SM
Sarthak Mittal
cs.LGcs.AIstat.MLcs.CLcs.CVcs.NEcs.RO
On Valency
published · living versionsW_5txyfx4z·v1 · currentpublished
Preprints & journals
28 papers in the corpus · 2018–2026Shieldstral2607.25857v2 · Antonia Calvi, Avinash Sooriyarachchi, Giada Pistilli et al.2026 · 0 citationsarXiv
Robostral Navigate2607.20785v3 · Abdelaziz Bounhar, Abhijeet Somani, Aditi Kabra et al.2026 · 0 citationsarXiv
Simplifying the Modeling of Arbitrary Conditionals in Natural Language2606.14943v1 · Yinhan Lu, Eric Elmoznino, L'eo Gagnon et al.2026 · 0 citationsarXiv
Beyond Distribution Sharpening: The Importance of Task Rewards2604.16259v1 · Sarthak Mittal, Leo Gagnon, Guillaume Lajoie2026 · 0 citationsarXiv
A Compression Perspective on Simplicity Bias2603.25839v1 · Tom Marty, Eric Elmoznino, Leo Gagnon et al.2026 · 0 citationsarXiv
A Comedy of Estimators: On KL Regularization in RL Training of LLMs2512.21852v4 · Vedant Shah, Johan Obando-Ceron, Vineet Jain et al.2025 · 0 citationsarXiv
Iterative Amortized Inference: Unifying In-Context Learning and Learned Optimizers2510.11471v1 · Sarthak Mittal, Divyat Mahajan, Guillaume Lajoie et al.2025 · 0 citationsarXiv
Reinforced sequential Monte Carlo for amortised sampling2510.11711v3 · Sanghyeok Choi, Sarthak Mittal, V'ictor Elvira et al.2025 · 0 citationsarXiv
Recursive Self-Aggregation Unlocks Deep Thinking in Large Language Models2509.26626v2 · Siddarth Venkatraman, Vineet Jain, Sarthak Mittal et al.2025 · 0 citationsarXiv
Solving Bayesian inverse problems with diffusion priors and off-policy RL2503.09746v1 · Luca Scimeca, Siddarth Venkatraman, Moksh Jain et al.2025 · 0 citationsarXiv
In-Context Parametric Inference: Point or Distribution Estimators?2502.11617v1 · Sarthak Mittal, Yoshua Bengio, Nikolay Malkin et al.2025 · 0 citationsarXiv
Amortized In-Context Bayesian Posterior Estimation2502.06601v1 · Sarthak Mittal, Niels Leif Bracher, Guillaume Lajoie et al.2025 · 2 citationsarXiv
In-context learning and Occam's razor2410.14086v4 · Eric Elmoznino, Tom Marty, Tejas Kasetty et al.2024 · 0 citationsarXiv
Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction2410.08134v1 · Jarrid Rector-Brooks, Mohsin Hasan, Zhangzhi Peng et al.2024 · 2 citationsarXiv
Recurrent Interpolants for Probabilistic Time Series Prediction2409.11684v2 · Yu Chen, Marin Bilos, Sarthak Mittal et al.2024 · 0 citationsarXiv
Amortizing intractable inference in diffusion models for vision, language, and control2405.20971v3 · Siddarth Venkatraman, Moksh Jain, Luca Scimeca et al.2024 · 1 citationarXiv
Does learning the right latent variables necessarily improve in-context learning?2405.19162v2 · Sarthak Mittal, Eric Elmoznino, Leo Gagnon et al.2024 · 0 citationsarXiv
Iterated Denoising Energy Matching for Sampling from Boltzmann Densities2402.06121v2 · Tara Akhound-Sadegh, Jarrid Rector-Brooks, Avishek Joey Bose et al.2024 · 1 citationarXiv
Improved off-policy training of diffusion samplers2402.05098v5 · Marcin Sendera, Minsu Kim, Sarthak Mittal et al.2024 · 0 citationsarXiv
Leveraging Synthetic Targets for Machine Translation2305.06155v1 · Sarthak Mittal, Oleksii Hrinchuk, Oleksii Kuchaiev2023 · 1 citationarXiv
MixupE: Understanding and Improving Mixup from Directional Derivative Perspective2212.13381v5 · Yingtian Zou, Vikas Verma, Sarthak Mittal et al.2022 · 2 citationsarXiv
From Points to Functions: Infinite-dimensional Representations in Diffusion Models2210.13774v1 · Sarthak Mittal, Guillaume Lajoie, Stefan Bauer et al.2022 · 3 citationsarXiv
On Neural Architecture Inductive Biases for Relational Tasks2206.05056v1 · Giancarlo Kerg, Sarthak Mittal, David Rolnick et al.2022 · 10 citationsarXiv
Is a Modular Architecture Enough?2206.02713v1 · Sarthak Mittal, Yoshua Bengio, Guillaume Lajoie2022 · 19 citationsarXiv
Compositional Attention: Disentangling Search and Retrieval2110.09419v2 · Sarthak Mittal, Sharath Chandra Raparthy, Irina Rish et al.2021 · 11 citationsarXiv
Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning2107.00848v1 · Nan Rosemary Ke, Aniket Didolkar, Sarthak Mittal et al.2021 · 8 citationsarXiv
Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules2006.16981v3 · Sarthak Mittal, Alex Lamb, Anirudh Goyal et al.2020 · 26 citationsarXiv
A Modern Take on the Bias-Variance Tradeoff in Neural Networks1810.08591v4 · Brady Neal, Sarthak Mittal, Aristide Baratin et al.2018 · 111 citationsICML 2019 Workshop on Identifying and Understanding Deep Learning Phenomena
Career total: 28 works. 28 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.