Sarath Chandar

182 papers A* 24A 4B 3Journal 119Unranked 29

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	CADmium: Fine-Tuning Code Language Models for Text- Driven Sequential CAD Design. Trans. Mach. Learn. Res. Prashant Govindarajan, Davide Baldelli, Jay Pathak, Quentin Fournier, Sarath Chandar
2026	J	`jnl`	CoPeP: Benchmarking Continual Pretraining for Protein Language Models. CoRR Darshan Patil, Pranshu Malviya, Mathieu Reymond, Quentin Fournier, Sarath Chandar
2026	—	`conf`	Investigating the Multilingual Calibration Effects of Language Model Instruction Tuning. EACL (Volume 2: Short Papers) Jerry Huang, Peng Lu, Qiuhao Zeng, Yusuke Iwasawa, Yutaka Matsuo, Sarath Chandar, Edison Marrese-Taylor, Irene Li
2026	J	`jnl`	Investigating the Multilingual Calibration Effects of Language Model Instruction-Tuning. CoRR Jerry Huang, Peng Lu, Qiuhao Zeng, Yusuke Iwasawa, Yutaka Matsuo, Sarath Chandar, Edison Marrese-Taylor, Irene Li
2026	J	`jnl`	LLMs Can't Play Hangman: On the Necessity of a Private Working Memory for Language Agents. CoRR Davide Baldelli, Ali Parviz, Amal Zouaq, Sarath Chandar
2026	J	`jnl`	Squeezing More from the Stream : Learning Representation Online for Streaming Reinforcement Learning. CoRR Nilaksh, Antoine Clavaud, Mathieu Reymond, François Rivest, Sarath Chandar
2026	J	`jnl`	The Expressive Limits of Diagonal SSMs for State-Tracking. CoRR Mehran Shakerinava, Behnoush Khavari, Siamak Ravanbakhsh, Sarath Chandar
2025	A*	`conf`	A Generalist Hanabi Agent. ICLR Arjun Vaithilingam Sudhakar, Hadi Nekoei, Mathieu Reymond, Miao Liu, Janarthanan Rajendran, Sarath Chandar
2025	J	`jnl`	A Generalist Hanabi Agent. CoRR Arjun Vaithilingam Sudhakar, Hadi Nekoei, Mathieu Reymond, Miao Liu, Janarthanan Rajendran, Sarath Chandar
2025	A*	`conf`	BindGPT: A Scalable Framework for 3D Molecular Design via Language Modeling and Reinforcement Learning. AAAI Artem Zholus, Maksim Kuznetsov, Roman Schutski, Rim Shayakhmetov, Daniil Polykovskiy, Sarath Chandar, Alex Zhavoronkov
2025	J	`jnl`	Boosting LLM Reasoning via Spontaneous Self-Correction. CoRR Xutong Zhao, Tengyu Xu, Xuewei Wang, Zhengxing Chen, Di Jin, Liang Tan, Yen-Ting, Zishun Yu, Zhuokai Zhao, Yun He, Sinong Wang, Han Fang, Sarath Chandar, Chenguang Zhu
2025	J	`jnl`	CADmium: Fine-Tuning Code Language Models for Text-Driven Sequential CAD Design. CoRR Prashant Govindarajan, Davide Baldelli, Jay Pathak, Quentin Fournier, Sarath Chandar
2025	—	`conf`	Combining Domain and Alignment Vectors Provides Better Knowledge-Safety Trade-offs in LLMs. ACL (2) Megh Thakkar, Quentin Fournier, Matthew Riemer, Pin-Yu Chen, Amal Zouaq, Payel Das, Sarath Chandar
2025	J	`jnl`	CrystalGym: A New Benchmark for Materials Discovery Using Reinforcement Learning. CoRR Prashant Govindarajan, Mathieu Reymond, Antoine Clavaud, Mariano Phielipp, Santiago Miret, Sarath Chandar
2025	J	`jnl`	Did I Faithfully Say What I Thought? Bridging the Gap Between Neural Activity and Self-Explanations in Large Language Models. CoRR Milan Bhan, Jean-Noël Vittaut, Nicolas Chesneau, Sarath Chandar, Marie-Jeanne Lesot
2025	J	`jnl`	Do Large Language Models Know How Much They Know? CoRR Gabriele Prato, Jerry Huang, Prasannna Parthasarathi, Shagun Sodhani, Sarath Chandar
2025	—	`conf`	Do Robot Snakes Dream like Electric Sheep? Investigating the Effects of Architectural Inductive Biases on Hallucination. ACL (Findings) Jerry Huang, Prasanna Parthasarathi, Mehdi Rezagholizadeh, Boxing Chen, Sarath Chandar
2025	J	`jnl`	Effect of Document Packing on the Latent Multi-Hop Reasoning Capabilities of Large Language Models. CoRR Gabriele Prato, Shagun Sodhani, Alessandro Sordoni, Sarath Chandar
2025	J	`jnl`	GRPO-λ: Credit Assignment improves LLM Reasoning. CoRR Prasanna Parthasarathi, Mathieu Reymond, Boxing Chen, Yufei Cui, Sarath Chandar
2025	J	`jnl`	Just-in-time Episodic Feedback Hinter: Leveraging Offline Knowledge to Improve LLM Agents Adaptation. CoRR Hadi Nekoei, Aman Jaiswal, Patrice Béchard, Oleh Shliazhko, Orlando Marquez Ayala, Mathieu Reymond, Massimo Caccia, Alexandre Drouin, Sarath Chandar, Alexandre Lacoste
