3 81 134

Wenhao Chai

wchai

http://rese1f.github.io

AI & ML interests

computer vision, artificial intelligence

Recent Activity

upvoted a paper 2 days ago

Flow-GRPO: Training Flow Matching Models via Online RL

liked a dataset 5 days ago

Enigma-AI/multiplayer-racing-full-res

upvoted a paper 8 days ago

Practical Efficiency of Muon for Pretraining

View all activity

Organizations

wchai's activity

upvoted a paper 2 days ago

Flow-GRPO: Training Flow Matching Models via Online RL

Paper • 2505.05470 • Published 6 days ago • 65

upvoted 2 papers 8 days ago

Practical Efficiency of Muon for Pretraining

Paper • 2505.02222 • Published 9 days ago • 36

TEMPURA: Temporal Event Masked Prediction and Understanding for Reasoning in Action

Paper • 2505.01583 • Published 11 days ago • 9

upvoted a paper 10 days ago

Science-T2I: Addressing Scientific Illusions in Image Synthesis

Paper • 2504.13129 • Published 27 days ago • 3

upvoted a paper 19 days ago

Step1X-Edit: A Practical Framework for General Image Editing

Paper • 2504.17761 • Published 20 days ago • 88

upvoted a paper 23 days ago

It's All Connected: A Journey Through Test-Time Memorization, Attentional Bias, Retention, and Online Optimization

Paper • 2504.13173 • Published 27 days ago • 18

upvoted a paper 26 days ago

WORLDMEM: Long-term Consistent World Simulation with Memory

Paper • 2504.12369 • Published 28 days ago • 32

upvoted 4 papers about 1 month ago

GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation

Paper • 2504.08736 • Published Apr 11 • 47

upvoted a collection about 1 month ago

Kimi-VL-A3B

Collection

Moonshot's efficient MoE VLMs, exceptional on agent, long-context, and thinking • 6 items • Updated Apr 12 • 65

upvoted 3 papers about 1 month ago

OmniSVG: A Unified Scalable Vector Graphics Generation Model

Paper • 2504.06263 • Published Apr 8 • 160

Less-to-More Generalization: Unlocking More Controllability by In-Context Generation

Paper • 2504.02160 • Published Apr 2 • 37

An Empirical Study of GPT-4o Image Generation Capabilities

Paper • 2504.05979 • Published Apr 8 • 62

upvoted a collection about 1 month ago

Science-T2I

Collection

Addressing Scientific Illusions in Image Synthesis • 10 items • Updated 17 days ago • 4

upvoted 2 papers about 1 month ago

Scaling Language-Free Visual Representation Learning

Paper • 2504.01017 • Published Apr 1 • 29

MoCha: Towards Movie-Grade Talking Character Synthesis

Paper • 2503.23307 • Published Mar 30 • 133

upvoted a collection about 2 months ago

Qwen2.5-Omni

Collection

End-to-End Omni (text, audio, image, video, and natural speech interaction) model based Qwen2.5 • 5 items • Updated 14 days ago • 110

upvoted a paper about 2 months ago

Modifying Large Language Model Post-Training for Diverse Creative Writing

Paper • 2503.17126 • Published Mar 21 • 36