in wireless links where a high directivity is envisaged). Spanning the dc bias voltage between -25 V and 25 V at 24 GHz, the gain can be tuned continuously between -1.5 dBi and 4 dBi, whereas the resonance frequency undergoes a maximum shift of 166 MHz. This voltage-dependent tuning of the gain represents a first step in developing carbon-based applications to control amplitude and phase simultaneously and independently. These results (never reported) demonstrate the big potential of nanocrystalline graphite for high-performance microwave components that are CMOS compatible (a highly desirable characteristic for high fabrication yield and large-scale production), with unprecedented tunability for next-generation high-capacity communications.

Published
2021
Full Text
View/download PDF

4. Advancing Mathematical Epidemic Modeling via synergies with Chemical Reaction Network Theory and Lagrange-Hamilton Geometry

Author

Avram, Florin, Adenane, Rim, and Neagu, Mircea

Subjects
Mathematics - Dynamical Systems
Abstract

This essay reviews some key concepts in mathematical epidemiology and examines the intersection of this field with related scientific disciplines, such as chemical reaction network theory and Lagrange-Hamilton geometry. Through a synthesis of theoretical insights and practical perspectives, we underscore the significance of essentially non-negative kinetic systems in the development and implementation of robust epidemiological models. Our purpose is to make the case that currently mathematical modeling of epidemiology is focusing too much on simple particular cases, and maybe not enough on more complex models, whose challenges would require cooperation with scientific computing experts and with researchers in the "sister disciplines" involving essentially nonnegative kinetic systems (like virology, ecology, chemical reaction networks, population dynamics, etc)., Comment: arXiv admin note: text overlap with arXiv:2311.16686

Published
2024

5. Do Cure Violence Programs Reduce Gun Violence? Evidence from New York City

Author

Avram, Rachel, Koepcke, Eric J., Moussawi, Alaa, and Nuñez, Melissa

Subjects
Economics - General Economics
Abstract

Cure Violence is a community violence intervention program that aims to reduce gun violence by mediating conflicts, "treating" high-risk individuals, and changing community norms. Using NYC shootings data from 2006-2023, we assess the efficacy of Cure Violence using both difference-in-differences and event study models. We find that, on average, Cure Violence is associated with a 14% reduction in shootings relative to the counterfactual. This association persists in the years after treatment, neither increasing nor decreasing much over time. We exploit variation in the geography and timing of Cure implementation to argue against alternative explanations. Additionally, we find suggestive evidence of spillover effects into nearby precincts, as well as increasing returns to opening new Cure programs. Interpreted causally, our results imply that around 1,300 shootings were avoided between 2012-2023 due to Cure -- generating a net social surplus of $2.45 billion and achieving a benefit-cost ratio of 6.5:1.

Published
2024

6. Finding bifurcations in mathematical epidemiology via reaction network methods

Author

Vassena, Nicola, Avram, Florin, and Adenane, Rim

Subjects
Mathematics - Dynamical Systems, 92D25, 92D30, 92C42, 34C23
Abstract

Mathematical Epidemiology (ME) shares with Chemical Reaction Network Theory (CRNT) the basic mathematical structure of its dynamical systems. Despite this central similarity, methods from CRNT have been seldom applied to solving problems in ME. We explore here the applicability of CRNT methods to find bifurcations at endemic equilibria of ME models. We adapt three CRNT methods to the features of ME. First, we prove that essentially all ME models admit Hopf bifurcations for certain monotone choices of the interaction functions. Second, we offer a parametrization of equilibria Jacobians of ME systems where few interactions are not in mass action form. Third, for a quite general class of models, we show that periodic oscillations in closed systems imply periodic oscillations when demography is added. Finally, we apply such results to two families of networks: a general SIR model with a nonlinear force of infection and treatment rate and a recent SIRnS model with a gradual increase in infectiousness. We give both necessary conditions and sufficient conditions for the occurrence of bifurcations at endemic equilibria of both families., Comment: 41 Pages, 3 figures

Published
2024

7. Verbal Learning and Memory Deficits across Neurological and Neuropsychiatric Disorders: Insights from an ENIGMA Mega Analysis.

Author

Kennedy, Eamonn, Liebel, Spencer, Lindsey, Hannah, Vadlamani, Shashank, Lei, Pui-Wa, Adamson, Maheen, Alda, Martin, Alonso-Lana, Silvia, Anderson, Tim, Arango, Celso, Asarnow, Robert, Avram, Mihai, Ayesa-Arriola, Rosa, Babikian, Talin, Banaj, Nerisa, Bird, Laura, Borgwardt, Stefan, Brodtmann, Amy, Brosch, Katharina, Caeyenberghs, Karen, Calhoun, Vince, Chiaravalloti, Nancy, Cifu, David, Crespo-Facorro, Benedicto, Dalrymple-Alford, John, Dams-OConnor, Kristen, Dannlowski, Udo, Darby, David, Davenport, Nicholas, DeLuca, John, Diaz-Caneja, Covadonga, Disner, Seth, Dobryakova, Ekaterina, Ehrlich, Stefan, Esopenko, Carrie, Ferrarelli, Fabio, Frank, Lea, Franz, Carol, Fuentes-Claramonte, Paola, Genova, Helen, Giza, Christopher, Goltermann, Janik, Grotegerd, Dominik, Gruber, Marius, Gutierrez-Zotes, Alfonso, Ha, Minji, Haavik, Jan, Hinkin, Charles, Hoskinson, Kristen, Hubl, Daniela, Irimia, Andrei, Jansen, Andreas, Kaess, Michael, Kang, Xiaojian, Kenney, Kimbra, Keřková, Barbora, Khlif, Mohamed, Kim, Minah, Kindler, Jochen, Kircher, Tilo, Knížková, Karolina, Kolskår, Knut, Krch, Denise, Kremen, William, Kuhn, Taylor, Kumari, Veena, Kwon, Junsoo, Langella, Roberto, Laskowitz, Sarah, Lee, Jungha, Lengenfelder, Jean, Liou-Johnson, Victoria, Lippa, Sara, Løvstad, Marianne, Lundervold, Astri, Marotta, Cassandra, Marquardt, Craig, Mattos, Paulo, Mayeli, Ahmad, McDonald, Carrie, Meinert, Susanne, Melzer, Tracy, Merchán-Naranjo, Jessica, Michel, Chantal, Morey, Rajendra, Mwangi, Benson, Myall, Daniel, Nenadić, Igor, Newsome, Mary, Nunes, Abraham, OBrien, Terence, Oertel, Viola, Ollinger, John, Olsen, Alexander, Ortiz García de la Foz, Victor, Ozmen, Mustafa, Pardoe, Heath, Parent, Marise, Piras, Fabrizio, and Piras, Federica

