1 14 1

Donghao Zhou

donghao-zhou

https://correr-zhou.github.io

Correr-Zhou

AI & ML interests

Generative AI

Recent Activity

upvoted a paper 2 days ago

Dynamic Concepts Personalization from Single Videos

upvoted a paper 2 days ago

SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features

upvoted a paper 7 days ago

MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency

View all activity

Organizations

None yet

donghao-zhou's activity

upvoted 2 papers 2 days ago

Dynamic Concepts Personalization from Single Videos

Paper • 2502.14844 • Published 3 days ago • 13

SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features

Paper • 2502.14786 • Published 3 days ago • 101

upvoted a paper 7 days ago

MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency

Paper • 2502.09621 • Published 10 days ago • 26

upvoted a paper 12 days ago

Magic 1-For-1: Generating One Minute Video Clips within One Minute

Paper • 2502.07701 • Published 12 days ago • 32

upvoted a paper 15 days ago

ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features

Paper • 2502.04320 • Published 17 days ago • 33

upvoted 2 papers 18 days ago

Generating Multi-Image Synthetic Data for Text-to-Image Customization

Paper • 2502.01720 • Published 20 days ago • 6

VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models

Paper • 2502.02492 • Published 19 days ago • 56

upvoted an article 19 days ago

Article

Open-source DeepResearch – Freeing our search agents

20 days ago

• 1.08k

upvoted a paper 24 days ago

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Paper • 2501.16411 • Published 27 days ago • 18

upvoted a paper 30 days ago

Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step

Paper • 2501.13926 • Published Jan 23 • 37

upvoted a paper about 1 month ago

ConceptMaster: Multi-Concept Video Customization on Diffusion Transformer Models Without Test-Time Tuning

Paper • 2501.04698 • Published Jan 8 • 14

upvoted a paper 3 months ago

HumanEdit: A High-Quality Human-Rewarded Dataset for Instruction-based Image Editing

Paper • 2412.04280 • Published Dec 5, 2024 • 14

upvoted 2 papers 4 months ago

MagicTailor: Component-Controllable Personalization in Text-to-Image Diffusion Models

Paper • 2410.13370 • Published Oct 17, 2024 • 37

Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis

Paper • 2410.08261 • Published Oct 10, 2024 • 50