2 73 130

Wenhao Chai

wchai

http://rese1f.github.io

AI & ML interests

computer vision, artificial intelligence

Recent Activity

upvoted a paper about 10 hours ago

HoloPart: Generative 3D Part Amodal Segmentation

upvoted a paper about 10 hours ago

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

liked a model about 20 hours ago

agentica-org/DeepCoder-14B-Preview

View all activity

Organizations

wchai's activity

upvoted 2 papers about 10 hours ago

HoloPart: Generative 3D Part Amodal Segmentation

Paper • 2504.07943 • Published about 20 hours ago • 21

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

Paper • 2504.07128 • Published 10 days ago • 23

upvoted a paper 1 day ago

DDT: Decoupled Diffusion Transformer

Paper • 2504.05741 • Published 3 days ago • 57

upvoted a collection 2 days ago

Kimi-VL-A3B

Collection

Moonshot's efficient MoE VLMs, exceptional on agent, long-context, and thinking • 4 items • Updated about 7 hours ago • 52

upvoted 3 papers 2 days ago

OmniSVG: A Unified Scalable Vector Graphics Generation Model

Paper • 2504.06263 • Published 3 days ago • 121

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

Paper • 2504.02160 • Published 9 days ago • 30

An Empirical Study of GPT-4o Image Generation Capabilities

Paper • 2504.05979 • Published 3 days ago • 56

upvoted a collection 6 days ago

Science-T2I

Collection

Addressing Scientific Illusions in Image Synthesis • 9 items • Updated 7 days ago • 2

upvoted a paper 8 days ago

Scaling Language-Free Visual Representation Learning

Paper • 2504.01017 • Published 10 days ago • 25

upvoted a paper 10 days ago

MoCha: Towards Movie-Grade Talking Character Synthesis

Paper • 2503.23307 • Published 12 days ago • 116

upvoted a collection 16 days ago

Qwen2.5-Omni

Collection

End-to-End Omni (text, audio, image, video, and natural speech interaction) model based Qwen2.5 • 3 items • Updated 15 days ago • 83

upvoted a paper 18 days ago

Modifying Large Language Model Post-Training for Diverse Creative Writing

Paper • 2503.17126 • Published 21 days ago • 34

upvoted a paper 22 days ago

TULIP: Towards Unified Language-Image Pretraining

Paper • 2503.15485 • Published 23 days ago • 44

upvoted 2 papers 23 days ago

DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Paper • 2503.14476 • Published 24 days ago • 116

RWKV-7 "Goose" with Expressive Dynamic State Evolution

Paper • 2503.14456 • Published 24 days ago • 137

upvoted a paper 25 days ago

Cockatiel: Ensembling Synthetic and Human Preferenced Training for Detailed Video Caption

Paper • 2503.09279 • Published about 1 month ago • 5

upvoted 2 papers 28 days ago

Autoregressive Image Generation with Randomized Parallel Decoding

Paper • 2503.10568 • Published 29 days ago • 8

Transformers without Normalization

Paper • 2503.10622 • Published 29 days ago • 155

upvoted a paper about 1 month ago

MagicInfinite: Generating Infinite Talking Videos with Your Words and Voice

Paper • 2503.05978 • Published Mar 7 • 35