Hugging Face's logo
Activity Feed

AI & ML interests

Webhooks are now publicly available on Hugging Face!

Recent Activity
taesiriĀ  submitted a paper 3 days ago
Robostral Navigate
taesiriĀ  submitted a paper 3 days ago
Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction
taesiriĀ  submitted a paper 3 days ago
NVIDIA-labs OO Agents: Native Python Object-Oriented Agents
View all activity
satpalsrĀ 
posted an update 5 days ago
view post
Post
1906
We just released an end-to-end system that sets a new state of the art in egocentric video understanding, generating fine-grained action labels from raw robot and human videos while outperforming Gemini, GPT, Claude, and other leading models.

https://x.com/fpv_labs/status/2079600323883331880
MaartenGrĀ 
authored a paper 6 days ago
osansevieroĀ 
authored a paper 17 days ago
osansevieroĀ 
submitted a paper to Daily Papers 19 days ago
victorĀ 
posted an update 2 months ago
view post
Post
2898
Sharing how I built the LongCat-Video-Avatar 1.5 Space (+500k views on X) in one agent session. Gave a coding agent its own AI lab on ZeroGPU, framed the goal, walked away. It designed, deployed, tested against the live API, fixed, shipped.

Full recipe with the copy-paste prompt: https://huggingface.co/blog/victor/building-zerogpu-spaces-autonomously
  • 1 reply
Ā·
satpalsrĀ 
submitted a paper to Daily Papers 2 months ago
satpalsrĀ 
authored a paper 2 months ago
satpalsrĀ 
posted an update 2 months ago
view post
Post
210
We're open-sourcing our infra with 10M+ frames of dataset!

We're releasing Stera, an open-source infra that turns an off-the-shelf device in your pocket into a high-fidelity multimodal data pipeline. It's built around four layers. Capture ā†’ Process ā†’ Evaluate ā†’ Export.

Stera Capture removes the need for bespoke/gated hardware and runs on an off-the-shelf iPhone. It fuses together synchronized RGB, IMU, Lidar-guided depth, and 6-DoF pose out of the box from ARKit and exports them to a raw MCAP file.

Dataset: fpvlabs/stera-10m
Launch Details: https://x.com/fpv_labs/status/2055262652033908832
victorĀ 
posted an update 3 months ago
view post
Post
6223
Want to share my enthusiasm for zai-org/GLM-5.1 here too šŸ”„

I think we have it: our open source Claude Code = GLM-5.1 + Pi (https://pi.dev/) - Built a Three.js racing game to eval and it's extremely impressive. Thoughts:

- One-shot car physics with real drift mechanics (this is hard)

- My fav part: Awesome at self iterating (with no vision!) created 20+ Bun.WebView debugging tools to drive the car programmatically and read game state. Proved a winding bug with vector math without ever seeing the screen

- 531-line racing AI in a single write: 4 personalities, curvature map, racing lines, tactical drifting. Built telemetry tools to compare player vs AI speed curves and data-tuned parameters

- All assets from scratch: 3D models, procedural textures, sky shader, engine sounds, spatial AI audio!

- Can do hard math: proved road normals pointed DOWN via vector cross products, computed track curvature normalized by arc length to tune AI cornering speed

You are going to hear about this model a lot in the next months - open source let's go - and thanks z-aišŸš€šŸš€
  • 5 replies
Ā·
satpalsrĀ 
posted an update 4 months ago
view post
Post
192
OpenAI is hiring for SLAM Engineers!
And open-source shouldn't lag behind.

It's pretty hard and necessary problem required to be solved for bringing generalisable robots in real-world.

We are pushing out first deep down & will be open-sourcing stuff in the next releases. Hope everyone is ready! Cheers to HF & more hugs.

