Li

8

Papers

31

Total Citations

Papers (8)

AR-Diffusion: Asynchronous Video Generation with Auto-Regressive Diffusion

Sculpting Memory: Multi-Concept Forgetting in Diffusion Models via Dynamic Mask and Concept-Aware Optimization

EigenGS Representation: From Eigenspace to Gaussian Image Space

Optimal Transport for Brain-Image Alignment: Unveiling Redundancy and Synergy in Neural Information Processing

Empowering Resampling Operation for Ultra-High-Definition Image Enhancement with Model-Aware Guidance

UniCorn: A Unified Contrastive Learning Approach for Multi-view Molecular Representation Learning

Learning Precise Affordances from Egocentric Videos for Robotic Manipulation

Principles of Visual Tokens for Efficient Video Understanding