Shagun Sodhani

60 papers A* 16Journal 40Unranked 4

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench. CoRR Edan Toledo, Karen Hambardzumyan, Martin Josifoski, Rishi Hazra, Nicolas Mario Baldwin, Alexis Audran-Reiss, Michael Kuchnik, Despoina Magka, Minqi Jiang, Alisia Maria Lupidi, Andrei Lupu, Roberta Raileanu, Kelvin Niu, Tatiana Shavrina, Jean-Christophe Gagnon-Audet, Michael Shvartsman, Shagun Sodhani, Alexander H. Miller, Abhishek Charnalia, Derek Dunfield, Carole-Jean Wu, Pontus Stenetorp, Nicola Cancedda, Jakob Nicolaus Foerster, Yoram Bachrach
2025	J	`jnl`	Do Large Language Models Know How Much They Know? CoRR Gabriele Prato, Jerry Huang, Prasannna Parthasarathi, Shagun Sodhani, 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	A*	`conf`	MaestroMotif: Skill Design from Artificial Intelligence Feedback. ICLR Martin Klissarov, Mikael Henaff, Roberta Raileanu, Shagun Sodhani, Pascal Vincent, Amy Zhang, Pierre-Luc Bacon, Doina Precup, Marlos C. Machado, Pierluca D'Oro
2025	J	`jnl`	Scaling and Distilling Transformer Models for sEMG. CoRR Nicholas Mehlman, Jean-Christophe Gagnon-Audet, Michael Shvartsman, Kelvin Niu, Alexander H. Miller, Shagun Sodhani
2025	J	`jnl`	Scaling and Distilling Transformer Models for sEMG. Trans. Mach. Learn. Res. Nicholas Mehlman, Jean-Christophe Gagnon-Audet, Michael Shvartsman, Kelvin Niu, Alexander H. Miller, Shagun Sodhani
2025	J	`jnl`	The Automated LLM Speedrunning Benchmark: Reproducing NanoGPT Improvements. CoRR Bingchen Zhao, Despoina Magka, Minqi Jiang, Xian Li, Roberta Raileanu, Tatiana Shavrina, Jean-Christophe Gagnon-Audet, Kelvin Niu, Shagun Sodhani, Michael Shvartsman, Andrei Lupu, Alisia Maria Lupidi, Edan Toledo, Karen Hambardzumyan, Martin Josifoski, Thomas Foster, Lucia Cipolina-Kun, Abhishek Charnalia, Derek Dunfield, Alexander H. Miller, Oisin Mac Aodha, Jakob N. Foerster, Yoram Bachrach
2024	A*	`conf`	Do Large Language Models Know How Much They Know? EMNLP Gabriele Prato, Jerry Huang, Prasanna Parthasarathi, Shagun Sodhani, Sarath Chandar
2024	A*	`conf`	Harnessing small projectors and multiple views for efficient vision pretraining. NeurIPS Arna Ghosh, Kumar Krishna Agrawal, Shagun Sodhani, Adam Oberman, Blake A. Richards
2024	J	`jnl`	MaestroMotif: Skill Design from Artificial Intelligence Feedback. CoRR Martin Klissarov, Mikael Henaff, Roberta Raileanu, Shagun Sodhani, Pascal Vincent, Amy Zhang, Pierre-Luc Bacon, Doina Precup, Marlos C. Machado, Pierluca D'Oro
2024	A*	`conf`	Motif: Intrinsic Motivation from Artificial Intelligence Feedback. ICLR Martin Klissarov, Pierluca D'Oro, Shagun Sodhani, Roberta Raileanu, Pierre-Luc Bacon, Pascal Vincent, Amy Zhang, Mikael Henaff
2024	A*	`conf`	TorchRL: A data-driven decision-making library for PyTorch. ICLR Albert Bou, Matteo Bettini, Sebastian Dittert, Vikash Kumar, Shagun Sodhani, Xiaomeng Yang, Gianni De Fabritiis, Vincent Moens
2024	A*	`conf`	When should we prefer Decision Transformers for Offline Reinforcement Learning? ICLR Prajjwal Bhargava, Rohan Chitnis, Alborz Geramifard, Shagun Sodhani, Amy Zhang
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`	Improving Generalization with Approximate Factored Value Functions. Trans. Mach. Learn. Res. Shagun Sodhani, Sergey Levine, Amy Zhang
2023	J	`jnl`	Motif: Intrinsic Motivation from Artificial Intelligence Feedback. CoRR Martin Klissarov, Pierluca D'Oro, Shagun Sodhani, Roberta Raileanu, Pierre-Luc Bacon, Pascal Vincent, Amy Zhang, Mikael Henaff
