activity
20242026
collaborators

10 papers

cs.CL2026

Message Passing Enables Efficient Reasoning

Xuecheng Liu, Daman Arora, Gokul Swamy +1

While inference-time scaling has improved the reasoning abilities of large language models (LLMs), the need to generate long chains-of-thought (CoTs) is a computational bottleneck.…

cs.CL2026

Gained in Translation: Privileged Pairwise Judges Enhance Multilingual Reasoning

Lintang Sutawika, Gokul Swamy, Zhiwei Steven Wu +1

When asked a question in a language less seen in its training data, current reasoning large language models (RLMs) often exhibit dramatically lower performance than when asked the…

cs.LG2025

A Smooth Sea Never Made a Skilled SAILOR: Robust Imitation via Learning to Search

Arnav Kumar Jain, Vibhakar Mohta, Subin Kim +5

The fundamental limitation of the behavioral cloning (BC) approach to imitation learning is that it only teaches an agent what the expert did at states the expert visited. This mea…

cs.LG2025

All Roads Lead to Likelihood: The Value of Reinforcement Learning in Fine-Tuning

Gokul Swamy, Sanjiban Choudhury, Wen Sun +2

From a first-principles perspective, it may seem odd that the strongest results in foundation model fine-tuning (FT) are achieved via a relatively complex, two-stage training proce…

cs.LG2024

REBEL: Reinforcement Learning via Regressing Relative Rewards

Zhaolin Gao, Jonathan D. Chang, Wenhao Zhan +7

While originally developed for continuous control problems, Proximal Policy Optimization (PPO) has emerged as the work-horse of a variety of reinforcement learning (RL) application…

cs.LG2024

The Importance of Online Data: Understanding Preference Fine-tuning via Coverage

Yuda Song, Gokul Swamy, Aarti Singh +2

Learning from human preference data has emerged as the dominant paradigm for fine-tuning large language models (LLMs). The two most common families of techniques -- online reinforc…