Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Yuhang Han

Yuhang Han

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

AI×2ML×1Vision×1

Frequent co-authors

Linfeng Zhang2×
Jingwei Song1×
Haofeng Xu1×
Jie Xiao1×
Chengke Bao1×
Jingwei Shi1×

Research Timeline

2026
STaR-KV: Spatio-Temporal Adaptive Re-weighting for KV Cache Compression in GUI Vision-Language Models

STaR-KV introduces a novel, training-free KV cache compression framework that adaptively re-weights token importance across spatial, temporal, and distributional axes, significantly reducing GPU memory usage for GUI vision-language models while maintaining high accuracy.

Staleness-Learning Rate Scaling Laws for Asynchronous RLHF

This paper analyzes the effect of using stale rollouts in asynchronous GRPO and derives a stability condition.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.AITheoreticalRecentJul 1, 2026

Staleness-Learning Rate Scaling Laws for Asynchronous RLHF

Jingwei Song, Haofeng Xu, Jie Xiao, Chengke Bao +7 more

This paper analyzes the effect of using stale rollouts in asynchronous GRPO and derives a stability condition.

View →
cs.CVcs.AIRecentJun 1, 2026

STaR-KV: Spatio-Temporal Adaptive Re-weighting for KV Cache Compression in GUI Vision-Language Models

Yuhang Han, Wenzheng Yang, Yujie Chen, Xiangqi Jin +3 more

STaR-KV introduces a novel, training-free KV cache compression framework that adaptively re-weights token importance across spatial, temporal, and distributional axes, significantly reducing GPU memor…

View →