Chenyang Wu

Papers on Lattice

Total citations

Topics

Publication activitypapers/week, last 8 weeks

Research focus

Computer Vision (2)Multimodal Models (1)Architecture Design (Transformers, SSMs, MoE) (1)Inference & Quantization (1)

Frequent co-authors

Xinran Qin (2)Fan Li (2)Dehong Kong (1)Lina Lei (1)

Papers (2)

Jun 4, 2026

Dehong Kong +123w ago

ShotCrop$^3$: Cropping Human-Centric Images into Cinematic Triple-Shot Compositions

ShotCrop$^3$ transforms a single image into a powerful narrative tool by generating three distinct shots, outperforming existing models in shot localization accuracy.

Dehong Kong, Lina Lei, Lingtao Zheng +10

Computer Vision Multimodal Models

Apr 30, 2026

Apr 30, 2026·also Nankai University

YOSE: You Only Select Essential Tokens for Efficient DiT-based Video Object Removal

Achieve up to 2.5X faster video object removal by focusing DiT computations only on the essential tokens dictated by the mask.

Chenyang Wu, Lina Lei, Fan Li +6

Architecture Design (Transformers, SSMs, MoE)Computer Vision Inference & Quantization

Search

Chenyang Wu

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)