2023	J	`jnl`	Sequence Modeling is a Robust Contender for Offline Reinforcement Learning. CoRR Prajjwal Bhargava, Rohan Chitnis, Alborz Geramifard, Shagun Sodhani, Amy Zhang
2023	J	`jnl`	TorchRL: A data-driven decision-making library for PyTorch. CoRR Albert Bou, Matteo Bettini, Sebastian Dittert, Vikash Kumar, Shagun Sodhani, Xiaomeng Yang, Gianni De Fabritiis, Vincent Moens
2023	A*	`conf`	VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training. ICLR Yecheng Jason Ma, Shagun Sodhani, Dinesh Jayaraman, Osbert Bastani, Vikash Kumar, Amy Zhang
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	—	`conf`	Block Contextual MDPs for Continual Learning. L4DC Shagun Sodhani, Franziska Meier, Joelle Pineau, Amy Zhang
2022	A*	`conf`	Robust Policy Learning over Multiple Uncertainty Sets. ICML Annie Xie, Shagun Sodhani, Chelsea Finn, Joelle Pineau, Amy Zhang
2022	J	`jnl`	Robust Policy Learning over Multiple Uncertainty Sets. CoRR Annie Xie, Shagun Sodhani, Chelsea Finn, Joelle Pineau, Amy Zhang
2022	A*	`conf`	The Neural Race Reduction: Dynamics of Abstraction in Gated Networks. ICML Andrew M. Saxe, Shagun Sodhani, Sam Jay Lewallen
2022	J	`jnl`	The Neural Race Reduction: Dynamics of Abstraction in Gated Networks. CoRR Andrew M. Saxe, Shagun Sodhani, Sam Jay Lewallen
2022	J	`jnl`	VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training. CoRR Yecheng Jason Ma, Shagun Sodhani, Dinesh Jayaraman, Osbert Bastani, Vikash Kumar, Amy Zhang
2021	J	`jnl`	Block Contextual MDPs for Continual Learning. CoRR Shagun Sodhani, Franziska Meier, Joelle Pineau, Amy Zhang
2021	A*	`conf`	IIRC: Incremental Implicitly-Refined Classification. CVPR Mohamed A. Abdelsalam, Mojtaba Faramarzi, Shagun Sodhani, Sarath Chandar
2021	A*	`conf`	Learning Robust State Abstractions for Hidden-Parameter Block MDPs. ICLR Amy Zhang, Shagun Sodhani, Khimya Khetarpal, Joelle Pineau
2021	A*	`conf`	Multi-Task Reinforcement Learning with Context-based Representations. ICML Shagun Sodhani, Amy Zhang, Joelle Pineau
2021	J	`jnl`	Multi-Task Reinforcement Learning with Context-based Representations. CoRR Shagun Sodhani, Amy Zhang, Joelle Pineau
2021	A*	`conf`	Recurrent Independent Mechanisms. ICLR Anirudh Goyal, Alex Lamb, Jordan Hoffmann, Shagun Sodhani, Sergey Levine, Yoshua Bengio, Bernhard Schölkopf
2020	J	`jnl`	A Closer Look at Codistillation for Distributed Training. CoRR Shagun Sodhani, Olivier Delalleau, Mahmoud Assran, Koustuv Sinha, Nicolas Ballas, Michael G. Rabbat
2020	J	`jnl`	Evaluating Logical Generalization in Graph Neural Networks. CoRR Koustuv Sinha, Shagun Sodhani, Joelle Pineau, William L. Hamilton
2020	J	`jnl`	IIRC: Incremental Implicitly-Refined Classification. CoRR Mohamed A. Abdelsalam, Mojtaba Faramarzi, Shagun Sodhani, Sarath Chandar
2020	J	`jnl`	Ideas for Improving the Field of Machine Learning: Summarizing Discussion from the NeurIPS 2019 Retrospectives Workshop. CoRR Shagun Sodhani, Mayoore S. Jaiswal, Lauren Baker, Koustuv Sinha, Carl Shneider, Peter Henderson, Joel Lehman, Ryan Lowe
2020	A*	`conf`	Invariant Causal Prediction for Block MDPs. ICML Amy Zhang, Clare Lyle, Shagun Sodhani, Angelos Filos, Marta Kwiatkowska, Joelle Pineau, Yarin Gal, Doina Precup
2020	J	`jnl`	Invariant Causal Prediction for Block MDPs. CoRR Amy Zhang, Clare Lyle, Shagun Sodhani, Angelos Filos, Marta Kwiatkowska, Joelle Pineau, Yarin Gal, Doina Precup
2020	J	`jnl`	Multi-Task Reinforcement Learning as a Hidden-Parameter Block MDP. CoRR Amy Zhang, Shagun Sodhani, Khimya Khetarpal, Joelle Pineau
2020	A*	`conf`	Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives. ICLR Anirudh Goyal, Shagun Sodhani, Jonathan Binas, Xue Bin Peng, Sergey Levine, Yoshua Bengio
