Search

Your search keyword '"Singh, Surya"' showing total 2,873 results
Start Over Author "Singh, Surya"

Refine your results

more »

more »

more »

more »

more »
2,873 results on '"Singh, Surya"'

4. A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions

Author

Gupta, Shailja, Ranjan, Rajesh, and Singh, Surya Narayan

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

This paper presents a comprehensive study of Retrieval-Augmented Generation (RAG), tracing its evolution from foundational concepts to the current state of the art. RAG combines retrieval mechanisms with generative language models to enhance the accuracy of outputs, addressing key limitations of LLMs. The study explores the basic architecture of RAG, focusing on how retrieval and generation are integrated to handle knowledge-intensive tasks. A detailed review of the significant technological advancements in RAG is provided, including key innovations in retrieval-augmented language models and applications across various domains such as question-answering, summarization, and knowledge-based tasks. Recent research breakthroughs are discussed, highlighting novel methods for improving retrieval efficiency. Furthermore, the paper examines ongoing challenges such as scalability, bias, and ethical concerns in deployment. Future research directions are proposed, focusing on improving the robustness of RAG models, expanding the scope of application of RAG models, and addressing societal implications. This survey aims to serve as a foundational resource for researchers and practitioners in understanding the potential of RAG and its trajectory in natural language processing., Comment: 4 Figures

Published
2024

5. Early review of Gender Bias of OpenAI o1-mini: Higher Intelligence of LLM does not necessarily solve Gender Bias and Stereotyping issues

Author

Ranjan, Rajesh, Gupta, Shailja, and Singh, Surya Naranyan

Subjects
Computer Science - Computers and Society
Abstract

In this paper, we present an early evaluation of the OpenAI o1-mini model, analyzing its performance in gender inclusivity and bias. Our research, conducted on 700 personas 350 from GPT-4o mini and 350 from o1-mini, reveals that despite improvements in inclusivity regarding personality traits and preferences, significant gender biases remain. For instance, o1-mini rated male personas higher in competency, with a score of 8.06, compared to female personas at 7.88 and non-binary personas at 7.80. Additionally, o1-mini assigned PhD roles to 28% of male personas but only 22.4% of females and 0% of non-binary personas. Male personas were also more likely to be perceived as successful founders, at 69.4%, and CEOs, at 62.17%, compared to female personas at 67.97% and 61.11%, and non-binary personas at 65.7% and 58.37%. The analysis reveals persistent gender biases across fields like Engineering, Data, and Technology, where males dominate, reflecting traditional stereotypes. Conversely, fields like Design, Art, and Marketing show a stronger presence of females, reinforcing societal notions that associate creativity and communication with females. These findings highlight ongoing challenges in mitigating gender bias, reinforcing the need for further interventions to ensure equitable representation across all genders in AI models.

Published
2024

6. A Comprehensive Survey of Bias in LLMs: Current Landscape and Future Directions

Author

Ranjan, Rajesh, Gupta, Shailja, and Singh, Surya Narayan

Subjects
Computer Science - Computation and Language, Computer Science - Artificial Intelligence, Computer Science - Computers and Society, Computer Science - Human-Computer Interaction
Abstract

Large Language Models(LLMs) have revolutionized various applications in natural language processing (NLP) by providing unprecedented text generation, translation, and comprehension capabilities. However, their widespread deployment has brought to light significant concerns regarding biases embedded within these models. This paper presents a comprehensive survey of biases in LLMs, aiming to provide an extensive review of the types, sources, impacts, and mitigation strategies related to these biases. We systematically categorize biases into several dimensions. Our survey synthesizes current research findings and discusses the implications of biases in real-world applications. Additionally, we critically assess existing bias mitigation techniques and propose future research directions to enhance fairness and equity in LLMs. This survey serves as a foundational resource for researchers, practitioners, and policymakers concerned with addressing and understanding biases in LLMs., Comment: 2 Tables, 1 Figure

