Songshi Liang

2 accepted papers

2026

Does Your Reasoning Model Implicitly Know When to Stop Thinking?

Zixuan Huang, Xin Xia, Yuxi Ren, Jianbin Zheng, Xuanda Wang, Zhixia Zhang +8

ICML 2026poster

Recent advancements in large reasoning models (LRMs) have greatly improved their capabilities on complex reasoning tasks through Long Chains of Thought (CoTs). However, this approach often results in substantial redundancy, impairing computational efficiency and causing significant delays in real-ti…

Cited by 0 Source ↗Scholar ↗

2026

Real-Time Aligned Reward Model beyond Semantics

Zixuan Huang, Xin Xia, Yuxi Ren, Jianbin Zheng, Xuefeng Xiao, Hongyan Xie +7

ICML 2026poster

Reinforcement Learning from Human Feedback (RLHF) is a pivotal technique for aligning large language models (LLMs) with human preferences, yet it is susceptible to reward overoptimization, in which policy models overfit to the reward model, exploit spurious reward patterns instead of faithfully capt…

Cited by 0 Source ↗Scholar ↗