2025	J	`jnl`	Monitoring morphometric drift in lifelong learning segmentation of the spinal cord. CoRR Enamundram Naga Karthik, Sandrine Bédard, Jan Valosek, Christoph S. Aigner, Elise Bannier, Josef Bednarík, Virginie Callot, Anna J. E. Combes, Armin Curt, Gergely Dávid, Falk Eippert, Lynn Farner, Michael G. Fehlings, Patrick Freund, Tobias Granberg, Cristina Granziera, RHSCIR Network Imaging Group, Ulrike Horn, Tomás Horák, Suzanne Humphreys, Markus Hupp, Anne Kerbrat, Nawal Kinany, Shannon H. Kolind, Petr Kudlicka, Anna Lebret, Lisa Eunyoung Lee, Caterina Mainero, Allan R. Martin, Megan McGrath, Govind Nair, Kristin P. O'Grady, Jiwon Oh, Russell Ouellette, Nikolai Pfender, Dario Pfyffer, Pierre-François Pradat, Alexandre Prat, Emanuele Pravatà, Daniel S. Reich, Ilaria Ricchi, Naama Rotem-Kohavi, Simon Schading-Sassenhausen, Maryam Seif, Andrew C. Smith, Seth A. Smith, Grace Sweeney, Roger C. Tam, Anthony Traboulsee, Constantina Andrada Treaba, Charidimos Tsagkas, Zachary Vavasour, Dimitri Van De Ville, Kenneth Arnold Weber II, Sarath Chandar, Julien Cohen-Adad
2025	J	`jnl`	NeoBERT: A Next Generation BERT. Trans. Mach. Learn. Res. Lola Le Breton, Quentin Fournier, John Xavier Morris, Mariam El Mezouar, Sarath Chandar
2025	J	`jnl`	NeoBERT: A Next-Generation BERT. CoRR Lola Le Breton, Quentin Fournier, Mariam El Mezouar, Sarath Chandar
2025	J	`jnl`	Neural Coherence : Find higher performance to out-of-distribution tasks from few samples. CoRR Simon Guiroy, Mats Leon Richter, Sarath Chandar, Christopher Pal
2025	J	`jnl`	NovoMolGen: Rethinking Molecular Language Model Pretraining. CoRR Kamran Chitsaz, Roshan Balaji, Quentin Fournier, Nirav Pravinbhai Bhatt, Sarath Chandar
2025	J	`jnl`	Optimizers Qualitatively Alter Solutions And We Should Leverage This. CoRR Razvan Pascanu, Clare Lyle, Ionut-Vlad Modoranu, Naima Elosegui Borras, Dan Alistarh, Petar Velickovic, Sarath Chandar, Soham De, James Martens
2025	J	`jnl`	Parity Requires Unified Input Dependence and Negative Eigenvalues in SSMs. CoRR Behnoush Khavari, Mehran Shakerinava, Jayesh Khullar, Jerry Huang, François Rivest, Siamak Ravanbakhsh, Sarath Chandar
2025	J	`jnl`	Probing the effectiveness of World Models for Spatial Reasoning through Test-time Scaling. CoRR Saurav Jha, Muhammad Jehanzeb Mirza, Wei Lin, Shiqi Yang, Sarath Chandar
2025	J	`jnl`	Revisiting Replay and Gradient Alignment for Continual Pre-Training of Large Language Models. CoRR Istabrak Abbes, Gopeshh Subbaraj, Matthew Riemer, Nizar Islah, Benjamin Thérien, Tsuguchika Tabaru, Hiroaki Kingetsu, Sarath Chandar, Irina Rish
2025	J	`jnl`	Shielded Controller Units for RL with Operational Constraints Applied to Remote Microgrids. CoRR Hadi Nekoei, Alexandre Blondin Massé, Rachid Hassani, Sarath Chandar, Vincent Mai
2025	—	`conf`	Small Encoders Can Rival Large Decoders in Detecting Groundedness. ACL (Findings) Istabrak Abbes, Gabriele Prato, Quentin Fournier, Fernando Rodriguez, Alaa Boukhary, Adam Elwood, Sarath Chandar
2025	J	`jnl`	Small Encoders Can Rival Large Decoders in Detecting Groundedness. CoRR Istabrak Abbes, Gabriele Prato, Quentin Fournier, Fernando Rodriguez, Alaa Boukhary, Adam Elwood, Sarath Chandar
2025	J	`jnl`	Steering Large Language Model Activations in Sparse Spaces. CoRR Reza Bayat, Ali Rahimi-Kalahroudi, Mohammad Pezeshki, Sarath Chandar, Pascal Vincent
2025	J	`jnl`	TAPNext: Tracking Any Point (TAP) as Next Token Prediction. CoRR Artem Zholus, Carl Doersch, Yi Yang, Skanda Koppula, Viorica Patraucean, Xu Owen He, Ignacio Rocco, Mehdi S. M. Sajjadi, Sarath Chandar, Ross Goroshin
2025	J	`jnl`	The Markovian Thinker. CoRR Milad Aghajohari, Kamran Chitsaz, Amirhossein Kazemnejad, Sarath Chandar, Alessandro Sordoni, Aaron C. Courville, Siva Reddy
2025	J	`jnl`	V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning. CoRR Mido Assran, Adrien Bardes, David Fan, Quentin Garrido, Russell Howes, Mojtaba Komeili, Matthew J. Muckley, Ammar Rizvi, Claire Roberts, Koustuv Sinha, Artem Zholus, Sergio Arnaud, Abha Gejji, Ada Martin, Francois Robert Hogan, Daniel Dugas, Piotr Bojanowski, Vasil Khalidov, Patrick Labatut, Francisco Massa, Marc Szafraniec, Kapil Krishnakumar, Yong Li, Xiaodong Ma, Sarath Chandar, Franziska Meier, Yann LeCun, Michael Rabbat, Nicolas Ballas
2024	—	`conf`	A Deep Dive into the Trade-Offs of Parameter-Efficient Preference Alignment Techniques. ACL (1) Megh Thakkar, Quentin Fournier, Matthew Riemer, Pin-Yu Chen, Amal Zouaq, Payel Das, Sarath Chandar