Published
2024

7. Comprehensive Study on Sentiment Analysis: From Rule-based to modern LLM based system

Author

Gupta, Shailja, Ranjan, Rajesh, and Singh, Surya Narayan

Subjects
Computer Science - Computation and Language, Computer Science - Artificial Intelligence, Computer Science - Computers and Society, Computer Science - Human-Computer Interaction
Abstract

This paper provides a comprehensive survey of sentiment analysis within the context of artificial intelligence (AI) and large language models (LLMs). Sentiment analysis, a critical aspect of natural language processing (NLP), has evolved significantly from traditional rule-based methods to advanced deep learning techniques. This study examines the historical development of sentiment analysis, highlighting the transition from lexicon-based and pattern-based approaches to more sophisticated machine learning and deep learning models. Key challenges are discussed, including handling bilingual texts, detecting sarcasm, and addressing biases. The paper reviews state-of-the-art approaches, identifies emerging trends, and outlines future research directions to advance the field. By synthesizing current methodologies and exploring future opportunities, this survey aims to understand sentiment analysis in the AI and LLM context thoroughly., Comment: 2 Images

Published
2024

24. OriCon3D: Effective 3D Object Detection using Orientation and Confidence

Author

Rajani, Dhyey Manish, Singh, Surya Pratap, and Swayampakula, Rahul Kashyap

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

In this paper, we propose an advanced methodology for the detection of 3D objects and precise estimation of their spatial positions from a single image. Unlike conventional frameworks that rely solely on center-point and dimension predictions, our research leverages a deep convolutional neural network-based 3D object weighted orientation regression paradigm. These estimates are then seamlessly integrated with geometric constraints obtained from a 2D bounding box, resulting in derivation of a comprehensive 3D bounding box. Our novel network design encompasses two key outputs. The first output involves the estimation of 3D object orientation through the utilization of a discrete-continuous loss function. Simultaneously, the second output predicts objectivity-based confidence scores with minimal variance. Additionally, we also introduce enhancements to our methodology through the incorporation of lightweight residual feature extractors. By combining the derived estimates with the geometric constraints inherent in the 2D bounding box, our approach significantly improves the accuracy of 3D object pose determination, surpassing baseline methodologies. Our method is rigorously evaluated on the KITTI 3D object detection benchmark, demonstrating superior performance.

Published
2023

25. Twilight SLAM: Navigating Low-Light Environments

Author

Singh, Surya Pratap, Mazotti, Billy, Rajani, Dhyey Manish, Mayilvahanan, Sarvesh, Li, Guoyuan, and Ghaffari, Maani

Subjects
Computer Science - Robotics
Abstract

This paper presents a detailed examination of low-light visual Simultaneous Localization and Mapping (SLAM) pipelines, focusing on the integration of state-of-the-art (SOTA) low-light image enhancement algorithms with standard and contemporary SLAM frameworks. The primary objective of our work is to address a pivotal question: Does illuminating visual input significantly improve localization accuracy in both semi-dark and dark environments? In contrast to previous works that primarily address partially dim-lit datasets, we comprehensively evaluate various low-light SLAM pipelines across obscurely-lit environments. Employing a meticulous experimental approach, we qualitatively and quantitatively assess different combinations of image enhancers and SLAM frameworks, identifying the best-performing combinations for feature-based visual SLAM. The findings advance low-light SLAM by highlighting the practical implications of enhancing visual input for improved localization accuracy in challenging lighting conditions. This paper also offers valuable insights, encouraging further exploration of visual enhancement strategies for enhanced SLAM performance in real-world scenarios.

