Hugging Face's logo
Activity Feed

AI & ML interests

None defined yet.

Recent Activity
nielsrย  submitted a paper 1 day ago
Gemini Embedding 2: A Native Multimodal Embedding Model from Gemini
nielsrย  submitted a paper 7 days ago
Stable Audio 3
DongfuJiangย  authored a paper 14 days ago
Watch Before You Answer: Learning from Visually Grounded Post-Training
View all activity
victorย 
posted an update 2 days ago
view post
Post
279
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
johkoย 
posted an update 7 days ago
view post
Post
107
One prompt, three answers - which model is from where?

johko/llm-blind-date

I built a little demo where you give three models (Apertus, Llama, Qwen3) the same prompt and in the end you have to guess which is which just based on their answers.

GIve it a try! ;)
fffiloniย 
posted an update 10 days ago
view post
Post
3241
I built HF Radio on Hugging Face Spaces ๐Ÿ“ป
fffiloni/HF-Radio

A live community radio for AI-generated songs, powered by tracks created with ACE-Step.

You can tune in, discover community-made songs in many languages, vote on what sounds good, and mark your real favorites as Bangers.

The more people listen, vote, and create, the better the station gets.

Under the hood, it connects a few Hugging Face pieces together:

Spaces for the live app, HF buckets for community tracks, OAuth for signed-in listeners, server-side streaming with ffmpeg, hourly playlist refreshes, moderation, jingles, and community feedback loops.

Itโ€™s not just a playlist.

Itโ€™s a shared taste experiment:
new songs get a shot every hour, and the community helps decide what deserves another spin.

Come listen.
Find weird gems.
Support the Bangers.
Shape the radio.

โ€”> fffiloni/HF-Radio
Tonicย 
posted an update 14 days ago
view post
Post
2721
๐Ÿ™‹๐Ÿปโ€โ™‚๏ธ Hey there folks ,

Turns out : if we predict ๐ŸŒ earth we can save a lot of time looking for interesting things and less time looking at things that we expect to see.

Sentinel-2 imagery ๐Ÿ›ฐ๏ธbasically takes a long time to download towards earth. so our "near real time" systems are quite far from that in practical terms.

meanwhile , if we "predict" what we will see , based on what we do see , we can send down much less data in a timely way , and prioritize ๐Ÿ“กearth-bound response .

I'm talking about illegal fishing , logging , mining or building in nature reserves , the more of that we predict early the more we're able to stop it on time.

At least that's the concept !

check out the blog : https://huggingface.co/blog/Tonic/save-patagonia-by-predicting-earth


- Collection: https://huggingface.co/collections/NuTonic/earth-observation-with-temporal-and-general-understanding
- Code: https://github.com/Josephrp/Nutonic
- Dataset: NuTonic/sat-vl-sft-training-ready-v1
- Model: NuTonic/lspace
- Training: NuTonic/lspace-trackio
- Evals: NuTonic/Patagonia_Eval
  • 2 replies
ยท
DongfuJiangย 
authored 4 papers 14 days ago
fffiloniย 
posted an update 15 days ago
view post
Post
480
Great technical guide by Nico Martin on the Hugging Face blog, showing how to use Transformers.js inside a Chrome extension and run ONNX models from the Hub locally with WebGPU inside a Manifest V3 extension.

The interesting part: this is not just a chatbot in a side panel.

The article walks through the architecture behind a browser agent that can read open tabs, query webpages, search history, and highlight elements directly on the page โ€” with models downloaded from the Hugging Face Hub, cached under the extension origin, and executed locally instead of being called through a remote API for every prompt.

A strong blueprint for building local-first web copilots, reading assistants, and AI-powered browsing workflows.

Article: https://huggingface.co/blog/transformersjs-chrome-extension
fffiloniย 
posted an update 17 days ago
view post
Post
330
Iโ€™ve been reading โ€œWhat if AI systems werenโ€™t chatbots?โ€
What if AI systems weren't chatbots? (2605.07896) ๐Ÿ‘€

The paper asks a simple but important question: what if the chatbot interface is not just a neutral wrapper around AI models, but part of the problem?

A chatbot can make a system feel more capable, more certain, and more โ€œhumanโ€ than it really is. That matters, because interfaces shape how we trust, use, and delegate to AI systems.

