Sarthak Mittal

42 papers A* 11A 1B 1Journal 26Unranked 3

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	A Compression Perspective on Simplicity Bias. CoRR Tom Marty, Eric Elmoznino, Léo Gagnon, Tejas Kasetty, Mizu Nishikawa-Toomey, Sarthak Mittal, Guillaume Lajoie, Dhanya Sridhar
2025	J	`jnl`	A Comedy of Estimators: On KL Regularization in RL Training of LLMs. CoRR Vedant Shah, Johan S. Obando-Ceron, Vineet Jain, Brian R. Bartoldson, Bhavya Kailkhura, Sarthak Mittal, Glen Berseth, Pablo Samuel Castro, Yoshua Bengio, Nikolay Malkin, Moksh Jain, Siddarth Venkatraman, Aaron C. Courville
2025	J	`jnl`	Amortized In-Context Bayesian Posterior Estimation. CoRR Sarthak Mittal, Niels Bracher, Guillaume Lajoie, Priyank Jaini, Marcus A. Brubaker
2025	A*	`conf`	Does learning the right latent variables necessarily improve in-context learning? ICML Sarthak Mittal, Eric Elmoznino, Léo Gagnon, Sangnie Bhardwaj, Guillaume Lajoie, Dhanya Sridhar
2025	A*	`conf`	In-Context Learning and Occam's Razor. ICML Eric Elmoznino, Tom Marty, Tejas Kasetty, Léo Gagnon, Sarthak Mittal, Mahan Fathi, Dhanya Sridhar, Guillaume Lajoie
2025	J	`jnl`	In-Context Parametric Inference: Point or Distribution Estimators? CoRR Sarthak Mittal, Yoshua Bengio, Nikolay Malkin, Guillaume Lajoie
2025	J	`jnl`	Iterative Amortized Inference: Unifying In-Context Learning and Learned Optimizers. CoRR Sarthak Mittal, Divyat Mahajan, Guillaume Lajoie, Mohammad Pezeshki
2025	A*	`conf`	Learning Condensed Graph via Differentiable Atom Mapping for Reaction Yield Prediction. ICML Ankit Ghosh, Gargee Kashyap, Sarthak Mittal, Nupur Jain, Raghavan B. Sunoj, Abir De
2025	J	`jnl`	Next-Token Prediction Should be Ambiguity-Sensitive: A Meta-Learning Perspective. CoRR Léo Gagnon, Eric Elmoznino, Sarthak Mittal, Tom Marty, Tejas Kasetty, Dhanya Sridhar, Guillaume Lajoie
2025	J	`jnl`	Recursive Self-Aggregation Unlocks Deep Thinking in Large Language Models. CoRR Siddarth Venkatraman, Vineet Jain, Sarthak Mittal, Vedant Shah, Johan S. Obando-Ceron, Yoshua Bengio, Brian R. Bartoldson, Bhavya Kailkhura, Guillaume Lajoie, Glen Berseth, Nikolay Malkin, Moksh Jain
2025	J	`jnl`	Reinforced sequential Monte Carlo for amortised sampling. CoRR Sanghyeok Choi, Sarthak Mittal, Víctor Elvira, Jinkyoo Park, Nikolay Malkin
2025	J	`jnl`	Solving Bayesian inverse problems with diffusion priors and off-policy RL. CoRR Luca Scimeca, Siddarth Venkatraman, Moksh Jain, Minsu Kim, Marcin Sendera, Mohsin Hasan, Luke Rowe, Sarthak Mittal, Pablo Lemos, Emmanuel Bengio, Alexandre Adam, Jarrid Rector-Brooks, Yashar Hezaveh, Laurence Perreault Levasseur, Yoshua Bengio, Glen Berseth, Nikolay Malkin
2025	A*	`conf`	Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction. ICLR Jarrid Rector-Brooks, Mohsin Hasan, Zhangzhi Peng, Cheng-Hao Liu, Sarthak Mittal, Nouha Dziri, Michael M. Bronstein, Pranam Chatterjee, Alexander Tong, Joey Bose