2024	J	`jnl`	A Deep Dive into the Trade-Offs of Parameter-Efficient Preference Alignment Techniques. CoRR Megh Thakkar, Quentin Fournier, Matthew D. Riemer, Pin-Yu Chen, Amal Zouaq, Payel Das, Sarath Chandar
2024	—	`conf`	Are self-explanations from Large Language Models faithful? ACL (Findings) Andreas Madsen, Sarath Chandar, Siva Reddy
2024	J	`jnl`	Are self-explanations from Large Language Models faithful? CoRR Andreas Madsen, Sarath Chandar, Siva Reddy
2024	A*	`conf`	Balancing Context Length and Mixing Times for Reinforcement Learning at Scale. NeurIPS Matthew Riemer, Khimya Khetarpal, Janarthanan Rajendran, Sarath Chandar
2024	J	`jnl`	BindGPT: A Scalable Framework for 3D Molecular Design via Language Modeling and Reinforcement Learning. CoRR Artem Zholus, Maksim Kuznetsov, Roman Schutski, Rim Shayakhmetov, Daniil Polykovskiy, Sarath Chandar, Alex Zhavoronkov
2024	J	`jnl`	Combining Domain and Alignment Vectors to Achieve Better Knowledge-Safety Trade-offs in LLMs. CoRR Megh Thakkar, Yash More, Quentin Fournier, Matthew Riemer, Pin-Yu Chen, Amal Zouaq, Payel Das, Sarath Chandar
2024	—	`ed.`	Conference on Lifelong Learning Agents, 29-1 August 2024, University of Pisa, Pisa, Italy. CoLLAs Vincenzo Lomonaco, Stefano Melacci, Tinne Tuytelaars, Sarath Chandar, Razvan Pascanu
2024	A*	`conf`	Context-Aware Assistant Selection for Improved Inference Acceleration with Large Language Models. EMNLP Jerry Huang, Prasanna Parthasarathi, Mehdi Rezagholizadeh, Sarath Chandar
2024	J	`jnl`	Context-Aware Assistant Selection for Improved Inference Acceleration with Large Language Models. CoRR Jerry Huang, Prasanna Parthasarathi, Mehdi Rezagholizadeh, Sarath Chandar
2024	A*	`conf`	Do Large Language Models Know How Much They Know? EMNLP Gabriele Prato, Jerry Huang, Prasanna Parthasarathi, Shagun Sodhani, Sarath Chandar
2024	J	`jnl`	Do Robot Snakes Dream like Electric Sheep? Investigating the Effects of Architectural Inductive Biases on Hallucination. CoRR Jerry Huang, Prasanna Parthasarathi, Mehdi Rezagholizadeh, Boxing Chen, Sarath Chandar
2024	—	`conf`	Exploring Quantization for Efficient Pre-Training of Transformer Language Models. EMNLP (Findings) Kamran Chitsaz, Quentin Fournier, Gonçalo Mordido, Sarath Chandar
2024	J	`jnl`	Exploring Quantization for Efficient Pre-Training of Transformer Language Models. CoRR Kamran Chitsaz, Quentin Fournier, Gonçalo Mordido, Sarath Chandar
2024	A*	`conf`	Fairness-Aware Structured Pruning in Transformers. AAAI Abdelrahman Zayed, Gonçalo Mordido, Samira Shabanian, Ioana Baldini, Sarath Chandar
2024	A*	`conf`	Faithfulness Measurable Masked Language Models. ICML Andreas Madsen, Siva Reddy, Sarath Chandar
2024	A*	`conf`	Intelligent Switching for Reset-Free RL. ICLR Darshan Patil, Janarthanan Rajendran, Glen Berseth, Sarath Chandar
2024	J	`jnl`	Intelligent Switching for Reset-Free RL. CoRR Darshan Patil, Janarthanan Rajendran, Glen Berseth, Sarath Chandar
2024	J	`jnl`	Interpretability Needs a New Paradigm. CoRR Andreas Madsen, Himabindu Lakkaraju, Siva Reddy, Sarath Chandar
2024	A*	`conf`	Lookbehind-SAM: k steps back, 1 step forward. ICML Gonçalo Mordido, Pranshu Malviya, Aristide Baratin, Sarath Chandar
2024	—	`conf`	MVP: Minimal Viable Phrase for Long Text Understanding. LREC/COLING Louis Clouâtre, Amal Zouaq, Sarath Chandar
2024	A*	`conf`	Mastering Memory Tasks with World Models. ICLR Mohammad Reza Samsami, Artem Zholus, Janarthanan Rajendran, Sarath Chandar
2024	J	`jnl`	Mastering Memory Tasks with World Models. CoRR Mohammad Reza Samsami, Artem Zholus, Janarthanan Rajendran, Sarath Chandar
2024	—	`conf`	On the Costs and Benefits of Adopting Lifelong Learning for Software Analytics - Empirical Study on Brown Build and Risk Prediction. ICSE-SEIP Doriane Olewicki, Sarra Habchi, Mathieu Nayrolles, Mojtaba Faramarzi, Sarath Chandar, Bram Adams
2024	J	`jnl`	Predicting the Impact of Model Expansion through the Minima Manifold: A Loss Landscape Perspective. CoRR Pranshu Malviya, Jerry Huang, Quentin Fournier, Sarath Chandar
2024	J	`jnl`	Promoting Exploration in Memory-Augmented Adam using Critical Momenta. Trans. Mach. Learn. Res. Pranshu Malviya, Gonçalo Mordido, Aristide Baratin, Reza Babanezhad Harikandeh, Jerry Huang, Simon Lacoste-Julien, Razvan Pascanu, Sarath Chandar
2024	—	`conf`	Sharpness-Aware Minimization Scaled by Outlier Normalization for Robust DNNs on In-Memory Computing Accelerators. IEEECONF Sébastien Henwood, Gonçalo Mordido, Yvon Savaria, Sarath Chandar, François Leduc-Primeau
