Xiaoliang Dai

7

Papers

264

Total Citations

Papers (7)

EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything

LEGO: Learning EGOcentric Action Frame Generation via Visual Instruction Tuning

LinGen: Towards High-Resolution Minute-Length Text-to-Video Generation with Linear Computational Complexity

Unleashing In-context Learning of Autoregressive Models for Few-shot Image Manipulation

Cache Me if You Can: Accelerating Diffusion Models through Block Caching

Layout-Agnostic Scene Text Image Synthesis with Diffusion Models

Movie Weaver: Tuning-Free Multi-Concept Video Personalization with Anchored Prompts