2020	J	`jnl`	Toward Training Recurrent Neural Networks for Lifelong Learning. Neural Comput. Shagun Sodhani, Sarath Chandar, Yoshua Bengio
2020	J	`jnl`	Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims. CoRR Miles Brundage, Shahar Avin, Jasmine Wang, Haydn Belfield, Gretchen Krueger, Gillian K. Hadfield, Heidy Khlaaf, Jingying Yang, Helen Toner, Ruth Fong, Tegan Maharaj, Pang Wei Koh, Sara Hooker, Jade Leung, Andrew Trask, Emma Bluemke, Jonathan Lebensold, Cullen O'Keefe, Mark Koren, Théo Ryffel, J. B. Rubinovitz, Tamay Besiroglu, Federica Carugati, Jack Clark, Peter Eckersley, Sarah de Haas, Maritza Johnson, Ben Laurie, Alex Ingerman, Igor Krawczuk, Amanda Askell, Rosario Cammarota, Andrew Lohn, David Krueger, Charlotte Stix, Peter Henderson, Logan Graham, Carina Prunkl, Bianca Martin, Elizabeth Seger, Noa Zilberman, Seán Ó hÉigeartaigh, Frens Kroeger, Girish Sastry, Rebecca Kagan, Adrian Weller, Brian Tse, Elizabeth Barnes, Allan Dafoe, Paul Scharre, Ariel Herbert-Voss, Martijn Rasser, Shagun Sodhani, Carrick Flynn, Thomas Krendl Gilbert, Lisa Dyer, Saif M. Khan, Yoshua Bengio, Markus Anderljung
2019	J	`jnl`	Attending Over Triads for Learning Signed Network Embedding. Frontiers Big Data Shagun Sodhani, Meng Qu, Jian Tang
2019	—	`conf`	CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Text. EMNLP/IJCNLP (1) Koustuv Sinha, Shagun Sodhani, Jin Dong, Joelle Pineau, William L. Hamilton
2019	J	`jnl`	CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Text. CoRR Koustuv Sinha, Shagun Sodhani, Jin Dong, Joelle Pineau, William L. Hamilton
2019	J	`jnl`	Learning Powerful Policies by Using Consistent Dynamics Model. CoRR Shagun Sodhani, Anirudh Goyal, Tristan Deleu, Yoshua Bengio, Sergey Levine, Jian Tang
2019	J	`jnl`	Recurrent Independent Mechanisms. CoRR Anirudh Goyal, Alex Lamb, Jordan Hoffmann, Shagun Sodhani, Sergey Levine, Yoshua Bengio, Bernhard Schölkopf
2019	J	`jnl`	Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives. CoRR Anirudh Goyal, Shagun Sodhani, Jonathan Binas, Xue Bin Peng, Sergey Levine, Yoshua Bengio
2018	J	`jnl`	Compositional Language Understanding with Text-based Relational Reasoning. CoRR Koustuv Sinha, Shagun Sodhani, William L. Hamilton, Joelle Pineau
2018	J	`jnl`	Environments for Lifelong Reinforcement Learning. CoRR Khimya Khetarpal, Shagun Sodhani, Sarath Chandar, Doina Precup
2018	—	`conf`	Improving Search Through A3C Reinforcement Learning Based Conversational Agent. ICCS (2) Milan Aggarwal, Aarushi Arora, Shagun Sodhani, Balaji Krishnamurthy
2018	J	`jnl`	Memory Augmented Self-Play. CoRR Shagun Sodhani, Vardaan Pahuja
2018	—	`conf`	News Category Network based Approach for News Source Recommendations. ICACCI Swati Gupta, Shagun Sodhani, Dhaval Patel, Biplab Banerjee
2018	J	`jnl`	On Training Recurrent Neural Networks for Lifelong Learning. CoRR Shagun Sodhani, Sarath Chandar, Yoshua Bengio
2018	J	`jnl`	Reproducibility Report for "Learning To Count Objects In Natural Images For Visual Question Answering". CoRR Shagun Sodhani, Vardaan Pahuja
2018	J	`jnl`	Spatial Co-location Pattern Mining - A new perspective using Graph Database. CoRR Sanket Vaibhav Mehta, Shagun Sodhani, Dhaval Patel
2017	J	`jnl`	Reinforcement Learning Based Conversational Search Assistant. CoRR Milan Aggarwal, Aarushi Arora, Shagun Sodhani, Balaji Krishnamurthy
2017	J	`jnl`	Survey of Recent Advances in Visual Question Answering. CoRR Supriya Pandhre, Shagun Sodhani
2015	J	`jnl`	Stack Exchange Tagger. CoRR Sanket Vaibhav Mehta, Shagun Sodhani