Hugging Face's logo
Activity Feed

AI & ML interests

None defined yet.

Recent Activity
nielsr  submitted a paper 4 days ago
A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens
nielsr  submitted a paper 10 days ago
MDPBench: A Benchmark for Multilingual Document Parsing in Real-World Scenarios
1aurent  authored a paper 14 days ago
Voxtral TTS
View all activity
Nymbo 
posted an update about 12 hours ago
view post
Post
79
Gemma-4-26B-A4B refusing to believe that web search results are real and is convinced that all search results are simulated or hallucinations. It also thinks that I, the user, might be simulated or hallucinating.

Just one more step till AGI at home 😎
fffiloni 
posted an update 3 days ago
view post
Post
2768
✨ PASD Magnify is back on Hugging Face Spaces

fffiloni/PASD

PASD isn’t recent, but still delivers strong results — worth restoring rather than replacing.

Getting it to run again wasn’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 — and I couldn’t modify the original source directly.

Recreating the old environment wasn’t practical.
So I patched the downloaded code at runtime before import and made it compatible with today’s stack.

That ended up being the only approach that held without forking or freezing everything to outdated versions.

If you’ve used it before (or are curious), feel free to give it another try.
fffiloni 
posted an update 12 days ago
view post
Post
2834
✅ Back up and running!

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

It lets you:
- 🎙️ Separate multiple speakers from an audio file
- 🎬 Extract each speaker directly from a video
- 🎧 Split audio into dialog, music, and sound effects (DnR)
- 🎥 Apply DnR separation directly on videos

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

Try it here 👉 fffiloni/TIGER-audio-extraction
fffiloni 
posted an update 13 days ago
view post
Post
2228
AniDoc is back 🎉

I’ve fixed the Space and brought it back to life:
- ✅ Working again after being broken for a while
- ✅ Updated to Gradio 6
- ✅ Compatible with ZeroGPU
- ✅ 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
Severian 
posted an update 19 days ago
view post
Post
4413
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://huggingface.co/proxy/severian-cmt-sefa-realtime-vfx-keyer.hf.space/
  • 2 replies
·
DongfuJiang 
authored 3 papers 19 days ago
fffiloni 
posted an update 26 days ago
view post
Post
4113
I brought DALL·E mini back to life 🤖🎨

You can try it here:
fffiloni/dalle-mini-reboot

And I also built a batch version using Hugging Face Jobs (up to 50 images per prompt):
fffiloni/dalle-mini-via-jobs

The goal was to stay close to the original JAX/Flax pipeline, while integrating it with modern tooling (Gradio + Jobs).

It ended up being a fun way to revisit this model — still weird, still fun 😄
  • 3 replies
·
Nymbo 
posted an update 29 days ago
view post
Post
6538
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
·
fffiloni 
posted an update about 1 month ago
view post
Post
490
A clearer demo for TADA (now multilingual) 🔊🌍

I improved the public demo for TADA — a generative framework for speech modeling via text–acoustic dual alignment.

TADA models speech as a joint sequence of text tokens and acoustic tokens, using a transformer backbone to keep text and audio synchronized during generation.

The original demo already exposed these mechanisms, but the workflow made the pipeline hard to understand.

This updated demo makes the process clearer:

• load the model
• prepare a reference voice (optionally with transcript or Whisper auto-transcription)
• generate speech conditioned on that reference

It also adds multilingual support.

Presets are included for a few languages, but the model supports more:

English, French, Spanish, German, Arabic, Mandarin Chinese, Italian, Japanese, Polish, Portuguese

Feel free to try different voices, accents, or languages and see how the alignment behaves.

👉 fffiloni/tada-dual-alignment-tts-demo

Paper
TADA: A Generative Framework for Speech Modeling via Text-Acoustic Dual Alignment (2602.23068)
GeorgeBredis 
authored a paper about 1 month ago
GeorgeBredis 
submitted a paper to Daily Papers about 1 month ago
victor 
submitted a paper to Daily Papers about 2 months ago
mariagrandury 
authored 2 papers about 2 months ago
victor 
posted an update 2 months ago
view post
Post
2663
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 👀

https://huggingface.co/blog/upskill
IlyasMoutawwakil 
posted an update 3 months ago
view post
Post
3176
Transformers v5 just landed! 🚀
It significantly unifies and reduces modeling code across architectures, while opening the door to a whole new class of performance optimizations.