Published
2023

37. Mortality, perioperative complications and surgical timelines in hip fracture patients: Comparison of the Spanish with the non-Spanish Cohort of the HIP ATTACK-1 trial

Author

Veevaete, Laurent, Waroux, Bernard le Polain de, Lavand'homme, Patricia, Cornu, Olivier, Tribak, Karim, Yombi, Jean C, Touil, Nassim, Bhutia, Jigme T, Clinckaert, Carol, Clippeleir, Dirk De, Reul, Maike, Patel, Ameen, Tandon, Vikas, Gauthier, Leslie P, Avram, Victoria R.A., Winemaker, Mitchell, de Beer, Justin, Simpson, Diane L, Worster, Andrew, Alvarado, Kim A, Gregus, Krysten K, Lawrence, Kelly H, Leong, Darryl P, Joseph, Philip G, Magloire, Patrick, Deheshi, Benjamin, Bisland, Stuart, Wood, Thomas J, Tushinski, Daniel M., Wilson, David A.J., Haider, Shariq, Bali, Kamal, Kearon, Clive, Manach, Yannick Le, Adili, Anthony, Tiboni, Maria E, Neary, John D, Cowan, David D, Khanna, Vickas, Zaki, Amna, Farrell, Janet C, MacDonald, Anne Marie, Conen, David, Wong, Steven C.W., Karbassi, Arsha, Wright, Douglas S, Shanthanna, Harsha, Coughlin, Ryan, Khan, Moin, Wikkerink, Spencer, Quraishi, Faraaz A, Lawendy, Abdel-Rahman, Kishta, Waleed, Schemitsch, Emil, Carey, Timothy, Macleod, Mark D, Sanders, David W, Vasarhelyi, Edward, Bartley, Debra, Dresser, George K, Tieszer, Christina, Jenkinson, Richard J, Shadowitz, Steven, Lee, Jacques S, Choi, Stephen, Kreder, Hans J, Nousiainen, Markku, Kunz, Monica R, Tuazon, Ravianne, Shrikumar, Mopina, Ravi, Bheeshma, Wasserstein, David, Stephen, David J.G., Nam, Diane, Henry, Patrick D.G., Wood, Gavin C.A., Mann, Stephen M., Jaeger, Melanie T., Sivilotti, Marco L.A., Smith, Christopher A., Frank, Christopher C., Grant, Heather, Ploeg, Leone, Yach, Jeff D., Harrison, Mark M., Campbell, Aaron R., Bicknell, Ryan T., Bardana, Davide D., Feibel, Robert J., McIlquham, Katie, Gallant, Catherine, Halman, Samantha, Thiruganasambandamoorth, Venkatesh, Ruggiero, Sara, Hadden, William J., Chen, Brian P.J., Coupal, Stephanie A., McMahon, Stephen J., McLean, Lisa M., Shirali, Hemant R., Haider, Syed Y., Smith, Crystal A., Watts, Evan, Santone, David J., Koo, Kevin, Yee, Allan J., Oyenubi, Ademilola N., Nauth, Aaron, Schemitsch, Emil H., Daniels, Timothy R., Ward, Sarah E., Hall, Jeremy A., Ahn, Henry, Whelan, Daniel B., Atrey, Amit, Khoshbin, Amir, Puskas, David, Droll, Kurt, Cullinan, Claude, Payendeh, Jubin, Lefrancois, Tina, Mozzon, Lise, Marion, Travis, Jacka, Michael J., Greene, James, Menon, Matthew, Stiegelmahr, Robert, Dillane, Derek, Irwin, Marleen, Beaupre, Lauren, Coles, Chad P., Trask, Kelly, MacDonald, Shelley, Trenholm, J.A.I., Oxner, William, Richardson, C.G., Dehghan, Niloofar, Sadoughi, Mehdi, Sharma, Achal, White, Neil J., Olivieri, Loretta, Hunt, Stephen B., Turgeon, Thomas R., Bohm, Eric R., Tran, Sarah, Giilck, Stephen M., Hupel, Tom, Guy, Pierre, O'Brien, Peter J., Duncan, Andrew