Zhifang Sui

LLM-REVal: Can We Trust LLM Reviewers Yet?

Stabilizing MoE Reinforcement Learning by Aligning Training and Inference Routers

Enhancing Reliability across Short and Long-Form Question Answering via Reinforcement Learning

SelfBudgeter: Adaptive Token Allocation for Efficient LLM Reasoning

Towards Stable and Effective Reinforcement learning for Mixture-of-Experts

Self-Boosting Large Language Models with Synthetic Preference Data

Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models

Lookers-On See Most of the Game: An External Insight-Guided Method for Enhancing Uncertainty Estimation