2024	A*	`conf`	Amortizing intractable inference in diffusion models for vision, language, and control. NeurIPS Siddarth Venkatraman, Moksh Jain, Luca Scimeca, Minsu Kim, Marcin Sendera, Mohsin Hasan, Luke Rowe, Sarthak Mittal, Pablo Lemos, Emmanuel Bengio, Alexandre Adam, Jarrid Rector-Brooks, Yoshua Bengio, Glen Berseth, Nikolay Malkin
2024	J	`jnl`	Amortizing intractable inference in diffusion models for vision, language, and control. CoRR Siddarth Venkatraman, Moksh Jain, Luca Scimeca, Minsu Kim, Marcin Sendera, Mohsin Hasan, Luke Rowe, Sarthak Mittal, Pablo Lemos, Emmanuel Bengio, Alexandre Adam, Jarrid Rector-Brooks, Yoshua Bengio, Glen Berseth, Nikolay Malkin
2024	J	`jnl`	Does learning the right latent variables necessarily improve in-context learning? CoRR Sarthak Mittal, Eric Elmoznino, Léo Gagnon, Sangnie Bhardwaj, Dhanya Sridhar, Guillaume Lajoie
2024	A*	`conf`	Improved off-policy training of diffusion samplers. NeurIPS Marcin Sendera, Minsu Kim, Sarthak Mittal, Pablo Lemos, Luca Scimeca, Jarrid Rector-Brooks, Alexandre Adam, Yoshua Bengio, Nikolay Malkin
2024	J	`jnl`	In-context learning and Occam's razor. CoRR Eric Elmoznino, Tom Marty, Tejas Kasetty, Léo Gagnon, Sarthak Mittal, Mahan Fathi, Dhanya Sridhar, Guillaume Lajoie
2024	A*	`conf`	Iterated Denoising Energy Matching for Sampling from Boltzmann Densities. ICML Tara Akhound-Sadegh, Jarrid Rector-Brooks, Avishek Joey Bose, Sarthak Mittal, Pablo Lemos, Cheng-Hao Liu, Marcin Sendera, Siamak Ravanbakhsh, Gauthier Gidel, Yoshua Bengio, Nikolay Malkin, Alexander Tong
2024	J	`jnl`	Iterated Denoising Energy Matching for Sampling from Boltzmann Densities. CoRR Tara Akhound-Sadegh, Jarrid Rector-Brooks, Avishek Joey Bose, Sarthak Mittal, Pablo Lemos, Cheng-Hao Liu, Marcin Sendera, Siamak Ravanbakhsh, Gauthier Gidel, Yoshua Bengio, Nikolay Malkin, Alexander Tong
2024	J	`jnl`	On diffusion models for amortized inference: Benchmarking and improving stochastic control and sampling. CoRR Marcin Sendera, Minsu Kim, Sarthak Mittal, Pablo Lemos, Luca Scimeca, Jarrid Rector-Brooks, Alexandre Adam, Yoshua Bengio, Nikolay Malkin
2024	J	`jnl`	Recurrent Interpolants for Probabilistic Time Series Prediction. CoRR Yu Chen, Marin Bilos, Sarthak Mittal, Wei Deng, Kashif Rasul, Anderson Schneider
2024	J	`jnl`	Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction. CoRR Jarrid Rector-Brooks, Mohsin Hasan, Zhangzhi Peng, Zachary Quinn, Cheng-Hao Liu, Sarthak Mittal, Nouha Dziri, Michael M. Bronstein, Yoshua Bengio, Pranam Chatterjee, Alexander Tong, Avishek Joey Bose
2023	A*	`conf`	Diffusion Based Representation Learning. ICML Sarthak Mittal, Korbinian Abstreiter, Stefan Bauer, Bernhard Schölkopf, Arash Mehrjou
2023	—	`conf`	Leveraging Synthetic Targets for Machine Translation. ACL (Findings) Sarthak Mittal, Oleksii Hrinchuk, Oleksii Kuchaiev
2023	J	`jnl`	Leveraging Synthetic Targets for Machine Translation. CoRR Sarthak Mittal, Oleksii Hrinchuk, Oleksii Kuchaiev
