Ming-Ming Cheng

VCIP, CS, Nankai University

Papers on Lattice

Total citations

Topics

Publication activitypapers/week, last 8 weeks

Research focus

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

Frequent co-authors

Chenyang Wu (1)Lina Lei (1)Fan Li (1)Chun-Le Guo (1)

Papers (2)

Apr 30, 2026

Nankai University1d ago·also Huawei, NKIARI

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

Achieve up to 2.5x faster video object removal with comparable visual quality by intelligently selecting only the essential tokens for processing in Diffusion Transformers.

Chenyang Wu, Lina Lei, Fan Li +6

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

Apr 28, 2026

3d ago·also Nankai University, NJUST, Tongyi Lab

Mutual Forcing: Dual-Mode Self-Evolution for Fast Autoregressive Audio-Video Character Generation

Skip the bulky bidirectional teacher: this new method trains a fast, causal audio-video generator directly, slashing sampling steps while maintaining top-tier quality.

Yupeng Zhou, Yupeng Zhou, Lianghua Huang +17

Computer Vision Multimodal Models Speech & Audio

Search

Ming-Ming Cheng

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)