Hugging Face's logo
Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

cmhungsteve  authored a paper 17 days ago
4D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillation
cmhungsteve  submitted a paper 17 days ago
4D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillation
cmhungsteve  authored a paper 22 days ago
Zoom-Zero: Reinforced Coarse-to-Fine Video Understanding via Temporal Zoom-in
View all activity

tsungyi 
posted an update about 2 hours ago
view post
Post
16
🎉 Exciting News — NVIDIA Cosmos is celebrating its 1st birthday and has hit 5 MILLION downloads! 🎉

In just one year, the Cosmos ecosystem has grown rapidly:
🧠 Cosmos Reason and Cosmos Predict have surpassed 2 MILLION downloads each on @HuggingFace , topping physical AI leaderboards
🔄 Cosmos Transfer is enabling adaptation across domains and tasks
🔮 Cosmos Cookbook is the go-to hub for recipes from developers and partners like Uber and IntBot.

Thank you to our amazing developer community for making this possible. Here's to pushing the boundaries of world foundation models together!

🧑🏻‍🍳Read the Cosmos Cookbook: https://nvda.ws/4qevli8
📚 Explore Models & Datasets: https://huggingface.co/collections/nvidia/nvidia-cosmos-2
tsungyi 
posted an update 2 days ago
view post
Post
1775
Big news from CES — Cosmos Reason 2 is here — our most advanced reasoning vision-language model for physical AI, now topping the Physical AI Bench leaderboard🏆 shi-labs/physical-ai-bench-leaderboard

What’s new:
- Enhanced physical reasoning & spatio-temporal understanding
- Flexible deployment with 2B & 8B model sizes
- Long-context understanding (up to 256K tokens)
- Object detection with 2D/3D point localizations and trajectory data
- New Cosmos Cookbook Recipes for faster onboarding

Read the full blog 📖 https://huggingface.co/blog/nvidia/nvidia-cosmos-reason-2-brings-advanced-reasoning
Download Cosmos Reason 2 👉 nvidia/Cosmos-Reason2-8B

On top of Cosmos Reason 2, we also rolled out other new updates, including:
- Cosmos Predict 2.5 – Unified Text2World/Image2World/Video2World model for higher-quality synthetic video worlds
- Cosmos Transfer 2.5-2B – Lightweight, high-fidelity world-to-world translation with stronger physics alignment
- NVIDIA GR00T N1.6 – Open robot foundation model for general-purpose robotic learning and control, integrated with Cosmos Reason

Get Started with the Cosmos Cookbook 🧑🏻‍🍳 https://nvda.ws/4qevli8
di-zhang-fdu 
posted an update 7 days ago
di-zhang-fdu 
posted an update 9 days ago
cmhungsteve 
authored a paper 17 days ago
cmhungsteve 
submitted a paper to Daily Papers 17 days ago
cmhungsteve 
authored a paper 22 days ago
di-zhang-fdu 
authored a paper 23 days ago
di-zhang-fdu 
posted an update 23 days ago
view post
Post
340
If linear attention is a system of first-order ordinary differential equations, can we find its exact analytical solution? Can the analytical solution derived from mathematical deduction be used as an attention mechanism? We propose EFLA, which attempts to theoretically eliminate Euler-order integration errors. Please have a look and upvote!

Error-Free Linear Attention is a Free Lunch: Exact Solution from Continuous-Time Dynamics

Error-Free Linear Attention is a Free Lunch: Exact Solution from Continuous-Time Dynamics (2512.12602)
cmhungsteve 
authored a paper about 1 month ago
di-zhang-fdu 
posted an update about 1 month ago
txiong23 
authored a paper about 1 month ago
Fuxiao 
authored 6 papers about 1 month ago
cmhungsteve 
authored a paper about 2 months ago
di-zhang-fdu 
posted an update 2 months ago