2024	—	`conf`	Sub-goal Distillation: A Method to Improve Small Language Agents. CoLLAs Maryam Hashemzadeh, Elias Stengel-Eskin, Sarath Chandar, Marc-Alexandre Côté
2024	J	`jnl`	Sub-goal Distillation: A Method to Improve Small Language Agents. CoRR Maryam Hashemzadeh, Elias Stengel-Eskin, Sarath Chandar, Marc-Alexandre Côté
2024	J	`jnl`	Too Big to Fool: Resisting Deception in Language Models. CoRR Mohammad Reza Samsami, Mats Leon Richter, Juan A. Rodríguez, Megh Thakkar, Sarath Chandar, Maxime Gasse
2024	J	`jnl`	Torque-Aware Momentum. CoRR Pranshu Malviya, Gonçalo Mordido, Aristide Baratin, Reza Babanezhad Harikandeh, Gintare Karolina Dziugaite, Razvan Pascanu, Sarath Chandar
2024	A	`conf`	Toward Debugging Deep Reinforcement Learning Programs with RLExplorer. ICSME Rached Bouchoucha, Ahmed Haj Yahmed, Darshan Patil, Janarthanan Rajendran, Amin Nikanjam, Sarath Chandar, Foutse Khomh
2024	J	`jnl`	Toward Debugging Deep Reinforcement Learning Programs with RLExplorer. CoRR Rached Bouchoucha, Ahmed Haj Yahmed, Darshan Patil, Janarthanan Rajendran, Amin Nikanjam, Sarath Chandar, Foutse Khomh
2024	J	`jnl`	Towards Practical Tool Usage for Continually Learning LLMs. CoRR Jerry Huang, Prasanna Parthasarathi, Mehdi Rezagholizadeh, Sarath Chandar
2024	—	`conf`	Why Don't Prompt-Based Fairness Metrics Correlate? ACL (1) Abdelrahman Zayed, Gonçalo Mordido, Ioana Baldini, Sarath Chandar
2024	J	`jnl`	Why Don't Prompt-Based Fairness Metrics Correlate? CoRR Abdelrahman Zayed, Gonçalo Mordido, Ioana Baldini, Sarath Chandar
2023	J	`jnl`	An Empirical Investigation of the Role of Pre-training in Lifelong Learning. J. Mach. Learn. Res. Sanket Vaibhav Mehta, Darshan Patil, Sarath Chandar, Emma Strubell
2023	J	`jnl`	Conditionally Optimistic Exploration for Cooperative Deep Multi-Agent Reinforcement Learning. CoRR Xutong Zhao, Yangchen Pan, Chenjun Xiao, Sarath Chandar, Janarthanan Rajendran
2023	A	`conf`	Conditionally optimistic exploration for cooperative deep multi-agent reinforcement learning. UAI Xutong Zhao, Yangchen Pan, Chenjun Xiao, Sarath Chandar, Janarthanan Rajendran
2023	—	`ed.`	Conference on Lifelong Learning Agents, 22-25 August 2023, McGill University, Montréal, Québec, Canada. CoLLAs Sarath Chandar, Razvan Pascanu, Hanie Sedghi, Doina Precup
2023	—	`conf`	Dealing With Non-stationarity in Decentralized Cooperative Multi-Agent Deep Reinforcement Learning via Multi-Timescale Learning. CoLLAs Hadi Nekoei, Akilesh Badrinaaraayanan, Amit Sinha, Mohammad Amini, Janarthanan Rajendran, Aditya Mahajan, Sarath Chandar
2023	J	`jnl`	Dealing With Non-stationarity in Decentralized Cooperative Multi-Agent Deep Reinforcement Learning via Multi-Timescale Learning. CoRR Hadi Nekoei, Akilesh Badrinaaraayanan, Amit Sinha, Mohammad Amini, Janarthanan Rajendran, Aditya Mahajan, Sarath Chandar
2023	A*	`conf`	Deep Learning on a Healthy Data Diet: Finding Important Examples for Fairness. AAAI Abdelrahman Zayed, Prasanna Parthasarathi, Gonçalo Mordido, Hamid Palangi, Samira Shabanian, Sarath Chandar
2023	A*	`conf`	EpiK-Eval: Evaluation for Language Models as Epistemic Models. EMNLP Gabriele Prato, Jerry Huang, Prasanna Parthasarathi, Shagun Sodhani, Sarath Chandar
2023	J	`jnl`	EpiK-Eval: Evaluation for Language Models as Epistemic Models. CoRR Gabriele Prato, Jerry Huang, Prasanna Parthasarathi, Shagun Sodhani, Sarath Chandar
2023	J	`jnl`	Fairness-Aware Structured Pruning in Transformers. CoRR Abdelrahman Zayed, Gonçalo Mordido, Samira Shabanian, Ioana Baldini, Sarath Chandar
2023	J	`jnl`	Faithfulness Measurable Masked Language Models. CoRR Andreas Madsen, Siva Reddy, Sarath Chandar
2023	J	`jnl`	Language Model-In-The-Loop: Data Optimal Approach to Learn-To-Recommend Actions in Text Games. CoRR Arjun Vaithilingam Sudhakar, Prasanna Parthasarathi, Janarthanan Rajendran, Sarath Chandar
2023	J	`jnl`	Lookbehind Optimizer: k steps back, 1 step forward. CoRR Gonçalo Mordido, Pranshu Malviya, Aristide Baratin, Sarath Chandar
2023	—	`conf`	Measuring the Knowledge Acquisition-Utilization Gap in Pretrained Language Models. EMNLP (Findings) Amirhossein Kazemnejad, Mehdi Rezagholizadeh, Prasanna Parthasarathi, Sarath Chandar