Subjects
Parkinson’s disease, attention-deficit/hyperactivity disorder, bipolar disorder, dementia, depression, memory, schizophrenia, stroke, traumatic brain injury, verbal learning
Abstract

Deficits in memory performance have been linked to a wide range of neurological and neuropsychiatric conditions. While many studies have assessed the memory impacts of individual conditions, this study considers a broader perspective by evaluating how memory recall is differentially associated with nine common neuropsychiatric conditions using data drawn from 55 international studies, aggregating 15,883 unique participants aged 15-90. The effects of dementia, mild cognitive impairment, Parkinsons disease, traumatic brain injury, stroke, depression, attention-deficit/hyperactivity disorder (ADHD), schizophrenia, and bipolar disorder on immediate, short-, and long-delay verbal learning and memory (VLM) scores were estimated relative to matched healthy individuals. Random forest models identified age, years of education, and site as important VLM covariates. A Bayesian harmonization approach was used to isolate and remove site effects. Regression estimated the adjusted association of each clinical group with VLM scores. Memory deficits were strongly associated with dementia and schizophrenia (p < 0.001), while neither depression nor ADHD showed consistent associations with VLM scores (p > 0.05). Differences associated with clinical conditions were larger for longer delayed recall duration items. By comparing VLM across clinical conditions, this study provides a foundation for enhanced diagnostic precision and offers new insights into disease management of comorbid disorders.

Published
2024

8. Evaluation of stenoses using AI video models applied to coronary angiography.

Author

Labrecque Langlais, Élodie, Corbin, Denis, Tastet, Olivier, Hayek, Ahmad, Doolub, Gemina, Mrad, Sebastián, Tardif, Jean-Claude, Tanguay, Jean-François, Marquis-Gravel, Guillaume, Tison, Geoffrey, Kadoury, Samuel, Le, William, Gallo, Richard, Lesage, Frederic, and Avram, Robert

Abstract

The coronary angiogram is the gold standard for evaluating the severity of coronary artery disease stenoses. Presently, the assessment is conducted visually by cardiologists, a method that lacks standardization. This study introduces DeepCoro, a ground-breaking AI-driven pipeline that integrates advanced vessel tracking and a video-based Swin3D model that was trained and validated on a dataset comprised of 182,418 coronary angiography videos spanning 5 years. DeepCoro achieved a notable precision of 71.89% in identifying coronary artery segments and demonstrated a mean absolute error of 20.15% (95% CI: 19.88-20.40) and a classification AUROC of 0.8294 (95% CI: 0.8215-0.8373) in stenosis percentage prediction compared to traditional cardiologist assessments. When compared to two expert interventional cardiologists, DeepCoro achieved lower variability than the clinical reports (19.09%; 95% CI: 18.55-19.58 vs 21.00%; 95% CI: 20.20-21.76, respectively). In addition, DeepCoro can be fine-tuned to a different modality type. When fine-tuned on quantitative coronary angiography assessments, DeepCoro attained an even lower mean absolute error of 7.75% (95% CI: 7.37-8.07), underscoring the reduced variability inherent to this method. This study establishes DeepCoro as an innovative video-based, adaptable tool in coronary artery disease analysis, significantly enhancing the precision and reliability of stenosis assessment.

Published
2024

9. HistNERo: Historical Named Entity Recognition for the Romanian Language

Author

Avram, Andrei-Marius, Iuga, Andreea, Manolache, George-Vlad, Matei, Vlad-Cristian, Micliuş, Răzvan-Gabriel, Muntean, Vlad-Andrei, Sorlescu, Manuel-Petru, Şerban, Dragoş-Andrei, Urse, Adrian-Dinu, Păiş, Vasile, and Cercel, Dumitru-Clementin

Subjects
Computer Science - Computation and Language
Abstract

This work introduces HistNERo, the first Romanian corpus for Named Entity Recognition (NER) in historical newspapers. The dataset contains 323k tokens of text, covering more than half of the 19th century (i.e., 1817) until the late part of the 20th century (i.e., 1990). Eight native Romanian speakers annotated the dataset with five named entities. The samples belong to one of the following four historical regions of Romania, namely Bessarabia, Moldavia, Transylvania, and Wallachia. We employed this proposed dataset to perform several experiments for NER using Romanian pre-trained language models. Our results show that the best model achieved a strict F1-score of 55.69%. Also, by reducing the discrepancies between regions through a novel domain adaption technique, we improved the performance on this corpus to a strict F1-score of 66.80%, representing an absolute gain of more than 10%., Comment: Accepted at the International Conference on Document Analysis and Recognition (ICDAR 2024)

Published
2024

10. Analogue of the Cauchy-Schwarz inequality for determinants: a simple proof

Author

Sidi, Avram

Subjects
Mathematics - General Mathematics, 15
Abstract

In this note, we present a simple proof of an analogue of the Cauchy-Schwarz inequality relevant to products of determinants. Specifically, we show that $$ |\det(A^*MB)|^2\leq \det(A^*MA)\cdot \det(B^*MB),\quad A,B\in \mathbb{C}^{m\times n},$$ where $M\in\mathbb{C}^{m\times m}$ is hermitian positive definite. Here $m$ and $n$ are arbitrary. In case $m\leq n$, equality holds trivially. Equality holds when $m>n$ and $\text{rank}(A)=\text{rank}(B)=n$ if and only if the columns of $A$ and the columns of $B$ span the same subspace of $\mathbb{C}^m$., Comment: 7

Published
2024

12. LYT-NET: Lightweight YUV Transformer-based Network for Low-light Image Enhancement

Author

Brateanu, A., Balmez, R., Avram, A., Orhei, C., and Ancuti, C.

