Yeyang Zhou — accepted AI-conference papers

2025

Entropy-based Exploration Conduction for Multi-step Reasoning

Jinghan Zhang, Xiting Wang, Fengran Mo, Yeyang Zhou, Wanfu Gao, Kunpeng Liu

ACL 2025finding

Multi-step processes via large language models (LLMs) have proven effective for solving complex reasoning tasks. However, the depth of exploration of the reasoning procedure can significantly affect the task performance. Existing methods to automatically decide the depth often lead to high cost and…

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

R-KV: Redundancy-aware KV Cache Compression for Reasoning Models

Zefan Cai, Wen Xiao, Hanshi Sun, Cheng Luo, Yikai Zhang, Ke Wan +8

NeurIPS 2025poster

Reasoning models have demonstrated impressive performance in self-reflection and chain-of-thought reasoning. However, they often produce excessively long outputs, leading to prohibitively large key-value (KV) caches during inference. While chain-of-thought inference significantly improves performanc…

Cited by 0 Source ↗Scholar ↗