Hugging Face's logo
Activity Feed

AI & ML interests

Webhooks are now publicly available on Hugging Face!

Recent Activity
taesiriĀ  submitted a paper about 22 hours ago
Harness-of-Harness: Multi-Day Autonomous Software Development with Continual Improvement
taesiriĀ  submitted a paper about 22 hours ago
UI-Venus-2 Technical Report
taesiriĀ  submitted a paper about 22 hours ago
Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving
View all activity
TuanaĀ 
posted an update 16 days ago
julien-cĀ 
posted an update about 1 month ago
view post
Post
4793
who's working on an NVFP4 version of Kimi-K3?
  • 4 replies
Ā·
MaartenGrĀ 
authored a paper about 1 month ago
osansevieroĀ 
authored a paper about 2 months ago
osansevieroĀ 
submitted a paper to Daily Papers about 2 months ago
raeidsaqurĀ 
authored 3 papers 3 months ago
victorĀ 
posted an update 3 months ago
view post
Post
4788
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·
victorĀ 
posted an update 5 months ago
view post
Post
6283
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·
xianbaoĀ 
submitted a paper to Daily Papers 6 months ago
victorĀ 
submitted a paper to Daily Papers 6 months ago
chansungĀ 
authored a paper 7 months ago
chansungĀ 
submitted a paper to Daily Papers 7 months ago
julien-cĀ 
submitted a paper to Daily Papers 7 months ago
victorĀ 
posted an update 7 months ago
view post
Post
2874
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 9 months ago
view post
Post
3614
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
xianbaoĀ 
authored a paper 10 months ago
nouamanetaziĀ 
posted an update 10 months ago
view post
Post
5142
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
vumichienĀ 
authored a paper 11 months ago