collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2026

BASIS: Batchwise Advantage Estimation from Single-Rollout Information Sharing for LLM Reasoning

Shijin Gong, Erhan Xu, Kai Ye +3

Reinforcement learning with verifiable rewards has become a standard recipe for improving the reasoning abilities of large language models. Existing algorithms face a tradeoff betw…

cs.LG2026

Kernelized Advantage Estimation: From Nonparametric Statistics to LLM Reasoning

Shijin Gong, Kai Ye, Jin Zhu +3

Recent advances in large language models (LLMs) have increasingly relied on reinforcement learning (RL) to improve their reasoning capabilities. Three types of approaches have been…

cs.LG2026

Conditional Factuality Controlled LLMs with Generalization Certificates via Conformal Sampling

Kai Ye, Qingtao Pan, Shuo Li

Large language models (LLMs) need reliable test-time control of hallucinations. Existing conformal methods for LLMs typically provide only \emph{marginal} guarantees and rely on a…

cs.LG2026

Demystifying Group Relative Policy Optimization: Its Policy Gradient is a U-Statistic

Hongyi Zhou, Kai Ye, Erhan Xu +4

Group relative policy optimization (GRPO), a core methodological component of DeepSeekMath and DeepSeek-R1, has emerged as a cornerstone for scaling reasoning capabilities of large…

cs.LG2025

Doubly Robust Alignment for Large Language Models

Erhan Xu, Kai Ye, Hongyi Zhou +3

This paper studies reinforcement learning from human feedback (RLHF) for aligning large language models with human preferences. While RLHF has demonstrated promising results, many…