2023	J	`jnl`	Measuring the Knowledge Acquisition-Utilization Gap in Pretrained Language Models. CoRR Amirhossein Kazemnejad, Mehdi Rezagholizadeh, Prasanna Parthasarathi, Sarath Chandar
2023	J	`jnl`	Post-hoc Interpretability for Neural NLP: A Survey. ACM Comput. Surv. Andreas Madsen, Siva Reddy, Sarath Chandar
2023	J	`jnl`	Promoting Exploration in Memory-Augmented Adam using Critical Momenta. CoRR Pranshu Malviya, Gonçalo Mordido, Aristide Baratin, Reza Babanezhad Harikandeh, Jerry Huang, Simon Lacoste-Julien, Razvan Pascanu, Sarath Chandar
2023	J	`jnl`	Replay Buffer With Local Forgetting for Adaptive Deep Model-Based Reinforcement Learning. CoRR Ali Rahimi-Kalahroudi, Janarthanan Rajendran, Ida Momennejad, Harm van Seijen, Sarath Chandar
2023	—	`conf`	Replay Buffer with Local Forgetting for Adapting to Local Environment Changes in Deep Model-Based Reinforcement Learning. CoLLAs Ali Rahimi-Kalahroudi, Janarthanan Rajendran, Ida Momennejad, Harm van Seijen, Sarath Chandar
2023	A*	`conf`	Self-Influence Guided Data Reweighting for Language Model Pre-training. EMNLP Megh Thakkar, Tolga Bolukbasi, Sriram Ganapathy, Shikhar Vashishth, Sarath Chandar, Partha Talukdar
2023	J	`jnl`	Self-Influence Guided Data Reweighting for Language Model Pre-training. CoRR Megh Thakkar, Tolga Bolukbasi, Sriram Ganapathy, Shikhar Vashishth, Sarath Chandar, Partha Talukdar
2023	J	`jnl`	Should We Attend More or Less? Modulating Attention for Fairness. CoRR Abdelrahman Zayed, Gonçalo Mordido, Samira Shabanian, Sarath Chandar
2023	J	`jnl`	Thompson sampling for improved exploration in GFlowNets. CoRR Jarrid Rector-Brooks, Kanika Madan, Moksh Jain, Maksym Korablyov, Cheng-Hao Liu, Sarath Chandar, Nikolay Malkin, Yoshua Bengio
2023	—	`conf`	Towards Few-shot Coordination: Revisiting Ad-hoc Teamplay Challenge In the Game of Hanabi. CoLLAs Hadi Nekoei, Xutong Zhao, Janarthanan Rajendran, Miao Liu, Sarath Chandar
2023	J	`jnl`	Towards Few-shot Coordination: Revisiting Ad-hoc Teamplay Challenge In the Game of Hanabi. CoRR Hadi Nekoei, Xutong Zhao, Janarthanan Rajendran, Miao Liu, Sarath Chandar
2023	J	`jnl`	Towards Lifelong Learning for Software Analytics Models: Empirical Study on Brown Build and Risk Prediction. CoRR Doriane Olewicki, Sarra Habchi, Mathieu Nayrolles, Mojtaba Faramarzi, Sarath Chandar, Bram Adams
2022	J	`jnl`	An Introduction to Lifelong Supervised Learning. CoRR Shagun Sodhani, Mojtaba Faramarzi, Sanket Vaibhav Mehta, Pranshu Malviya, Mohamed A. Abdelsalam, Janarthanan Rajendran, Sarath Chandar
2022	A	`conf`	Combining Reinforcement Learning and Constraint Programming for Sequence-Generation Tasks with Hard Constraints. CP Daphné Lafleur, Sarath Chandar, Gilles Pesant
2022	—	`ed.`	Conference on Lifelong Learning Agents, CoLLAs 2022, 22-24 August 2022, McGill University, Montréal, Québec, Canada. CoLLAs Sarath Chandar, Razvan Pascanu, Doina Precup
2022	J	`jnl`	Deep Learning on a Healthy Data Diet: Finding Important Examples for Fairness. CoRR Abdelrahman Zayed, Prasanna Parthasarathi, Gonçalo Mordido, Hamid Palangi, Samira Shabanian, Sarath Chandar
2022	—	`conf`	Detecting Languages Unintelligible to Multilingual Models through Local Structure Probes. EMNLP (Findings) Louis Clouâtre, Prasanna Parthasarathi, Amal Zouaq, Sarath Chandar
2022	J	`jnl`	Detecting Languages Unintelligible to Multilingual Models through Local Structure Probes. CoRR Louis Clouâtre, Prasanna Parthasarathi, Amal Zouaq, Sarath Chandar
2022	—	`conf`	Improving Meta-Learning Generalization with Activation-Based Early-Stopping. CoLLAs Simon Guiroy, Christopher Pal, Gonçalo Mordido, Sarath Chandar
2022	J	`jnl`	Improving Meta-Learning Generalization with Activation-Based Early-Stopping. CoRR Simon Guiroy, Christopher Pal, Gonçalo Mordido, Sarath Chandar
2022	J	`jnl`	Improving Sample Efficiency of Value Based Models Using Attention and Vision Transformers. CoRR Amir Ardalan Kalantari, Mohammad Amini, Sarath Chandar, Doina Precup
2022	—	`conf`	Local Structure Matters Most in Most Languages. AACL/IJCNLP (2) Louis Clouâtre, Prasanna Parthasarathi, Amal Zouaq, Sarath Chandar
2022	J	`jnl`	Local Structure Matters Most in Most Languages. CoRR Louis Clouâtre, Prasanna Parthasarathi, Amal Zouaq, Sarath Chandar
2022	—	`conf`	Local Structure Matters Most: Perturbation Study in NLU. ACL (Findings) Louis Clouâtre, Prasanna Parthasarathi, Amal Zouaq, Sarath Chandar