2023	A	`conf`	MixupE: Understanding and improving Mixup from directional derivative perspective. UAI Yingtian Zou, Vikas Verma, Sarthak Mittal, Wai Hoh Tang, Hieu Pham, Juho Kannala, Yoshua Bengio, Arno Solin, Kenji Kawaguchi
2022	A*	`conf`	Compositional Attention: Disentangling Search and Retrieval. ICLR Sarthak Mittal, Sharath Chandra Raparthy, Irina Rish, Yoshua Bengio, Guillaume Lajoie
2022	J	`jnl`	Deep Reinforcement Learning-Based Traffic Light Scheduling Framework for SDN-Enabled Smart Transportation System. IEEE Trans. Intell. Transp. Syst. Neetesh Kumar, Sarthak Mittal, Vaibhav Garg, Neeraj Kumar
2022	J	`jnl`	From Points to Functions: Infinite-dimensional Representations in Diffusion Models. CoRR Sarthak Mittal, Guillaume Lajoie, Stefan Bauer, Arash Mehrjou
2022	A*	`conf`	Is a Modular Architecture Enough? NeurIPS Sarthak Mittal, Yoshua Bengio, Guillaume Lajoie
2022	J	`jnl`	Is a Modular Architecture Enough? CoRR Sarthak Mittal, Yoshua Bengio, Guillaume Lajoie
2022	J	`jnl`	MixupE: Understanding and Improving Mixup from Directional Derivative Perspective. CoRR Vikas Verma, Sarthak Mittal, Wai Hoh Tang, Hieu Pham, Juho Kannala, Yoshua Bengio, Arno Solin, Kenji Kawaguchi
2022	J	`jnl`	On Neural Architecture Inductive Biases for Relational Tasks. CoRR Giancarlo Kerg, Sarthak Mittal, David Rolnick, Yoshua Bengio, Blake A. Richards, Guillaume Lajoie
2021	J	`jnl`	Compositional Attention: Disentangling Search and Retrieval. CoRR Sarthak Mittal, Sharath Chandra Raparthy, Irina Rish, Yoshua Bengio, Guillaume Lajoie
2021	B	`conf`	Congestion Control utilizing Software Defined Control Architecture at the Traffic Light Intersection. MASS Vaibhav Garg, Anuj Sachan, Neetesh Kumar, Sarthak Mittal
2021	—	`conf`	Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning. NeurIPS Datasets and Benchmarks Nan Rosemary Ke, Aniket Didolkar, Sarthak Mittal, Anirudh Goyal, Guillaume Lajoie, Stefan Bauer, Danilo Jimenez Rezende, Michael Mozer, Yoshua Bengio, Chris Pal
2021	J	`jnl`	Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning. CoRR Nan Rosemary Ke, Aniket Didolkar, Sarthak Mittal, Anirudh Goyal, Guillaume Lajoie, Stefan Bauer, Danilo J. Rezende, Yoshua Bengio, Michael Mozer, Christopher J. Pal
2020	A*	`conf`	Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules. ICML Sarthak Mittal, Alex Lamb, Anirudh Goyal, Vikram Voleti, Murray Shanahan, Guillaume Lajoie, Michael Mozer, Yoshua Bengio
2020	J	`jnl`	Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules. CoRR Sarthak Mittal, Alex Lamb, Anirudh Goyal, Vikram Voleti, Murray Shanahan, Guillaume Lajoie, Michael Mozer, Yoshua Bengio
2019	—	`conf`	Prediction of employee performance using machine learning techniques. AISS Anu Singh Lather, Ruchika Malhotra, Priya Saloni, Prabhjot Singh, Sarthak Mittal
2018	J	`jnl`	A Modern Take on the Bias-Variance Tradeoff in Neural Networks. CoRR Brady Neal, Sarthak Mittal, Aristide Baratin, Vinayak Tantia, Matthew Scicluna, Simon Lacoste-Julien, Ioannis Mitliagkas