Yixin Huang

yixinhuang48's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 1 day ago

CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation

Paper • 2602.24286 • Published 4 days ago • 62

upvoted an article 2 days ago

view article

Article

Forge: Scalable Agent RL Framework and Algorithm

• 

19 days ago

•

131

liked a model 7 days ago

xgen-universe/Capybara

Any-to-Any • Updated 5 days ago • 217

liked a Space 7 days ago

Running

Reachy

326

Reachy Phone Home

📱

326

Phone focus companion for Reachy Mini

liked a dataset 7 days ago

zai-org/terminal-bench-2-verified

Updated 5 days ago • 6.86k • 58

liked a model 7 days ago

lightx2v/Wan2.1-T2V-1.3B-longcat-step1500

Text-to-Video • Updated 21 days ago • 141 • 6

liked a model 9 days ago

nvidia/personaplex-7b-v1

Audio-to-Audio • Updated 1 day ago • 543k • 2.23k

upvoted an article 9 days ago

view article

Article

Community Evals: Because we're done trusting black-box leaderboards over the community

• 
• 
• +5

28 days ago

•

83

upvoted an article 10 days ago

view article

Article

Introducing NVIDIA Cosmos Policy for Advanced Robot Control

• 

Jan 29

•

44

liked a dataset 13 days ago

tencent/CL-bench

Viewer • Updated 26 days ago • 1.9k • 2.25k • 137

upvoted a paper 13 days ago

Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception

Paper • 2602.11858 • Published 20 days ago • 58

liked a model 20 days ago

zai-org/GLM-5

Text Generation • 754B • Updated 19 days ago • 200k • • 1.7k

upvoted a paper 20 days ago

WorldCompass: Reinforcement Learning for Long-Horizon World Models

Paper • 2602.09022 • Published 22 days ago • 20

upvoted a paper 25 days ago

What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?

Paper • 2512.24497 • Published Dec 30, 2025 • 7

liked a model 25 days ago

stepfun-ai/Step-3.5-Flash

Text Generation • 199B • Updated 19 days ago • 327k • • 673

liked a Space 25 days ago

Running

Featured

39

Step-3.5-Flash Chatbot

🚀

39

Run interactive Streamlit apps directly in your browser

upvoted a paper 25 days ago

Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models

Paper • 2510.05034 • Published Oct 6, 2025 • 51

liked a model 28 days ago

Qwen/Qwen3-Coder-Next

Text Generation • Updated 28 days ago • 953k • • 1.05k

upvoted a changelog 29 days ago

view changelog

Hugging Face Changelog

Find All Your Blog Drafts in One Place

30 days ago

• 40

upvoted an article 29 days ago

view article

Article

Introducing Daggr: Chain apps programmatically, inspect visually

• 
• 
• +3

Jan 29

•

103