When everything becomes: ask โ†’ answer
we can lose sight of the actual workflow:
- parameters
- alternatives
- uncertainty
- intermediate steps
- failure modes
- human control

For creative AI especially โ€” image, video, editing, animation โ€” Iโ€™m not sure โ€œchatโ€ should always be the default interface.

Sometimes we need a conversation.
But often we need a canvas, a timeline, sliders, masks, previews, comparisons, and visible pipelines.

This is also why I find many open ML demos interesting: Spaces, Gradio apps, visual tools, small focused interfaces.

They often explore another direction โ€” not just better assistants, but better tools. ๐Ÿค—
  • 2 replies
ยท
Prabhjotschughย 
authored a paper 18 days ago
Tonicย 
posted an update about 1 month ago
view post
Post
4262
๐Ÿ™‹๐Ÿปโ€โ™‚๏ธ Hey there folks,

since everyone liked my previous announcement post ( https://huggingface.co/posts/Tonic/338509028435394 ) so much , i'm back with more high quality proceedural datasets in the Geospacial domain for SFT training !

Check this one out :
NuTonic/sat-bbox-metadata-sft-v1

the goal is to be able to train vision models on multiple images for remote sensing analysis with one shot .

hope you like it ! ๐Ÿš€
  • 2 replies
ยท
fffiloniย 
posted an update about 1 month ago
Tonicย 
posted an update about 1 month ago
view post
Post
3620
๐Ÿ™‹๐Ÿปโ€โ™‚๏ธ Hey there folks ,

I'm sharing huggingface's largest dataset of annotated statelite images today.

check it out here : NuTonic/sat-image-boundingbox-sft-full

I hope you like it , the idea is to be able to use this with small vision models ๐Ÿš€
fffiloniย 
posted an update about 1 month ago
view post
Post
1818
๐Ÿš€ RB-Modulation is back on Hugging Face Spaces!

This is an older project that recently broke due to dependency changes, but itโ€™s now fixed and running again โœ…

๐Ÿ‘‰ Whatโ€™s fixed:
- GroundingDINO & LangSAM installation
- compatibility with recent environments
- GPU inference running smoothly again

๐Ÿ‘‰ Try it here:
fffiloni/RB-Modulation

Feel free to give it a try again โ€” feedback welcome!
victorย 
posted an update about 1 month ago
view post
Post
6085
Want to share my enthusiasm for zai-org/GLM-5.1 here too ๐Ÿ”ฅ

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-ai๐Ÿš€๐Ÿš€
  • 5 replies
ยท
fffiloniย 
posted an update about 2 months ago
view post
Post
3181
โœจ PASD Magnify is back on Hugging Face Spaces

fffiloni/PASD

PASD isnโ€™t recent, but still delivers strong results โ€” worth restoring rather than replacing.

Getting it to run again wasnโ€™t a simple dependency issue.
It relied on parts of diffusers that no longer exist, while moving to Gradio 6 forced a much newer HF stack โ€” and I couldnโ€™t modify the original source directly.

Recreating the old environment wasnโ€™t practical.
So I patched the downloaded code at runtime before import and made it compatible with todayโ€™s stack.

That ended up being the only approach that held without forking or freezing everything to outdated versions.

If youโ€™ve used it before (or are curious), feel free to give it another try.
fffiloniย 
posted an update about 2 months ago
view post
Post
2872
โœ… Back up and running!

My TIGER app is now fully working again, with fixes and full compatibility with Gradio 6 ๐Ÿš€

It lets you:
- ๐ŸŽ™๏ธ Separate multiple speakers from an audio file
- ๐ŸŽฌ Extract each speaker directly from a video
- ๐ŸŽง Split audio into dialog, music, and sound effects (DnR)
- ๐ŸŽฅ Apply DnR separation directly on videos

All powered by lightweight TIGER models for fast and efficient speech separation.

Try it here ๐Ÿ‘‰ fffiloni/TIGER-audio-extraction
fffiloniย 
posted an update about 2 months ago
view post
Post
2290
AniDoc is back ๐ŸŽ‰

Iโ€™ve fixed the Space and brought it back to life:
- โœ… Working again after being broken for a while
- โœ… Updated to Gradio 6
- โœ… Compatible with ZeroGPU
- โœ… Output videos now preserve original resolution and FPS

I also added advanced controls so you can experiment more (tracking, seed, motion, sketch).

Try it here: fffiloni/AniDoc
1aurentย 
authored a paper about 2 months ago