Find us at https://x.com/fpv_labs/status/2042585804162371713
xianbaoĀ 
submitted a paper to Daily Papers 5 months ago
victorĀ 
submitted a paper to Daily Papers 5 months ago
chansungĀ 
authored a paper 5 months ago
chansungĀ 
submitted a paper to Daily Papers 5 months ago
julien-cĀ 
submitted a paper to Daily Papers 6 months ago
victorĀ 
posted an update 6 months ago
view post
Post
2848
Interesting article: use Claude Code to help open models write CUDA kernels (for eg) by turning CC traces into Skills. They made a library out of it šŸ‘€

https://huggingface.co/blog/upskill
victorĀ 
posted an update 7 months ago
view post
Post
3586
Nvidia is on a roll lately. Nemotron 3 Nano is my new fav local model, but here's the real flex: they published the entire evaluation setup. Configs, prompts, logs, all of it. This is how you do open models šŸ”„

https://huggingface.co/blog/nvidia/nemotron-3-nano-evaluation-recipe
mrfakenameĀ 
posted an update 8 months ago
view post
Post
28671
Excited to share that I've joined the Hugging Face Fellows program! šŸ¤—

Looking forward to contributing to & working more closely with the open-source ecosystem - huge thanks to everyone who's supported me on this journey! šŸš€
xianbaoĀ 
authored a paper 9 months ago
nouamanetaziĀ 
posted an update 9 months ago
view post
Post
5042
After training š’š¦šØš„š‹šŒšŸ‘ on šŸ‘šŸ–šŸ’ š‡šŸšŸŽšŸŽš¬ for nearly a month, I've come to realize something most people overlook: š¢š§šŸš«ššš¬š­š«š®šœš­š®š«šž š¢š¬ š­š”šž š¦ššš¤šž-šØš«-š›š«šžššš¤ šŸšššœš­šØš« š¢š§ š‹š‹šŒ š­š«ššš¢š§š¢š§š . šŸ”„

Everyone talks about model architecture and data quality. And yes, those matter immensely. But here's what nobody tells you: when your training run fails at 2 AM because of mysterious šš‚š‚š‹ šžš«š«šØš«š¬, or when your expensive GPU cluster is running at šŸ”šŸŽ% šžšŸšŸš¢šœš¢šžš§šœš², the problem isn't your model. It's most probably a š¦š¢š¬š®š¬šž šØšŸ š­š”šž š”ššš«šš°ššš«šž. šŸ› ļø

Questions that seemed simple but had no clear answers: Why is šŒšØš„ š­š«ššš¢š§š¢š§š  š¬š„šØš°šžš« š­š”ššš§ ššžš§š¬šž š¦šØššžš„š¬? Which šš‚š‚š‹ šŸš„ššš š¬ should we actually set? How often should we checkpoint without killing throughput?

That's why we built š“š”šž š’š¦šØš„ š“š«ššš¢š§š¢š§š  šš„ššš²š›šØšØš¤ šŸ“–: a complete guide covering everything from model architecture and data curation to the SmolLM3 training marathon, post-training techniques, and crucially, the š¢š§šŸš«ššš¬š­š«š®šœš­š®š«šž š„ššš²šžš« that most teams get wrong.

We validated real vs theoretical bandwidth across the entire stack: š‡ššŒšŸ‘ š”š¢š­š­š¢š§š  šŸ‘ š“š/š¬, šš•š‹š¢š§š¤ šŸ’.šŸŽ š«šžšššœš”š¢š§š  šŸ•šŸ–šŸ” š†š/š¬, šš‚šˆšž š†šžš§šŸ’ ššš­ šŸšŸ’.šŸ š†š/š¬. Then we ran collective operations across šŸšŸšŸ– š†šš”š¬ (16 nodes, 8xH100s each) and measured how performance degrades at scale: all-reduce drops from šŸ’šŸ–šŸŽ š†š/š¬ on a single node to šŸ‘šŸšŸŽ-šŸ‘šŸ“šŸŽ š†š/š¬ across 16 nodes.

If you've ever wondered why your training runs are slower than they should be, or you're planning to scale up and want to avoid expensive mistakes, this guide might save you weeks of debugging.

š“š”šž š’š¦šØš„ š“š«ššš¢š§š¢š§š  šš„ššš²š›šØšØš¤: https://lnkd.in/e5MKXUHS

Shared with ā¤ļø by the HuggingFace team