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

This letter introduces LYT-Net, a novel lightweight transformer-based model for low-light image enhancement (LLIE). LYT-Net consists of several layers and detachable blocks, including our novel blocks--Channel-Wise Denoiser (CWD) and Multi-Stage Squeeze & Excite Fusion (MSEF)--along with the traditional Transformer block, Multi-Headed Self-Attention (MHSA). In our method we adopt a dual-path approach, treating chrominance channels U and V and luminance channel Y as separate entities to help the model better handle illumination adjustment and corruption restoration. Our comprehensive evaluation on established LLIE datasets demonstrates that, despite its low complexity, our model outperforms recent LLIE methods. The source code and pre-trained models are available at https://github.com/albrateanu/LYT-Net, Comment: 5 pages

Published
2024

13. 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

14. Scalable architecture for trapped-ion quantum computing using RF traps and dynamic optical potentials

Author

Schwerdt, David, Peleg, Lee, Shapira, Yotam, Priel, Nadav, Florshaim, Yanay, Gross, Avram, Zalic, Ayelet, Afek, Gadi, Akerman, Nitzan, Stern, Ady, Kish, Amit Ben, and Ozeri, Roee

Subjects
Quantum Physics, Physics - Atomic Physics
Abstract

Qubits based on ions trapped in linear radio-frequency traps form a successful platform for quantum computing, due to their high fidelity of operations, all-to-all connectivity and degree of local control. In principle there is no fundamental limit to the number of ion-based qubits that can be confined in a single 1D register. However, in practice there are two main issues associated with long trapped-ion crystals, that stem from the 'softening' of their modes of motion, upon scaling up: high heating rates of the ions' motion, and a dense motional spectrum; both impede the performance of high-fidelity qubit operations. Here we propose a holistic, scalable architecture for quantum computing with large ion-crystals that overcomes these issues. Our method relies on dynamically-operated optical potentials, that instantaneously segment the ion-crystal into cells of a manageable size. We show that these cells behave as nearly independent quantum registers, allowing for parallel entangling gates on all cells. The ability to reconfigure the optical potentials guarantees connectivity across the full ion-crystal, and also enables efficient mid-circuit measurements. We study the implementation of large-scale parallel multi-qubit entangling gates that operate simultaneously on all cells, and present a protocol to compensate for crosstalk errors, enabling full-scale usage of an extensively large register. We illustrate that this architecture is advantageous both for fault-tolerant digital quantum computation and for analog quantum simulations.

Published
2023

15. Written Language: A Promising Gateway to Anxiety Disorders Assessment

Author

Luisa Avram, Mugur Daniel Ciumageanu, and Florin Alin Sava

Abstract

Currently, self-report measures are the primary assessment tool for anxiety disorders. Since they have some limitations, alternative measurements, such as language-based measures, are worth investigating. This paper explores which language markers signal anxiety in fictitious stories written in response to four Thematic Apperception Test (TAT) cards. Participants (n = 492) from a non-probabilistic convenience sample were asked to write a short story next to each TAT card after completing the Generalized Anxiety Disorder-7. We used RoLIWC2015 to conduct the text analysis and applied the LASSO method to identify which language markers predict anxiety. The results showed that the respondents scoring high on anxiety also tend to use more words expressing negative emotions, and fewer words expressing positive emotions. Moreover, their language contained a higher frequency of words that implied semantic differentiation (i.e., but, else) and a lower frequency of words indicating leisure. In conclusion, this paper aims to shed new light on the multimethod assessment of anxiety, mainly focused on specific language signatures as reliable predictors of anxiety symptoms. Further research using more extensive text data is recommended to discover more linguistic markers and improve prediction accuracy.

Published
2024
Full Text
View/download PDF

18. Dynamics of an SIR epidemic model with limited medical resources, revisited and corrected

Author

Adenane, Rim, Avram, Florin, Fatini, Mohamed El, and Gupta, R. P.

Subjects
Mathematics - Dynamical Systems
Abstract

This paper generalizes and corrects a famous paper (more than 200 citations) concerning Hopf and Bogdanov-Takens bifurcations due to L. Zhou and M. Fan, "Dynamics of an SIR epidemic model with limited medical resources revisited", in which we discovered a significant numerical error. Importantly, unlike the paper of Zhou and Fan and several other papers that followed them, we offer a notebook where the reader may recover all the results and modify them for analyzing similar models. Our calculations lead to the introduction of some interesting symbolic objects, "Groebner eliminated traces and determinants" - see (4.5), (4.6), which seem to have appeared here for the first time and which might be of independent interest. We hope our paper might serve as yet another alarm bell regarding the importance of accompanying papers involving complicated hand computations by electronic notebooks.