W., Crawford, Gordon A., hou, Junlin, Zhao, Yanrui, Liu, Yang, Shan, Lei, Wu, Anshi, Muñoz, Juan M., Chaudier, Philippe, Douplat, Marion, Fessy, Michel Henri, Piriou, Vincent, Louboutin, Lucie, David, Jean Stephane, Friggeri, Arnaud, Beroud, Sebastien, Fayet, Jean Marie, Landais, Paul, Leung, Frankie Ka Li, Fang, Christian Xinshuo, Yee, Dennis King Hang, Sancheti, Parag K., Pradhan, Chetan V., Patil, Atul A., Puram, Chetan P., Borate, Madhav P., Kudrimoti, Kiran B., Adhye, Bharati A., Dongre, Himanshu V., John, Bobby, Abraham, Valsamma, Pandey, Ritesh A., Rajkumar, Arti, George, Preetha E., Sigamani, Alen, Stephen, Manesh, Chandran, Nitheesh, Ashraf, Mohammed, Georgekutty, A.M., Sulthan, Ahamad S., Adinarayanan, S., Sharma, Deep, Barnawal, Satish P., Swaminathan, Srinivasan, Bidkar, Prasanna U., Mishra, Sandeep K., Menon, Jagdish, M, Niranjan, Zk, Varghese, Hiremath, Santosh A., Nc, Madhusudhan, Jawali, Abhijit, Gnanadurai, Kingsly R., George, Carolin E., Maddipati, Atarao, Kp, Mary, Sharma, Vijay, Farooque, Kamran, Malhotra, Rajesh, Mittal, Samarth, Sawhney, Chavi, Gupta, Babita, Mathur, Purva, Gamangati, Shivanand, Tripathy, Vijaylaxmi, Menon, Prem H., Dhillon, Mandeep S., Chouhan, Devendra K., Patil, Sharanu, Narayan, Ravi, Lal, Purushotham, Bilchod, Prashanth N., Singh, Surya U., Gattu, Uttam V., Dashputra, Ravi P., Rahate, Prashant V., Turiel, Maurizio, Blasio, Giuseppe De, Accetta, Riccardo, Perazzo, Paolo, Stella, Daniele, Bonadies, Marika, Colombo, Chiara, Fozzato, Stefania, Pino, Fabio, Morelli, Ilaria, Colnaghi, Eleonora, Salini, Vincenzo, Denaro, Giuseppe, Beretta, Luigi, Placella, Giacomo, Giardina, Giuseppe, Binda, Mirko, Marcato, Anna, Guzzetti, Luca, Piccirillo, Fabio, Cecconi, Maurizio, Khor, H.M., Lai, Hou Yee, Kumar, C.S., Chee, K.H., Loh, P.S., Tan, Kit Mun, Singh, Simmrat, Foo, Li Lian, Prakasam, Komella, Chaw, Sook Hui, Lee, Meng-Li, Ngim, Joanne H.L., Boon, Huck Wee, Chin, Im Im, Kleinlugtenbelt, Ydo V., Landman, Ellie B.M., Flikweert, Elvira R., Roerdink, Herbert W., Brokelman, Roy B.G., Elskamp-Meijerman, Hannie F., Horst, Maarten R., Cobben, Jan-Hein M.G., Umer, Masood, Begum, Dilshad, Anjum, Anila, Hashmi, Pervaiz M., Ahmed, Tashfeen, Rashid, Haroon U., Khattak, Mujahid J., Rashid, Rizwan H., Lakdawala, Riaz H., Noordin, Shahryar, Juman, Naveed M., Khan, Robyna I., Riaz, Muhammad M., Bokhari, Syedah S., Almas, Ayesha, Wahab, Hussain, Ali, Arif, Khan, Hammad N., Khan, Eraj K., Nur, Aamer Nabi, Janjua, Kholood A., Orakzai, Sajjad H., Khan, Abdus S., Mustafa, Khawaja J., Sohail, Mian A., Umar, Muhammad, Khan, Siddra A., Ashraf, Muhammad, Khan, Muhammad K., Shiraz, Muhammad, Furgan, Ahmad, Ślęczka, Paweł, Dąbek, Piotr, Kumoń, Adam, Satora, Wojciech, Ambroży, Wojciech, Święch, Mariusz, Rycombel, Jacek, Grzelak, Adrian, Nowak- Kózka, Ilona, Gucwa, Jaroslaw, Machala, Waldemar, Ramokgopa, Mmampapatla