2022	A*	`conf`	Memory Augmented Optimizers for Deep Learning. ICLR Paul-Aymeric Martin McRae, Prasanna Parthasarathi, Mido Assran, Sarath Chandar
2022	J	`jnl`	PatchBlender: A Motion Prior for Video Transformers. CoRR Gabriele Prato, Yale Song, Janarthanan Rajendran, R. Devon Hjelm, Neel Joshi, Sarath Chandar
2022	A*	`conf`	PatchUp: A Feature-Space Block-Level Regularization Technique for Convolutional Neural Networks. AAAI Mojtaba Faramarzi, Mohammad Amini, Akilesh Badrinaaraayanan, Vikas Verma, Sarath Chandar
2022	J	`jnl`	Segmentation of Multiple Sclerosis Lesions across Hospitals: Learn Continually or Train from Scratch? CoRR Enamundram Naga Karthik, Anne Kerbrat, Pierre Labauge, Tobias Granberg, Jason Talbott, Daniel S. Reich, Massimo Filippi, Rohit Bakshi, Virginie Callot, Sarath Chandar, Julien Cohen-Adad
2022	J	`jnl`	Sharpness-Aware Training for Accurate Inference on Noisy DNN Accelerators. CoRR Gonçalo Mordido, Sarath Chandar, François Leduc-Primeau
2022	—	`conf`	TAG: Task-based Accumulated Gradients for Lifelong learning. CoLLAs Pranshu Malviya, Balaraman Ravindran, Sarath Chandar
2022	A*	`conf`	Towards Evaluating Adaptivity of Model-Based Reinforcement Learning Methods. ICML Yi Wan, Ali Rahimi-Kalahroudi, Janarthanan Rajendran, Ida Momennejad, Sarath Chandar, Harm van Seijen
2022	J	`jnl`	Towards Evaluating Adaptivity of Model-Based Reinforcement Learning Methods. CoRR Yi Wan, Ali Rahimi-Kalahroudi, Janarthanan Rajendran, Ida Momennejad, Sarath Chandar, Harm van Seijen
2021	B	`conf`	A Brief Study on the Effects of Training Generative Dialogue Models with a Semantic loss. SIGDIAL Prasanna Parthasarathi, Mohamed A. Abdelsalam, Sarath Chandar, Joelle Pineau
2021	J	`jnl`	A Brief Study on the Effects of Training Generative Dialogue Models with a Semantic loss. CoRR Prasanna Parthasarathi, Mohamed A. Abdelsalam, Joelle Pineau, Sarath Chandar
2021	—	`conf`	A Survey of Data Augmentation Approaches for NLP. ACL/IJCNLP (Findings) Steven Y. Feng, Varun Gangal, Jason Wei, Sarath Chandar, Soroush Vosoughi, Teruko Mitamura, Eduard H. Hovy
2021	J	`jnl`	A Survey of Data Augmentation Approaches for NLP. CoRR Steven Y. Feng, Varun Gangal, Jason Wei, Sarath Chandar, Soroush Vosoughi, Teruko Mitamura, Eduard H. Hovy
2021	J	`jnl`	An Empirical Investigation of the Role of Pre-training in Lifelong Learning. CoRR Sanket Vaibhav Mehta, Darshan Patil, Sarath Chandar, Emma Strubell
2021	A*	`conf`	Continuous Coordination As a Realistic Scenario for Lifelong Learning. ICML Hadi Nekoei, Akilesh Badrinaaraayanan, Aaron C. Courville, Sarath Chandar
2021	J	`jnl`	Continuous Coordination As a Realistic Scenario for Lifelong Learning. CoRR Hadi Nekoei, Akilesh Badrinaaraayanan, Aaron C. Courville, Sarath Chandar
2021	J	`jnl`	Demystifying Neural Language Models' Insensitivity to Word-Order. CoRR Louis Clouâtre, Prasanna Parthasarathi, Amal Zouaq, Sarath Chandar
2021	J	`jnl`	Do Encoder Representations of Generative Dialogue Models Encode Sufficient Information about the Task ? CoRR Prasanna Parthasarathi, Joelle Pineau, Sarath Chandar
2021	B	`conf`	Do Encoder Representations of Generative Dialogue Models have sufficient summary of the Information about the task ? SIGDIAL Prasanna Parthasarathi, Joelle Pineau, Sarath Chandar
2021	A*	`conf`	IIRC: Incremental Implicitly-Refined Classification. CVPR Mohamed A. Abdelsalam, Mojtaba Faramarzi, Shagun Sodhani, Sarath Chandar
2021	—	`conf`	MLMLM: Link Prediction with Mean Likelihood Masked Language Model. ACL/IJCNLP (Findings) Louis Clouâtre, Philippe Trempe, Amal Zouaq, Sarath Chandar
2021	J	`jnl`	Memory Augmented Optimizers for Deep Learning. CoRR Paul-Aymeric McRae, Prasanna Parthasarathi, Mahmoud Assran, Sarath Chandar
2021	J	`jnl`	Post-hoc Interpretability for Neural NLP: A Survey. CoRR Andreas Madsen, Siva Reddy, Sarath Chandar
2021	J	`jnl`	Scaling Laws for the Few-Shot Adaptation of Pre-trained Image Classifiers. CoRR Gabriele Prato, Simon Guiroy, Ethan Caballero, Irina Rish, Sarath Chandar
2021	J	`jnl`	TAG: Task-based Accumulated Gradients for Lifelong learning. CoRR Pranshu Malviya, Balaraman Ravindran, Sarath Chandar
2021	A*	`conf`	Towered Actor Critic For Handling Multiple Action Types In Reinforcement Learning For Drug Discovery. AAAI Sai Krishna Gottipati, Yashaswi Pathak, Boris Sattarov, Sahir, Rohan Nuttall, Mohammad Amini, Matthew E. Taylor, Sarath Chandar