Published
2023

19. End-to-End Lip Reading in Romanian with Cross-Lingual Domain Adaptation and Lateral Inhibition

Author

Mănescu, Emilian-Claudiu, Smădu, Răzvan-Alexandru, Avram, Andrei-Marius, Cercel, Dumitru-Clementin, and Pop, Florin

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

Lip reading or visual speech recognition has gained significant attention in recent years, particularly because of hardware development and innovations in computer vision. While considerable progress has been obtained, most models have only been tested on a few large-scale datasets. This work addresses this shortcoming by analyzing several architectures and optimizations on the underrepresented, short-scale Romanian language dataset called Wild LRRo. Most notably, we compare different backend modules, demonstrating the effectiveness of adding ample regularization methods. We obtain state-of-the-art results using our proposed method, namely cross-lingual domain adaptation and unlabeled videos from English and German datasets to help the model learn language-invariant features. Lastly, we assess the performance of adding a layer inspired by the neural inhibition mechanism., Comment: 7 pages, 4 figures, Accepted by WI-IAT 2023

Published
2023

20. Disposable face masks: a direct source for inhalation of microplastics

Author

Prada, Andres F., Distler, Avram, Cheng, Shyuan, Scott, John W., Chamorro, Leonardo P., Subramanian, Ganesh, Verma, Vishal, and Turner, Andrew

Subjects
Physics - Medical Physics, Physics - Fluid Dynamics
Abstract

Surgical masks have played a crucial role in healthcare facilities to protect against respiratory and infectious diseases, particularly during the COVID-19 pandemic. However, the synthetic fibers, mainly made of polypropylene, used in their production may adversely affect the environment and human health. Recent studies have confirmed the presence of microplastics and fibers in human lungs and have related these synthetic particles with the occurrence of pulmonary ground glass nodules. Using a piston system to simulate human breathing, this study investigates the role of surgical masks as a direct source of inhalation of microplastics. Results reveal the release of particles of sizes ranging from nanometers (300 nm) to millimeters (~2 mm) during normal breathing conditions, raising concerns about the potential health risks. Notably, large visible particles (> 1 mm) were observed to be ejected from masks with limited wear after only a few breathing cycles. Given the widespread use of masks by healthcare workers and the potential future need for mask usage by the general population during seasonal infectious diseases or new pandemics, developing face masks using safe materials for both users and the environment is imperative., Comment: 11 pages, 3 figures

Published
2023

21. Beyond the Global Brain Differences: Intraindividual Variability Differences in 1q21.1 Distal and 15q11.2 BP1-BP2 Deletion Carriers.

Author

Boen, Rune, Kaufmann, Tobias, van der Meer, Dennis, Frei, Oleksandr, Agartz, Ingrid, Ames, David, Andersson, Micael, Armstrong, Nicola, Artiges, Eric, Atkins, Joshua, Bauer, Jochen, Benedetti, Francesco, Boomsma, Dorret, Brodaty, Henry, Brosch, Katharina, Buckner, Randy, Cairns, Murray, Calhoun, Vince, Caspers, Svenja, Cichon, Sven, Corvin, Aiden, Crespo-Facorro, Benedicto, Dannlowski, Udo, David, Friederike, de Geus, Eco, de Zubicaray, Greig, Desrivières, Sylvane, Doherty, Joanne, Donohoe, Gary, Ehrlich, Stefan, Eising, Else, Espeseth, Thomas, Fisher, Simon, Forstner, Andreas, Fortaner-Uyà, Lidia, Frouin, Vincent, Fukunaga, Masaki, Ge, Tian, Glahn, David, Goltermann, Janik, Grabe, Hans, Green, Melissa, Groenewold, Nynke, Grotegerd, Dominik, Grøntvedt, Gøril, Hahn, Tim, Hashimoto, Ryota, Hehir-Kwa, Jayne, Henskens, Frans, Holmes, Avram, Håberg, Asta, Haavik, Jan, Jacquemont, Sebastien, Jansen, Andreas, Jockwitz, Christiane, Jönsson, Erik, Kikuchi, Masataka, Kircher, Tilo, Kumar, Kuldeep, Le Hellard, Stephanie, Leu, Costin, Linden, David, Liu, Jingyu, Loughnan, Robert, Mather, Karen, McMahon, Katie, McRae, Allan, Medland, Sarah, Meinert, Susanne, Moreau, Clara, Morris, Derek, Mowry, Bryan, Mühleisen, Thomas, Nenadić, Igor, Nöthen, Markus, Nyberg, Lars, Ophoff, Roel, Owen, Michael, Pantelis, Christos, Paolini, Marco, Paus, Tomas, Pausova, Zdenka, Persson, Karin, Quidé, Yann, Marques, Tiago, Sachdev, Perminder, Sando, Sigrid, Schall, Ulrich, Scott, Rodney, Selbæk, Geir, Shumskaya, Elena, Silva, Ana, Sisodiya, Sanjay, Stein, Frederike, Stein, Dan, Straube, Benjamin, Streit, Fabian, Strike, Lachlan, Teumer, Alexander, and Teutenberg, Lea

Subjects
15q11.2 BP1-BP2, 1q21.1 distal, Brain structure, Copy number variants, Intraindividual variability, Magnetic resonance imaging, Humans, Chromosome Deletion, Brain, Magnetic Resonance Imaging, Abnormalities, Multiple, Chromosomes, Human, Pair 15, DNA Copy Number Variations
Abstract

BACKGROUND: Carriers of the 1q21.1 distal and 15q11.2 BP1-BP2 copy number variants exhibit regional and global brain differences compared with noncarriers. However, interpreting regional differences is challenging if a global difference drives the regional brain differences. Intraindividual variability measures can be used to test for regional differences beyond global differences in brain structure. METHODS: Magnetic resonance imaging data were used to obtain regional brain values for 1q21.1 distal deletion (n = 30) and duplication (n = 27) and 15q11.2 BP1-BP2 deletion (n = 170) and duplication (n = 243) carriers and matched noncarriers (n = 2350). Regional intra-deviation scores, i.e., the standardized difference between an individuals regional difference and global difference, were used to test for regional differences that diverge from the global difference. RESULTS: For the 1q21.1 distal deletion carriers, cortical surface area for regions in the medial visual cortex, posterior cingulate, and temporal pole differed less and regions in the prefrontal and superior temporal cortex differed more than the global difference in cortical surface area. For the 15q11.2 BP1-BP2 deletion carriers, cortical thickness in regions in the medial visual cortex, auditory cortex, and temporal pole differed less and the prefrontal and somatosensory cortex differed more than the global difference in cortical thickness. CONCLUSIONS: We find evidence for regional effects beyond differences in global brain measures in 1q21.1 distal and 15q11.2 BP1-BP2 copy number variants. The results provide new insight into brain profiling of the 1q21.1 distal and 15q11.2 BP1-BP2 copy number variants, with the potential to increase understanding of the mechanisms involved in altered neurodevelopment.