T., Firth, Gregory B., Karera, Mwalimu, Fourtounas, Maria, Singh, Virsen, Biscardi, Anna, Iqbal, Muhammad N., Campbell, Ryan J., Maluleke, Matimba L., Moller, Carien, Nhlapo, Lerato, Maqungo, Sithombo, Flint, Margot, Nejthardt, Marcin B., Chetty, Sean, Naidoo, Rubendren, Guerra-Farfan, Ernesto, Tomas-Hernandez, Jordi, Garcia-Sanchez, Yaiza, Clua, Miriam Garrido, Molero-Garcia, Vicente, Minguell-Monyart, Joan, Teixidor-Serra, Jordi, Villar-Casares, Maria del Mar, Marsa, Jordi Selga, Porcel-Vazquez, Juan A., Andres-Peiro, Jose-Vicente, Aguilar, Marc, Mestre-Torres, Jaume, Colomina, Maria J., Guilabert, Patricia, Gozalo, M Luisa Paños, Abarca, Luis, Martin, Nuria, Usua, Gemma, Martinez-Ripol, Pedro, Posada, M.A. Gonzalez, Lalueza-Broto, Pilar, Sanchez-Raya, Judith, Camarena, Jorge Nuñez, Fraguas-Castany, Antoni, Balaguer-Castro, Mariano, Torner, Pere, Jornet-Gibert, Montsant, Serrano-Sanz, Jorge, Cámara-Cabrera, Jaume, Salomó-Domènech, Mònica, Yela-Verdú, Christian, Peig-Font, Anna, Ricol, Laura, Carreras-Castañer, Anna, Martínez-Sañudo, Luis, Herranz, Susana, Feijoo-Massó, Carlos, Sianes-Gallén, Mònica, Castillόn, Pablo, Bernaus, Martí, Quintas, Saioa, Gόmez, Olga, Salvador, Jordi, Abarca, Javier, Estrada, Cristina, Novellas, Marga, Torra, Mercè, Dealbert, Alfred, Macho, Oscar, Ivanov, Alexia, Valldosera, Esther, Arroyo, Marta, Pey, Borja, Yuste, Antoni, Mateo, Llorenç, Caso, Julio De, Anaya, Rafael, Higa-Sansone, J.L., Millan, Angelica, Baños, Victoria, Herrera-Mateo, Sergio, Aguado, Hector, Martinez-Municio, Gonzalo, León, Ricardo, Santiago-Maniega, Silvia, Zabalza, Ana, Labrador, Gregorio, Guerado, Enrique, Ramirez-Roldan, Alicia, Cruz, Encarnacion, Cano, Juan R, Bogallo, Jose M, Sangasoongsong, Paphon, Kulachote, Noratep, Sirisreetreerux, Norachart, Pengrung, Nachapan, Chalacheewa, Theerawat, Arnuntasupakul, Vanlapa, Yingchoncharoen, Teerapat, Naratreekoon, Bundit, Kadry, Miriam A, Thayaparan, Surendini, Abdlaziz, Ihab, Aframian, Arash, Imbuldeniya, Arjuna, Movahedi, Roya, Omran, Sherif, Vizcaychipi, Marcela P, Correia, Patricia, Patil, Shashank, Haire, Kevin, Mayor, Amy S.E., Dillingham, Sally, Nicholson, Laura, Elnaggar, Mohamed, John, Joby, Nanjayan, Shashi K, Parker, Martyn J, O'Sullivan, Susan, Marmor, Meir T, Matityahu, Amir, McClellan, Robert T, Comstock, Curt, Ding, Anthony, Toogood, Paul, Slobogean, Gerard, Joseph, Katherine, O'Toole, Robert, Sciadini, Marcus, Ryan, Scott P, Clark, Molly E, Cassidy, Charles, Balonov, Konstantin, Bergese, Sergio D, Phieffer, Laura S, Gonzalez-Zacarias, Alicia A, Marcantonio, Andrew J, Borges, Flavia K., Bhandari, Mohit, Nuñez, Jorge H., Castillon, Pablo, De Caso Rodriguez, Julio, Aguado, Hector J., Popova, Ekaterine, Tonelli, Ana Claudia, Balasubramanian, Kumar, Vincent, Jessica, Harvey, Valerie, Kocaqi, Etri, and Devereaux, P.J.

