QingyuShi's picture

3 14 5

QingyuShi

QingyuShi

·

Shi-qingyu

AI & ML interests

None yet

Recent Activity

upvoted a paper 3 days ago

Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and Methodology

upvoted a paper 13 days ago

VMoBA: Mixture-of-Block Attention for Video Diffusion Models

updated a model 13 days ago

QingyuShi/Muddit

View all activity

Organizations

authored a paper about 1 month ago

Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model

Paper • 2505.23606 • Published May 29 • 14

authored a paper 2 months ago

On Path to Multimodal Generalist: General-Level and General-Bench

Paper • 2505.04620 • Published May 7 • 82

authored 3 papers 3 months ago

RelationBooth: Towards Relation-Aware Customized Object Generation

Paper • 2410.23280 • Published Oct 30, 2024 • 1

An Empirical Study of GPT-4o Image Generation Capabilities

Paper • 2504.05979 • Published Apr 8 • 63

Decouple and Track: Benchmarking and Improving Video Diffusion Transformers for Motion Transfer

Paper • 2503.17350 • Published Mar 21 • 1