Yumeng Li's picture

Yumeng Li

Yumeng

·

https://yumengli007.github.io

AI & ML interests

Generative Models, Vision-Language Models, Out-of-Distribution Generalization

Recent Activity

upvoted a paper 1 day ago

Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation

authored a paper about 2 months ago

MosaicMem: Hybrid Spatial Memory for Controllable Video World Models

upvoted a paper about 2 months ago

MosaicMem: Hybrid Spatial Memory for Controllable Video World Models

View all activity

Organizations

None yet

Papers 9

arxiv:2603.17117

arxiv:2407.01790

arxiv:2403.13501

arxiv:2401.08815

models 1

Yumeng/ALDM

Text-to-Image • Updated May 29, 2024 • 1

datasets 0

None public yet