XL

Xin Li

cs.CVcs.LG

On Valency

published · living versions

W_r4r6wp7a·v1 · currentpublished

EdgeKernelBench: Unified LLM-Driven Kernel Generation for Edge Backends

with Yuhua Zheng, Xueyi Chen, Xinze Zou, Haoji Hu +1

1 version

W_fbtadppd·v1published

Think Visually Across Space and Time: Grounded Reasoning for Video Segmentation

W_w8n2x5gs·v1published

DeOverlay: A Benchmark and Source-Anchored Flow for Video Overlay Removal

Preprints & journals

3 papers in the corpus · 2026

DeOverlay: A Benchmark and Source-Anchored Flow for Video Overlay Removal2610.26081v1 · Deshui Miao, Yuhang Ma, Shaoyong Jia et al.2026 · 0 citationsarXivon Valency

Think Visually Across Space and Time: Grounded Reasoning for Video Segmentation2610.25090v1 · Junwei Wen, Deshui Miao, Guangming Lu et al.2026 · 0 citationsarXivon Valency

EdgeKernelBench: Unified LLM-Driven Kernel Generation for Edge Backends2610.24648v1 · Yuhua Zheng, Xueyi Chen, Xinze Zou et al.2026 · 0 citationsarXivon Valency

Career total: 3 works. 3 are in this corpus.

Profile built from the corpus for this byline.

Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.