Hugging Face's logo
Activity Feed

AI & ML interests

None defined yet.

Recent Activity
DongfuJiang  authored a paper 13 days ago
Watch Before You Answer: Learning from Visually Grounded Post-Training
DongfuJiang  authored a paper 13 days ago
ClawBench: Can AI Agents Complete Everyday Online Tasks?
DongfuJiang  authored a paper 13 days ago
Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
View all activity
Nymbo 
posted an update about 10 hours ago
view post
Post
47
I made a skill to autonomously mass download entire music discographies from any platform. You give the agent a long list of artists and send the prompt as a /goal. The agent develops a list of all mainline albums/projects of each artist, manually checks each playlist to verify the tracks beings curated, then downloads it all in efficient batches using yt-dlp.

I added 37,000 new tracks to my local library overnight. Check it out here: https://github.com/Nymbo/Music-Downloader-Skill
victor 
posted an update about 11 hours ago
johko 
posted an update 6 days ago
view post
Post
98
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! ;)
Tonic 
posted an update 13 days ago
view post
Post
2683
🙋🏻‍♂️ Hey there folks ,

Turns out : if we predict 🌏 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 🛰️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 📡earth-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
·
DongfuJiang 
authored 4 papers 13 days ago
Prabhjotschugh 
authored a paper 16 days ago
Tonic 
posted an update 29 days ago
view post
Post
4249
🙋🏻‍♂️ 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 ! 🚀
  • 2 replies
·
Tonic 
posted an update about 1 month ago
view post
Post
3611
🙋🏻‍♂️ 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 🚀
victor 
posted an update about 1 month ago
view post
Post
6080
Want to share my enthusiasm for zai-org/GLM-5.1 here too 🔥

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-ai🚀🚀
  • 5 replies
·
Severian 
posted an update 2 months ago
view post
Post
4465
I’ve been working on a new mathematical approach to real-time video compositing and background removal, and I wanted to share a live demo.

Traditionally, real-time keyers either use 3D color-space bounding boxes (which struggle with semi-transparent hair and motion blur) or heavy Machine Learning models (which require massive GPU compute and often suffer from temporal "jitter" on the edges).

I wanted to see if I could solve this using purely deterministic math so it could run client-side in a standard browser.

The engine uses a custom mathematical framework I call CMT SRL SEFA. Instead of looking at raw color values or guessing semantics like an AI, it treats the video feed as complex-encoded sequences. It uses harmonic frequencies to map phase geometry and applies a "Stability Cost Function" to find the global minimum stability. In short: it isolates the foreground from the background by measuring signal complexity and structural contradictions.

Give it a try using your own messy plates and such. As I am not a VFX artist, I am curious to hear thoughts and what should be improved upon and made better

https://severian-cmt-sefa-realtime-vfx-keyer.hf.space/
  • 2 replies
·
DongfuJiang 
authored 3 papers 2 months ago
Nymbo 
posted an update 2 months ago
view post
Post
7169
We should really have a release date range slider on the /models page. Tired of "trending/most downloaded" being the best way to sort and still seeing models from 2023 on the first page just because they're embedded in enterprise pipelines and get downloaded repeatedly. "Recently Created/Recently Updated" don't solve the discovery problem considering the amount of noise to sift through.

Slight caveat: Trending actually does have some recency bias, but it's not strong/precise enough.
  • 3 replies
·
xianbao 
submitted a paper to Daily Papers 2 months ago
GeorgeBredis 
authored a paper 3 months ago
GeorgeBredis 
submitted a paper to Daily Papers 3 months ago