Xintong Li

Papers on Lattice

Total citations

Topics

Publication activitypapers/week, last 8 weeks

Research focus

Reasoning & Chain-of-Thought (1)RLHF & Preference Learning (1)Training Efficiency & Optimization (1)

Frequent co-authors

Gagan Mundada (1)Zihan Huang (1)Rohan Surana (1)Sheldon Yu (1)

Papers (1)

Feb 19, 2026

Gagan Mundada +73w ago

WS-GRPO: Weakly-Supervised Group-Relative Policy Optimization for Rollout-Efficient Reasoning

Stop wasting compute: WS-GRPO learns when an LLM should stop reasoning, slashing rollout lengths without sacrificing accuracy by turning final answer correctness into prefix-level guidance.

Gagan Mundada, Zihan Huang, Rohan Surana +5

Reasoning & Chain-of-Thought RLHF & Preference Learning Training Efficiency & Optimization

Search

Xintong Li

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)