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

Teng Hu

2 indexed papers

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

Publications per year

2
26

Top categories

Vision×2AI×1

Frequent co-authors

Yuheng Chen1×
Yuji Wang1×
Qingdong He1×
Lizhuang Ma1×
Jiangning Zhang1×
Yuhang Han1×

Research Timeline

2026
Spatial-Temporal Decoupled Reference Conditioning for Identity-Preserving Text-to-Video Generation

The paper proposes ST-DRC, a Spatial-Temporal Decoupled Reference Conditioning framework that effectively balances high-level semantic control and low-level identity fidelity for text-to-video generation.

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.

Highlighted terms show continued research focus across papers

Papers

cs.CVRecentJun 1, 2026

Spatial-Temporal Decoupled Reference Conditioning for Identity-Preserving Text-to-Video Generation

Yuheng Chen, Teng Hu, Yuji Wang, Qingdong He +2 more

The paper proposes ST-DRC, a Spatial-Temporal Decoupled Reference Conditioning framework that effectively balances high-level semantic control and low-level identity fidelity for text-to-video generat…

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 →