2020	J	`jnl`	How To Evaluate Your Dialogue System: Probe Tasks as an Alternative for Token-level Evaluation Metrics. CoRR Prasanna Parthasarathi, Joelle Pineau, Sarath Chandar
2020	J	`jnl`	IIRC: Incremental Implicitly-Refined Classification. CoRR Mohamed A. Abdelsalam, Mojtaba Faramarzi, Shagun Sodhani, Sarath Chandar
2020	J	`jnl`	Learning To Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning. CoRR Sai Krishna Gottipati, Boris Sattarov, Sufeng Niu, Yashaswi Pathak, Haoran Wei, Shengchao Liu, Karam M. J. Thomas, Simon Blackburn, Connor W. Coley, Jian Tang, Sarath Chandar, Yoshua Bengio
2020	A*	`conf`	Learning to Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning. ICML Sai Krishna Gottipati, Boris Sattarov, Sufeng Niu, Yashaswi Pathak, Haoran Wei, Shengchao Liu, Simon Blackburn, Karam M. J. Thomas, Connor W. Coley, Jian Tang, Sarath Chandar, Yoshua Bengio
2020	J	`jnl`	MLMLM: Link Prediction with Mean Likelihood Masked Language Model. CoRR Louis Clouâtre, Philippe Trempe, Amal Zouaq, Sarath Chandar
2020	J	`jnl`	Maximum Reward Formulation In Reinforcement Learning. CoRR Sai Krishna Gottipati, Yashaswi Pathak, Rohan Nuttall, Sahir, Raviteja Chunduru, Ahmed Touati, Sriram Ganapathi Subramanian, Matthew E. Taylor, Sarath Chandar
2020	J	`jnl`	PatchUp: A Regularization Technique for Convolutional Neural Networks. CoRR Mojtaba Faramarzi, Mohammad Amini, Akilesh Badrinaaraayanan, Vikas Verma, Sarath Chandar
2020	J	`jnl`	Slot Contrastive Networks: A Contrastive Approach for Representing Objects. CoRR Evan Racah, Sarath Chandar
2020	J	`jnl`	The Hanabi challenge: A new frontier for AI research. Artif. Intell. Nolan Bard, Jakob N. Foerster, Sarath Chandar, Neil Burch, Marc Lanctot, H. Francis Song, Emilio Parisotto, Vincent Dumoulin, Subhodeep Moitra, Edward Hughes, Iain Dunning, Shibl Mourad, Hugo Larochelle, Marc G. Bellemare, Michael Bowling
2020	A*	`conf`	The LoCA Regret: A Consistent Metric to Evaluate Model-Based Behavior in Reinforcement Learning. NeurIPS Harm van Seijen, Hadi Nekoei, Evan Racah, Sarath Chandar
2020	J	`jnl`	The LoCA Regret: A Consistent Metric to Evaluate Model-Based Behavior in Reinforcement Learning. CoRR Harm van Seijen, Hadi Nekoei, Evan Racah, Sarath Chandar
2020	J	`jnl`	Toward Training Recurrent Neural Networks for Lifelong Learning. Neural Comput. Shagun Sodhani, Sarath Chandar, Yoshua Bengio
2019	—	`conf`	Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study. ACL (1) Chinnadhurai Sankar, Sandeep Subramanian, Chris Pal, Sarath Chandar, Yoshua Bengio
2019	J	`jnl`	Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study. CoRR Chinnadhurai Sankar, Sandeep Subramanian, Christopher J. Pal, Sarath Chandar, Yoshua Bengio
2019	A	`conf`	Edge Replacement Grammars : A Formal Language Approach for Generating Graphs. SDM Revanth Reddy, Sarath Chandar, Balaraman Ravindran
2019	J	`jnl`	Edge Replacement Grammars: A Formal Language Approach for Generating Graphs. CoRR Revanth Reddy, Sarath Chandar, Balaraman Ravindran
2019	—	`conf`	Structure Learning for Neural Module Networks. LANTERN@EMNLP-IJCNLP Vardaan Pahuja, Jie Fu, Sarath Chandar, Christopher Joseph Pal
2019	J	`jnl`	Structure Learning for Neural Module Networks. CoRR Vardaan Pahuja, Jie Fu, Sarath Chandar, Christopher J. Pal
2019	J	`jnl`	The Hanabi Challenge: A New Frontier for AI Research. CoRR Nolan Bard, Jakob N. Foerster, Sarath Chandar, Neil Burch, Marc Lanctot, H. Francis Song, Emilio Parisotto, Vincent Dumoulin, Subhodeep Moitra, Edward Hughes, Iain Dunning, Shibl Mourad, Hugo Larochelle, Marc G. Bellemare, Michael Bowling
2019	—	`conf`	Towards Lossless Encoding of Sentences. ACL (1) Gabriele Prato, Mathieu Duchesneau, Sarath Chandar, Alain Tapp
2019	J	`jnl`	Towards Lossless Encoding of Sentences. CoRR Gabriele Prato, Mathieu Duchesneau, Sarath Chandar, Alain Tapp
2019	A*	`conf`	Towards Non-Saturating Recurrent Units for Modelling Long-Term Dependencies. AAAI Sarath Chandar, Chinnadhurai Sankar, Eugene Vorontsov, Samira Ebrahimi Kahou, Yoshua Bengio
2019	J	`jnl`	Towards Non-saturating Recurrent Units for Modelling Long-term Dependencies. CoRR Sarath Chandar, Chinnadhurai Sankar, Eugene Vorontsov, Samira Ebrahimi Kahou, Yoshua Bengio
