Kai Tang

Researcher, tencent ailab

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 5

1 paper

Friday, December 5, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

No Loss, No Gain: Gated Refinement and Adaptive Compression for Prompt Optimization

#4012 · Wenhang Shi, Yiren Chen, Shuqing Bian, Xinyi Zhang, Kai Tang, Pengfei Hu, Zhe Zhao, WEI LU, Xiaoyong Du

GRACE achieves significant gains on performance and efficiency in prompt optimization by strategically introducing information loss through a dual mechanism of refinement and compression.