Published
2024

22. E-FAST Ultrasound Training Curriculum for Prehospital Emergency Medical Service (EMS) Clinicians

Author

Nguyen, BS, Clever M., Hartmann, BS, EMT-A, Krista, Goodmurphy, PhD, Craig, and Flamm, DO, EMT-P, FACEP, FAEMS, Avram

Abstract

Audience and Type of Curriculum: Audience and type of curriculum: This hybrid, asynchronous curriculum is designed for prehospital clinician colleagues, including but not limited to emergency medical technicians (EMT), advanced EMTs (AEMT), EMT-paramedics (EMT-P), critical care EMT-Ps (CCEMTP), critical care transport nurses (CCTN), and certified flight registered nurses (CFRN) to learn and practice ultrasound fundamentals in the setting of a standardized extended focused assessment with sonography in trauma (E- FAST) exam.Length of Curriculum: Over a five-month curriculum, learners will perform a pre-test, review online module lectures, attend an ultrasound scanning workshop, and perform post-test examinations.Introduction: The extended-focused assessment with sonography in trauma (E-FAST) exam can identify intrathoracic and intraabdominal free fluid, as well as pneumothoraces. The E-FAST ultrasound exam has previously been taught to clinicians of various backgrounds in healthcare including emergency medical service (EMS). However, an open-access, systemized curriculum for teaching E-FAST exams to EMS clinicians has not been published.Educational Goals: By the end of these training activities, prehospital EMS learners will be able to demonstrate foundational ultrasound skills in scanning, interpretation, and artifact recognition by identifying pertinent organs and anatomically relevant structures for an E-FAST examination. Learners will differentiate between normal and pathologic E-FAST ultrasound images by identifying the presence of free fluid and lung sliding. Learners will also explain the clinical significance and application of detecting free fluid during an E- FAST scan.Educational Methods: The educational strategies used in this curriculum include a hybrid, asynchronous curriculum encompassing 2.5 hours of lectures derived from online learning modules and in-person review. In addition, learners will attend 2 hours of hands-on proctored ultrasound scanning practicing E-FAST examinations.Research Methods: An online 13-question pre-test was administered prior to the study. An online post-test and in-person scanning OSCEs were administered at least eight weeks after their scheduled workshop consisting of an online 13-question multiple-choice post-test, a confidence survey, and a hands-on E-FAST Objectively Structured Clinical Exam (OSCE) session. A non-parametric Wilcoxon signed-rank test was performed between each pre-test and post-test metric to examine the statistical differences of paired data.Results: Post-test scores demonstrated statistically significant improvement in both image interpretation exams and ultrasound self-efficacy from the pre-test. The mean pre-test and post-test scores were 55.46% (7.21 ± 1.99) and 84.23% (10.89 ± 1.59) correct out of 13 questions, respectively (p < 0.0001). Participants surveyed an increase in self-efficacy reflected by a Likert scale for ultrasound usage and image interpretation (p < 0.005). The average post-test OSCE E-FAST exam score was 37.89 ± 2.76 out of 42 points (90.21%).Discussion: This 4.5-hour hybrid asynchronous model demonstrates an effective curriculum for teaching E- FAST ultrasound to prehospital clinicians.Topics: Ultrasound, sonography, prehospital clinicians, emergency medical services (EMS), paramedics, critical care transport, extended focused assessment with sonography in trauma (E-FAST), free fluid, sliding lung sign, elective, pain.

Published
2024

23. Trait Resilience as a Moderator between Personality Dysfunction and Caregiving Stress in Caregivers of Children and Adults with Developmental Disabilities

Author

Claudia I. Iacob, Ruxandra Folostina, and Eugen Avram

Abstract

Background: Long-term care of a relative with a disability is associated with negative consequences on the caregiver's mental health. Therefore, investigating how some personality traits, such as resilience, protect caregivers with dysfunctional personality traits from caregiving stress is necessary. This study examines the moderating role of resilience in the relationship between caregiver's personality dysfunction and care stress. Methods: A total of 224 family caregivers of children and adults with developmental disabilities participated in this cross-sectional research. They completed self-report measures of resilience, personality dysfunction, and care stress. Results: The results show that medium and high levels of resilience protect familial caregivers from the adverse effects of personality dysfunction on stress. The relationship is maintained for three of the five dysfunctional personality traits (antagonism, disinhibition, and psychoticism). Conclusions: From a theoretical point of view, the results show the contribution of the dimensional personality model to the study of caregiving stress. From a practical standpoint, the results can be used to optimise the resilience of familial caregivers, providing them with tools to take better care of their relatives.

Published
2024
Full Text
View/download PDF

24. Explicit mathematical epidemiology results on age renewal kernels and R0 formulas are often consequences of the rank one property of the next generation matrix

Author

Avram, Florin, Adenane, Rim, Goreac, Dan, and Halanay, Andrei

Subjects
Quantitative Biology - Populations and Evolution
Abstract

A very large class of ODE epidemic models (2.2) discussed in this paper enjoys the property of admitting also an integral renewal formulation, with respect to an "age of infection kernel" a(t) which has a matrix exponential form (3.2). We observe first that a very short proof of this fact is available when there is only one susceptible compartment, and when its associated "new infections" matrix has rank one. In this case, a(t) normalized to have integral 1, is precisely the probabilistic law which governs the time spent in all the "infectious states associated to the susceptible compartment", and the normalization is precisely the basic replacement number. The Laplace transform (LT) of a(t) is a generalization of the basic replacement number, and its structure reflects the laws of the times spent in each infectious state. Subsequently, we show that these facts admit extensions to processes with several susceptible classes, provided that all of them have a new infections matrix of rank one. These results reveal that the ODE epidemic models highlighted below have also interesting probabilistic properties.

