2 75 132

Wenhao Chai

wchai

http://rese1f.github.io

AI & ML interests

computer vision, artificial intelligence

Recent Activity

upvoted a paper 3 days ago

WORLDMEM: Long-term Consistent World Simulation with Memory

upvoted a paper 7 days ago

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

liked a dataset 9 days ago

nyu-visionx/CV-Bench

View all activity

Organizations

wchai's activity

upvoted a paper 3 days ago

WORLDMEM: Long-term Consistent World Simulation with Memory

Paper • 2504.12369 • Published 5 days ago • 29

upvoted a paper 7 days ago

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

Paper • 2504.08736 • Published 10 days ago • 46

liked a dataset 9 days ago

nyu-visionx/CV-Bench

Viewer • Updated 20 days ago • 5.28k • 5.48k • 30

upvoted 2 papers 10 days ago

HoloPart: Generative 3D Part Amodal Segmentation

Paper • 2504.07943 • Published 11 days ago • 27

DeepSeek-R1 Thoughtology: Let's <think> about LLM Reasoning

Paper • 2504.07128 • Published 20 days ago • 80

liked a model 11 days ago

agentica-org/DeepCoder-14B-Preview

Text Generation • Updated 12 days ago • 33.9k • 590

upvoted a paper 11 days ago

DDT: Decoupled Diffusion Transformer

Paper • 2504.05741 • Published 13 days ago • 71

reacted to AdinaY's post with 🔥 11 days ago

Post

2686

Moonshot AI 月之暗面 🌛 @Kimi_Moonshotis just dropped an MoE VLM and an MoE Reasoning VLM on the hub!!

Model:https://huggingface.co/collections/moonshotai/kimi-vl-a3b-67f67b6ac91d3b03d382dd85

✨3B with MIT license
✨Long context windows up to 128K
✨Strong multimodal reasoning (36.8% on MathVision, on par with 10x larger models) and agent skills (34.5% on ScreenSpot-Pro)