2018	J	`jnl`	A Deep Reinforcement Learning Chatbot (Short Version). CoRR Iulian Vlad Serban, Chinnadhurai Sankar, Mathieu Germain, Saizheng Zhang, Zhouhan Lin, Sandeep Subramanian, Taesup Kim, Michael Pieper, Sarath Chandar, Nan Rosemary Ke, Sai Rajeswar, Alexandre de Brébisson, Jose M. R. Sotelo, Dendi Suhubdy, Vincent Michalski, Alexandre Nguyen, Joelle Pineau, Yoshua Bengio
2018	A*	`conf`	Complex Sequential Question Answering: Towards Learning to Converse Over Linked Question Answer Pairs with a Knowledge Graph. AAAI Amrita Saha, Vardaan Pahuja, Mitesh M. Khapra, Karthik Sankaranarayanan, Sarath Chandar
2018	J	`jnl`	Complex Sequential Question Answering: Towards Learning to Converse Over Linked Question Answer Pairs with a Knowledge Graph. CoRR Amrita Saha, Vardaan Pahuja, Mitesh M. Khapra, Karthik Sankaranarayanan, Sarath Chandar
2018	J	`jnl`	Dynamic Neural Turing Machine with Continuous and Discrete Addressing Schemes. Neural Comput. Çaglar Gülçehre, Sarath Chandar, Kyunghyun Cho, Yoshua Bengio
2018	J	`jnl`	Environments for Lifelong Reinforcement Learning. CoRR Khimya Khetarpal, Shagun Sodhani, Sarath Chandar, Doina Precup
2018	J	`jnl`	Language Expansion In Text-Based Games. CoRR Ghulam Ahmed Ansari, Sagar J. P, Sarath Chandar, Balaraman Ravindran
2018	J	`jnl`	On Training Recurrent Neural Networks for Lifelong Learning. CoRR Shagun Sodhani, Sarath Chandar, Yoshua Bengio
2017	J	`jnl`	A Deep Reinforcement Learning Chatbot. CoRR Iulian Vlad Serban, Chinnadhurai Sankar, Mathieu Germain, Saizheng Zhang, Zhouhan Lin, Sandeep Subramanian, Taesup Kim, Michael Pieper, Sarath Chandar, Nan Rosemary Ke, Sai Mudumba, Alexandre de Brébisson, Jose Sotelo, Dendi Suhubdy, Vincent Michalski, Alexandre Nguyen, Joelle Pineau, Yoshua Bengio
2017	A*	`conf`	GuessWhat?! Visual Object Discovery through Multi-modal Dialogue. CVPR Harm de Vries, Florian Strub, Sarath Chandar, Olivier Pietquin, Hugo Larochelle, Aaron C. Courville
2017	J	`jnl`	Memory Augmented Neural Networks with Wormhole Connections. CoRR Çaglar Gülçehre, Sarath Chandar, Yoshua Bengio
2016	B	`conf`	A Correlational Encoder Decoder Architecture for Pivot Based Sequence Generation. COLING Amrita Saha, Mitesh M. Khapra, Sarath Chandar, Janarthanan Rajendran, Kyunghyun Cho
2016	J	`jnl`	A Correlational Encoder Decoder Architecture for Pivot Based Sequence Generation. CoRR Amrita Saha, Mitesh M. Khapra, Sarath Chandar, Janarthanan Rajendran, Kyunghyun Cho
2016	—	`conf`	Bridge Correlational Neural Networks for Multilingual Multimodal Representation Learning. HLT-NAACL Janarthanan Rajendran, Mitesh M. Khapra, Sarath Chandar, Balaraman Ravindran
2016	J	`jnl`	Correlational Neural Networks. Neural Comput. Sarath Chandar, Mitesh M. Khapra, Hugo Larochelle, Balaraman Ravindran
2016	J	`jnl`	Dynamic Neural Turing Machine with Soft and Hard Addressing Schemes. CoRR Çaglar Gülçehre, Sarath Chandar, Kyunghyun Cho, Yoshua Bengio
2016	—	`conf`	Generating Factoid Questions With Recurrent Neural Networks: The 30M Factoid Question-Answer Corpus. ACL (1) Iulian Vlad Serban, Alberto García-Durán, Çaglar Gülçehre, Sungjin Ahn, Sarath Chandar, Aaron C. Courville, Yoshua Bengio
2016	J	`jnl`	Generating Factoid Questions With Recurrent Neural Networks: The 30M Factoid Question-Answer Corpus. CoRR Iulian Vlad Serban, Alberto García-Durán, Çaglar Gülçehre, Sungjin Ahn, Sarath Chandar, Aaron C. Courville, Yoshua Bengio
2016	J	`jnl`	GuessWhat?! Visual object discovery through multi-modal dialogue. CoRR Harm de Vries, Florian Strub, Sarath Chandar, Olivier Pietquin, Hugo Larochelle, Aaron C. Courville
2016	J	`jnl`	Hierarchical Memory Networks. CoRR Sarath Chandar, Sungjin Ahn, Hugo Larochelle, Pascal Vincent, Gerald Tesauro, Yoshua Bengio
2016	—	`conf`	Multilingual Multimodal Language Processing Using Neural Networks. HLT-NAACL Tutorials Mitesh M. Khapra, Sarath Chandar
2015	J	`jnl`	Bridge Correlational Neural Networks for Multilingual Multimodal Representation Learning. CoRR Janarthanan Rajendran, Mitesh M. Khapra, Sarath Chandar, Balaraman Ravindran
2015	J	`jnl`	Correlational Neural Networks. CoRR Sarath Chandar, Mitesh M. Khapra, Hugo Larochelle, Balaraman Ravindran
2015	J	`jnl`	Reasoning about Linguistic Regularities in Word Embeddings using Matrix Manifolds. CoRR Sridhar Mahadevan, Sarath Chandar
2015	J	`jnl`	TSEB: More Efficient Thompson Sampling for Policy Learning. CoRR P. Prasanna, Sarath Chandar, Balaraman Ravindran