Published
2023

25. Towards Improving the Performance of Pre-Trained Speech Models for Low-Resource Languages Through Lateral Inhibition

Author

Avram, Andrei-Marius, Smădu, Răzvan-Alexandru, Păiş, Vasile, Cercel, Dumitru-Clementin, Ion, Radu, and Tufiş, Dan

Subjects
Computer Science - Computation and Language, Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing
Abstract

With the rise of bidirectional encoder representations from Transformer models in natural language processing, the speech community has adopted some of their development methodologies. Therefore, the Wav2Vec models were introduced to reduce the data required to obtain state-of-the-art results. This work leverages this knowledge and improves the performance of the pre-trained speech models by simply replacing the fine-tuning dense layer with a lateral inhibition layer inspired by the biological process. Our experiments on Romanian, a low-resource language, show an average improvement of 12.5% word error rate (WER) using the lateral inhibition layer. In addition, we obtain state-of-the-art results on both the Romanian Speech Corpus and the Robin Technical Acquisition Corpus with 1.78% WER and 29.64% WER, respectively., Comment: Accepted at TSP2023

Published
2023

26. Multilingual Multiword Expression Identification Using Lateral Inhibition and Domain Adaptation

Author

Avram, Andrei-Marius, Mititelu, Verginica Barbu, Păiş, Vasile, Cercel, Dumitru-Clementin, and Trăuşan-Matu, Ştefan

Subjects
Computer Science - Computation and Language
Abstract

Correctly identifying multiword expressions (MWEs) is an important task for most natural language processing systems since their misidentification can result in ambiguity and misunderstanding of the underlying text. In this work, we evaluate the performance of the mBERT model for MWE identification in a multilingual context by training it on all 14 languages available in version 1.2 of the PARSEME corpus. We also incorporate lateral inhibition and language adversarial training into our methodology to create language-independent embeddings and improve its capabilities in identifying multiword expressions. The evaluation of our models shows that the approach employed in this work achieves better results compared to the best system of the PARSEME 1.2 competition, MTLB-STRUCT, on 11 out of 14 languages for global MWE identification and on 12 out of 14 languages for unseen MWE identification. Additionally, averaged across all languages, our best approach outperforms the MTLB-STRUCT system by 1.23% on global MWE identification and by 4.73% on unseen global MWE identification., Comment: Accepted at Mathematics 2023

Published
2023

27. Adversarial Capsule Networks for Romanian Satire Detection and Sentiment Analysis

Author

Echim, Sebastian-Vasile, Smădu, Răzvan-Alexandru, Avram, Andrei-Marius, Cercel, Dumitru-Clementin, and Pop, Florin

Subjects
Computer Science - Computation and Language
Abstract

Satire detection and sentiment analysis are intensively explored natural language processing (NLP) tasks that study the identification of the satirical tone from texts and extracting sentiments in relationship with their targets. In languages with fewer research resources, an alternative is to produce artificial examples based on character-level adversarial processes to overcome dataset size limitations. Such samples are proven to act as a regularization method, thus improving the robustness of models. In this work, we improve the well-known NLP models (i.e., Convolutional Neural Networks, Long Short-Term Memory (LSTM), Bidirectional LSTM, Gated Recurrent Units (GRUs), and Bidirectional GRUs) with adversarial training and capsule networks. The fine-tuned models are used for satire detection and sentiment analysis tasks in the Romanian language. The proposed framework outperforms the existing methods for the two tasks, achieving up to 99.08% accuracy, thus confirming the improvements added by the capsule layers and the adversarial training in NLP approaches., Comment: 15 pages, 3 figures, Accepted by NLDB 2023

Published
2023
Full Text
View/download PDF

28. RoBERTweet: A BERT Language Model for Romanian Tweets

Author

Tăiatu, Iulian-Marius, Avram, Andrei-Marius, Cercel, Dumitru-Clementin, and Pop, Florin

Subjects
Computer Science - Computation and Language
Abstract

Developing natural language processing (NLP) systems for social media analysis remains an important topic in artificial intelligence research. This article introduces RoBERTweet, the first Transformer architecture trained on Romanian tweets. Our RoBERTweet comes in two versions, following the base and large architectures of BERT. The corpus used for pre-training the models represents a novelty for the Romanian NLP community and consists of all tweets collected from 2008 to 2022. Experiments show that RoBERTweet models outperform the previous general-domain Romanian and multilingual language models on three NLP tasks with tweet inputs: emotion detection, sexist language identification, and named entity recognition. We make our models and the newly created corpus of Romanian tweets freely available., Comment: Accepted at NLDB2023

Published
2023

38. “I just wanted more”: Hereditary cancer syndromes patients’ perspectives on the utility of circulating tumour DNA testing for cancer screening

Author

Adi-Wauran, Ella, Clausen, Marc, Shickh, Salma, Gagliardi, Anna R., Denburg, Avram, Oldfield, Leslie E., Sam, Jordan, Reble, Emma, Krishnapillai, Suvetha, Regier, Dean A., Baxter, Nancy N., Dawson, Lesa, Penney, Lynette S., Foulkes, William, Basik, Mark, Sun, Sophie, Schrader, Kasmintan A., Karsan, Aly, Pollett, Aaron, Pugh, Trevor J., Kim, Raymond H., and Bombard, Yvonne

