Yuhang Han
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
AI×2ML×1Vision×1
Frequent co-authors
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