Published
2024
Full Text
View/download PDF

39. Safety profile of BCG revaccination for COVID prevention among elderly individuals in India

Author

Thakor, Mahendra, Pereira, Pratibha, Srinivasan, R., Ketharam, Asha, Sabde, Yogesh, Pavan Kumar, N., Gowda, Vidya, Hadaye, Rujuta, Shrinivasa, B.M., Bettappa, Prashantha, Mohan, Anant, KushiyaSri, Sreelakshmi, Manjunath, P.H., Bhavani, P.K., Sangwan, Ramesh K., Tejaswini, C.J., Balachander, Rakesh, Madhanraj, K., Kumar, Praveen, Nataraj, Gita, Kumari, Amrutha, Guleria, Randeep, Prabakaran, Sreelal T., Huda, Ramesh K., Balaji, Chiman, Vikas, Gundappa, Vivek, Shah, Daksha, Srivastava, Garima, Menon, Vishnu B., Sagar, Amit, Truchna, Tanwi, Sathish, Syama, Manda, Balwant, Kumar, Manoj, Bansali, Suman, Sarma, Devojit K., Singh, Surya, Panwalkar, Nikita, Toteja, G.S., Sarkar, Kamalesh, Tiwari, R.R., Murekhar, Manoj, Gupta, Nivedita, Babu, Subash, Devaleenal Daniel, Bella, Venkatesan, Mythily, and Padmapriyadarsini, Chandrasekaran

Published
2024
Full Text
View/download PDF

44. Soft Actor-Critic with Cross-Entropy Policy Optimization

Author

Shi, Zhenyang and Singh, Surya P. N.

Subjects
Computer Science - Machine Learning
Abstract

Soft Actor-Critic (SAC) is one of the state-of-the-art off-policy reinforcement learning (RL) algorithms that is within the maximum entropy based RL framework. SAC is demonstrated to perform very well in a list of continous control tasks with good stability and robustness. SAC learns a stochastic Gaussian policy that can maximize a trade-off between total expected reward and the policy entropy. To update the policy, SAC minimizes the KL-Divergence between the current policy density and the soft value function density. Reparameterization trick is then used to obtain the approximate gradient of this divergence. In this paper, we propose Soft Actor-Critic with Cross-Entropy Policy Optimization (SAC-CEPO), which uses Cross-Entropy Method (CEM) to optimize the policy network of SAC. The initial idea is to use CEM to iteratively sample the closest distribution towards the soft value function density and uses the resultant distribution as a target to update the policy network. For the purpose of reducing the computational complexity, we also introduce a decoupled policy structure that decouples the Gaussian policy into one policy that learns the mean and one other policy that learns the deviation such that only the mean policy is trained by CEM. We show that this decoupled policy structure does converge to a optimal and we also demonstrate by experiments that SAC-CEPO achieves competitive performance against the original SAC.

Published
2021

Catalog

Books, media, physical & digital resources
See catalog results