Published
2024
Full Text
View/download PDF

39. Romanian Multiword Expression Detection Using Multilingual Adversarial Training and Lateral Inhibition

Author

Avram, Andrei-Marius, Mititelu, Verginica Barbu, and Cercel, Dumitru-Clementin

Subjects
Computer Science - Computation and Language
Abstract

Multiword expressions are a key ingredient for developing large-scale and linguistically sound natural language processing technology. This paper describes our improvements in automatically identifying Romanian multiword expressions on the corpus released for the PARSEME v1.2 shared task. Our approach assumes a multilingual perspective based on the recently introduced lateral inhibition layer and adversarial training to boost the performance of the employed multilingual language models. With the help of these two methods, we improve the F1-score of XLM-RoBERTa by approximately 2.7% on unseen multiword expressions, the main task of the PARSEME 1.2 edition. In addition, our results can be considered SOTA performance, as they outperform the previous results on Romanian obtained by the participants in this competition., Comment: Accepted at the 19th Workshop on Multiword Expressions (MWE 2023). The arxiv version contains some minor corrections

Published
2023

40. Vision Transformers with Mixed-Resolution Tokenization

Author

Ronen, Tomer, Levy, Omer, and Golbert, Avram

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Vision Transformer models process input images by dividing them into a spatially regular grid of equal-size patches. Conversely, Transformers were originally introduced over natural language sequences, where each token represents a subword - a chunk of raw data of arbitrary size. In this work, we apply this approach to Vision Transformers by introducing a novel image tokenization scheme, replacing the standard uniform grid with a mixed-resolution sequence of tokens, where each token represents a patch of arbitrary size. Using the Quadtree algorithm and a novel saliency scorer, we construct a patch mosaic where low-saliency areas of the image are processed in low resolution, routing more of the model's capacity to important image regions. Using the same architecture as vanilla ViTs, our Quadformer models achieve substantial accuracy gains on image classification when controlling for the computational budget. Code and models are publicly available at https://github.com/TomerRonen34/mixed-resolution-vit .

Published
2023

41. Idiopathic Pulmonary Fibrosis Is Associated with Common Genetic Variants and Limited Rare Variants.

Author

Peljto, Anna L, Blumhagen, Rachel Z, Walts, Avram D, Cardwell, Jonathan, Powers, Julia, Corte, Tamera J, Dickinson, Joanne L, Glaspole, Ian, Moodley, Yuben P, Vasakova, Martina Koziar, Bendstrup, Elisabeth, Davidsen, Jesper R, Borie, Raphael, Crestani, Bruno, Dieude, Philippe, Bonella, Francesco, Costabel, Ulrich, Gudmundsson, Gunnar, Donnelly, Seamas C, Egan, Jim, Henry, Michael T, Keane, Michael P, Kennedy, Marcus P, McCarthy, Cormac, McElroy, Aoife N, Olaniyi, Joshua A, O'Reilly, Katherine MA, Richeldi, Luca, Leone, Paolo M, Poletti, Venerino, Puppo, Francesco, Tomassetti, Sara, Luzzi, Valentina, Kokturk, Nurdan, Mogulkoc, Nesrin, Fiddler, Christine A, Hirani, Nikhil, Jenkins, R Gisli, Maher, Toby M, Molyneaux, Philip L, Parfrey, Helen, Braybrooke, Rebecca, Blackwell, Timothy S, Jackson, Peter D, Nathan, Steven D, Porteous, Mary K, Brown, Kevin K, Christie, Jason D, Collard, Harold R, Eickelberg, Oliver, Foster, Elena E, Gibson, Kevin F, Glassberg, Marilyn, Kass, Daniel J, Kropski, Jonathan A, Lederer, David, Linderholm, Angela L, Loyd, Jim, Mathai, Susan K, Montesi, Sydney B, Noth, Imre, Oldham, Justin M, Palmisciano, Amy J, Reichner, Cristina A, Rojas, Mauricio, Roman, Jesse, Schluger, Neil, Shea, Barry S, Swigris, Jeffrey J, Wolters, Paul J, Zhang, Yingze, Prele, Cecilia MA, Enghelmayer, Juan I, Otaola, Maria, Ryerson, Christopher J, Salinas, Mauricio, Sterclova, Martina, Gebremariam, Tewodros H, Myllärniemi, Marjukka, Carbone, Roberto G, Furusawa, Haruhiko, Hirose, Masaki, Inoue, Yoshikazu, Miyazaki, Yasunari, Ohta, Ken, Ohta, Shin, Okamoto, Tsukasa, Kim, Dong Soon, Pardo, Annie, Selman, Moises, Aranda, Alvaro U, Park, Moo Suk, Park, Jong Sun, Song, Jin Woo, Molina-Molina, Maria, Planas-Cerezales, Lurdes, Westergren-Thorsson, Gunilla, Smith, Albert V, Manichaikul, Ani W, and Kim, John S

Subjects
Biomedical and Clinical Sciences, Cardiovascular Medicine and Haematology, Clinical Sciences, Autoimmune Disease, Lung, Rare Diseases, Genetics, Human Genome, Prevention, Precision Medicine, 2.1 Biological and endogenous factors, Good Health and Well Being, Humans, Idiopathic Pulmonary Fibrosis, Whole Genome Sequencing, Exome, whole-genome sequencing, interstitial lung disease, TOPMed, genetic association studies, telomerase, Medical and Health Sciences, Respiratory System, Cardiovascular medicine and haematology, Clinical sciences
Abstract

