28 citations · 150 across the 35 of their papers we have counts for
6 papers · 1 filter
A Comedy of Estimators: On KL Regularization in RL Training of LLMs
Vedant Shah, Johan Obando-Ceron, Vineet Jain +10
The reasoning performance of large language models (LLMs) can be substantially improved by training them with reinforcement learning (RL). The RL objective for LLM training involve…
Benchmarking World-Model Learning with Environment-Level Queries
Archana Warrier, Dat Nguyen, Michelangelo Naim +8
World models are central to building AI agents capable of flexible reasoning and planning. Yet current evaluations (i) test only properties measurable from observed interactions, s…
Recursive Self-Aggregation Unlocks Deep Thinking in Large Language Models
Siddarth Venkatraman, Vineet Jain, Sarthak Mittal +9
Test-time scaling methods improve the capabilities of large language models (LLMs) by increasing the amount of compute used during inference to make a prediction. Inference-time co…
Latent Veracity Inference for Identifying Errors in Stepwise Reasoning
Minsu Kim, Jean-Pierre Falet, Oliver E. Richardson +5
Chain-of-Thought (CoT) reasoning has advanced the capabilities and transparency of language models (LMs); however, reasoning chains can contain inaccurate statements that reduce pe…
Solving Bayesian inverse problems with diffusion priors and off-policy RL
Luca Scimeca, Siddarth Venkatraman, Moksh Jain +14
This paper presents a practical application of Relative Trajectory Balance (RTB), a recently introduced off-policy reinforcement learning (RL) objective that can asymptotically sol…
Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training
Brian Bartoldson, Siddarth Venkatraman, James Diffenderfer +7
Reinforcement learning (RL) is a critical component of large language model (LLM) post-training. However, on-policy algorithms used for post-training are not naturally robust to a…