My favorite new feature? 🤔
The new dynamic weight loader + converter. Here’s why 👇

Over the last few months, the core Transformers maintainers built an incredibly fast weight loader, capable of converting tensors on the fly while loading them in parallel threads. This means we’re no longer constrained by how parameters are laid out inside the safetensors weight files.

In practice, this unlocks two big things:
- Much more modular modeling code. You can now clearly see how architectures build on top of each other (DeepSeek v2 → v3, Qwen v2 → v3 → MoE, etc.). This makes shared bottlenecks obvious and lets us optimize the right building blocks once, for all model families.
- Performance optimizations beyond what torch.compile can do alone. torch.compile operates on the computation graph, but it can’t change parameter layouts. With the new loader, we can restructure weights at load time: fusing MoE expert projections, merging attention QKV projections, and enabling more compute-dense kernels that simply weren’t possible before.

Personally, I'm honored to have contributed in this direction, including the work on optimizing MoE implementations and making modeling code more torch-exportable, so these optimizations can be ported cleanly across runtimes.

Overall, Transformers v5 is a strong signal of where the community and industry are converging: Modularity and Performance, without sacrificing Flexibility.

Transformers v5 makes its signature from_pretrained an entrypoint where you can mix and match:
- Parallelism
- Quantization
- Custom kernels
- Flash/Paged attention
- Continuous batching
- ...

Kudos to everyone involved! I highly recommend the:
Release notes: https://github.com/huggingface/transformers/releases/tag/v5.0.0
Blog post: https://huggingface.co/blog/transformers-v5
  • 3 replies
·
IlyasMoutawwakil 
posted an update 3 months ago
view post
Post
2439
After 2 months of refinement, I'm happy to announce that a lot of Transformers' modeling code is now significantly more torch-compile & export-friendly 🔥

Why it had to be done 👇
PyTorch's Dynamo compiler is increasingly becoming the default interoperability layer for ML systems. Anything that relies on torch.export or torch.compile, from model optimization to cross-framework integrations, benefits directly when models can be captured as a single dynamo-traced graph !

Transformers models are now easier to:
⚙️ Compile end-to-end with torch.compile backends
📦 Export reliably via torch.export and torch.onnx.export
🚀 Deploy to ONNX / ONNX Runtime, Intel Corporation's OpenVINO, NVIDIA AutoDeploy (TRT-LLM), AMD's Quark, Meta's Executorch and more hardware-specific runtimes.

This work aims at unblocking entire TorchDynamo-based toolchains that rely on exporting Transformers across runtimes and accelerators.

We are doubling down on Transformers commitment to be a first-class citizen of the PyTorch ecosystem, more exportable, more optimizable, and easier to deploy everywhere.

There are definitely some edge-cases that we still haven't addressed so don't hesitate to try compiling / exporting your favorite transformers and to open issues / PRs.

PR in the comments ! More updates coming coming soon !
  • 1 reply
·
Nymbo 
posted an update 3 months ago
view post
Post
2793
Genuine recommendation: You should really use this AutoHotKey macro. Save the file as macros.ahk and run it. Before sending a prompt to your coding agent, press Ctrl + Alt + 1 and paste your prompt to any regular chatbot. Then send the output to the agent. This is the actual, boring, real way to "10x your prompting". Use the other number keys to avoid repeating yourself over and over again. I use this macro prolly 100-200 times per day. AutoHotKey isn't as new or hype as a lot of other workflows, but there's a reason it's still widely used after 17 years. Don't overcomplicate it.

; Requires AutoHotkey v1.1+

; All macros are `Ctrl + Alt + <variable>`

^!1::
    Send, Please help me more clearly articulate what I mean with this message (write the message in a code block):
return

^!2::
    Send, Please make the following changes:
return

^!3::
    Send, It seems you got cut off by the maximum response limit. Please continue by picking up where you left off.
return


In my experience the past few months, Ctrl + Alt + 1 works best with Instruct models (non-thinking). Reasoning causes some models to ramble and miss the point. I've just been using GPT-5.x for this.