collaborators

10 papers

cs.CL2026

Self-Improving Pretraining: using post-trained models to pretrain better models

Ellen Xiaoqing Tan, Jack Lanchantin, Shehzaad Dhuliawala +9

Large language models are classically trained in stages: pretraining on raw text followed by post-training for instruction following and reasoning. However, this separation creates…

cs.AI2026

Reasoning over mathematical objects: on-policy reward modeling and test time aggregation

Pranjal Aggarwal, Marjan Ghazvininejad, Seungone Kim +18

The ability to precisely derive mathematical objects is a core requirement for downstream STEM applications, including mathematics, physics, and chemistry, where reasoning must cul…

cs.CL2025

Hybrid Reinforcement: When Reward Is Sparse, It's Better to Be Dense

Leitian Tao, Ilia Kulikov, Swarnadeep Saha +5

Post-training for reasoning of large language models (LLMs) increasingly relies on verifiable rewards: deterministic checkers that provide 0-1 correctness signals. While reliable,…

cs.CL2025

J1: Incentivizing Thinking in LLM-as-a-Judge via Reinforcement Learning

Chenxi Whitehouse, Tianlu Wang, Ping Yu +4

The progress of AI is bottlenecked by the quality of evaluation, making powerful LLM-as-a-Judge models a core solution. The efficacy of these judges depends on their chain-of-thoug…

cs.CL2025

RESTRAIN: From Spurious Votes to Signals -- Self-Driven RL with Self-Penalization

Zhaoning Yu, Will Su, Leitian Tao +9

Reinforcement learning with human-annotated data has boosted chain-of-thought reasoning in large reasoning models, but these gains come at high costs in labeled data while falterin…

cs.AI2025

CoT-Self-Instruct: Building high-quality synthetic prompts for reasoning and non-reasoning tasks

Ping Yu, Jack Lanchantin, Tianlu Wang +6

We propose CoT-Self-Instruct, a synthetic data generation method that instructs LLMs to first reason and plan via Chain-of-Thought (CoT) based on given seed tasks, and then generat…