Rationale: Idiopathic pulmonary fibrosis (IPF) is a rare, irreversible, and progressive disease of the lungs. Common genetic variants, in addition to nongenetic factors, have been consistently associated with IPF. Rare variants identified by candidate gene, family-based, and exome studies have also been reported to associate with IPF. However, the extent to which rare variants, genome-wide, may contribute to the risk of IPF remains unknown. Objectives: We used whole-genome sequencing to investigate the role of rare variants, genome-wide, on IPF risk. Methods: As part of the Trans-Omics for Precision Medicine Program, we sequenced 2,180 cases of IPF. Association testing focused on the aggregated effect of rare variants (minor allele frequency ⩽0.01) within genes or regions. We also identified individual rare variants that are influential within genes and estimated the heritability of IPF on the basis of rare and common variants. Measurements and Main Results: Rare variants in both TERT and RTEL1 were significantly associated with IPF. A single rare variant in each of the TERT and RTEL1 genes was found to consistently influence the aggregated test statistics. There was no significant evidence of association with other previously reported rare variants. The SNP heritability of IPF was estimated to be 32% (SE = 3%). Conclusions: Rare variants within the TERT and RTEL1 genes and well-established common variants have the largest contribution to IPF risk overall. Efforts in risk profiling or the development of therapies for IPF that focus on TERT, RTEL1, common variants, and environmental risk factors are likely to have the largest impact on this complex disease.

Published
2023

42. Exploring Romanian Engineering Students' Perceptions of COVID-19 Emergency e-Learning Situation. A Mixed-Method Case Study

Author

Alexa, Lidia, Pîslaru, Marius, Avasilcai, Silvia, Lucescu, Leti?ia, Bujor, Adriana, and Avram, Elena

Abstract

The COVID-19 pandemic is the most disturbing event in the lifetime of most of our planet's citizens. The lockdown measures directly impacted many areas of our lives, including the educational sector, because locking down countries meant implicitly locking down the educational system. Moreover, what was first considered a temporary solution for an extraordinary situation began to look more and more like a medium to long-term general rule. Nevertheless, the questions are: are we all ready to move the entire educational process online and fully understand the challenges and implications for all stakeholders involved? This two-part research aims to provide some answers to these questions by identifying and analyzing the perceptions of Romanian engineering students enrolled at "Gheorghe Asachi" Technical University of Iasi (TUIASI) regarding the changes registered in the past year once the emergency e-learning situation started. The first part of the research was conducted between April and May 2020 through an online survey among 134 engineering students. It aimed at identifying the students' perception of the online learning systems provided by their university, considering the significant speed with which changes were imposed. In addition, this research phase focused on students' access to resources and knowledge to use and integrate online learning into their study routine. The second part of the research was carried out after almost a year of e-learning between March and April 2021 and consisted of six online focus groups with 36 students and aimed at identifying the main advantages and challenges students experience throughout the online educational process. The research revealed that although students are digital natives, they still have difficulties harnessing e-learning's advantages and integrating them into their study routine. Another significant aspect refers to the changing role of the professor perceived not only as an instructor but as a mentor during a time of crisis. The study results can offer higher education institutions insight and valuable information that can be used in designing and implementing online and hybrid activities and classes that better fit the students' needs and expectations in terms of e-learning.

Published
2022

43. BERT-based Authorship Attribution on the Romanian Dataset called ROST

Author

Avram, Sanda-Maria

Subjects
Computer Science - Artificial Intelligence, 68T50 (Primary) 68T01, 68T05, 68T07 (Secondary), I.2.0, I.2.7
Abstract

Being around for decades, the problem of Authorship Attribution is still very much in focus currently. Some of the more recent instruments used are the pre-trained language models, the most prevalent being BERT. Here we used such a model to detect the authorship of texts written in the Romanian language. The dataset used is highly unbalanced, i.e., significant differences in the number of texts per author, the sources from which the texts were collected, the time period in which the authors lived and wrote these texts, the medium intended to be read (i.e., paper or online), and the type of writing (i.e., stories, short stories, fairy tales, novels, literary articles, and sketches). The results are better than expected, sometimes exceeding 87\% macro-accuracy., Comment: arXiv admin note: text overlap with arXiv:2211.05180

Published
2023

44. TA-DA: Topic-Aware Domain Adaptation for Scientific Keyphrase Identification and Classification (Student Abstract)

Author

Smădu, Răzvan-Alexandru, Zaharia, George-Eduard, Avram, Andrei-Marius, Cercel, Dumitru-Clementin, Dascalu, Mihai, and Pop, Florin

Subjects
Computer Science - Computation and Language
Abstract

Keyphrase identification and classification is a Natural Language Processing and Information Retrieval task that involves extracting relevant groups of words from a given text related to the main topic. In this work, we focus on extracting keyphrases from scientific documents. We introduce TA-DA, a Topic-Aware Domain Adaptation framework for keyphrase extraction that integrates Multi-Task Learning with Adversarial Training and Domain Adaptation. Our approach improves performance over baseline models by up to 5% in the exact match of the F1-score., Comment: Accepted by AAAI 2023 Student Abstract

Published
2022

45. A comparison of several AI techniques for authorship attribution on Romanian texts

Author

Avram, Sanda Maria and Oltean, Mihai

Subjects
Computer Science - Artificial Intelligence, 03B65, 62H30, 68T01, 68T05, 68T07, 68T10, 68T20, 68T30, 68T50, 91F20, I.2.0, I.2.6
Abstract

Determining the author of a text is a difficult task. Here we compare multiple AI techniques for classifying literary texts written by multiple authors by taking into account a limited number of speech parts (prepositions, adverbs, and conjunctions). We also introduce a new dataset composed of texts written in the Romanian language on which we have run the algorithms. The compared methods are Artificial Neural Networks, Support Vector Machines, Multi Expression Programming, Decision Trees with C5.0, and k-Nearest Neighbour. Numerical experiments show, first of all, that the problem is difficult, but some algorithms are able to generate decent errors on the test set., Comment: We initially used the Accuracy evaluation tool to compute the macro-accuracy, obtaining a value of 88.84%. We, thereafter discovered that this value was erroneous and used other methods which gave us the value of 80.94% for the macro-accuracy. In this version of the paper we present the python module solution by using sklearn.metrics's classification_report and balanced_accuracy_score

Published
2022
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results