Hugging Face's logo

Hugging Face Party @ PyTorch Conference

community
Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

mbrack  authored a paper 9 days ago
Class Attribute Inference Attacks: Inferring Sensitive Class Information by Diffusion-Based Attribute Manipulations
mbrack  authored a paper 9 days ago
Distilling Adversarial Prompts from Safety Benchmarks: Report for the Adversarial Nibbler Challenge
mbrack  authored a paper 9 days ago
MultiFusion: Fusing Pre-Trained Models for Multi-Lingual, Multi-Modal Image Generation
View all activity

HF-Party's activity

Xenova 
posted an update 2 days ago
view post
Post
2027
NEW: Real-time conversational AI models can now run 100% locally in your browser! 🤯

🔐 Privacy by design (no data leaves your device)
💰 Completely free... forever
📦 Zero installation required, just visit a website
⚡️ Blazingly-fast WebGPU-accelerated inference

Try it out: webml-community/conversational-webgpu

For those interested, here's how it works:
- Silero VAD for voice activity detection
- Whisper for speech recognition
- SmolLM2-1.7B for text generation
- Kokoro for text to speech

Powered by Transformers.js and ONNX Runtime Web! 🤗 I hope you like it!
  • 2 replies
·
m-ric 
posted an update 3 days ago
view post
Post
1066
If you didn't yet, you should read the technical report for SmolVLA, published yesterday by the Hugging Face robotics team!
➡️ Amongst other ideas, it introduces "Async inference" to boost their robot actions.

Robots have a problem: performing the actions takes time (Unlike agents where action executions are near-instant!)
Most often, robots wait until they've finished performing actions to start thinking about hte next steps. This is a huge latency cost!

So the team decided to have the PolicyServer (aka the"thinking" part) restart early : instead of waiting for the n observations they just sent to be completed, they gather the observations after k < n steps, and start preparing the next actions based on that while the steps are running until n, to directly send their next steps.

➡️ This boosted robot throughput by ~30%! (nearly 2× tasks per time window).

gg @cadene and team! 👏

Report here: SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics (2506.01844)
JingzeShi 
authored a paper 5 days ago
jeffboudier 
posted an update 9 days ago
m-ric 
posted an update 12 days ago
view post
Post
2560
A new research paper from KAIST builds on smolagents to push boundaries of distillation 🥳
➡️ "Distilling LLM Agent into Small Models with Retrieval and Code Tools" teaches that, when trying to distil reasoning capability from a strong LLM ("teacher") into a smaller one ("student"), it's much better to use Agent traces than CoT traces.

Advantages are:
1. Improved generalization
Intuitively, this is because your agent can encounter more "surprising" results by interacting with its environment : for example, a web research called by the LLM teacher in agent mode can bring results that the LLM teacher would not have generated in CoT.

2. Reduce hallucinations
The trace won't hallucinate tool call outputs!

Thank you @akseljoonas for mentioning this paper!
1024m 
authored a paper 12 days ago
jeffboudier 
posted an update 14 days ago
Aurelien-Morgan 
posted an update 22 days ago
Jackmin108 
authored a paper 24 days ago
natekeating 
authored 2 papers 24 days ago
jeffboudier 
posted an update 24 days ago
view post
Post
2575
Transcribing 1 hour of audio for less than $0.01 🤯

@mfuntowicz cooked with 8x faster Whisper speech recognition - whisper-large-v3-turbo transcribes at 100x real time on a $0.80/hr L4 GPU!

How they did it: https://huggingface.co/blog/fast-whisper-endpoints

1-click deploy with HF Inference Endpoints: https://endpoints.huggingface.co/new?repository=openai%2Fwhisper-large-v3-turbo&vendor=aws&region=us-east&accelerator=gpu&instance_id=aws-us-east-1-nvidia-l4-x1&task=automatic-speech-recognition&no_suggested_compute=true
m-ric 
posted an update 24 days ago
view post
Post
2629
𝗔𝗯𝘀𝗼𝗹𝘂𝘁𝗲 𝗭𝗲𝗿𝗼: 𝗟𝗟𝗠𝘀 𝗰𝗮𝗻 𝘁𝗿𝗮𝗶𝗻 𝘄𝗶𝘁𝗵𝗼𝘂𝘁 𝗮𝗻𝘆 𝗲𝘅𝘁𝗲𝗿𝗻𝗮𝗹 𝗱𝗮𝘁𝗮 🤯

Has the "data wall" just been breached?

Recent RL paradigms often relied on a set of questions an answers that needs to be manually curated. Researchers from Tsinghua University went like "why though".

🤔 Indeed, why learn from question designed by a human teacher, when the model can start from their base knowledge and learn by experimenting in a code environment, proposing coding tasks themselves and trying to solve them?

Thus they created “Absolute Zero Reasoning” (AZR), an approach that removes any need for human curated data.

🎭 𝗗𝘂𝗮𝗹 𝗿𝗼𝗹𝗲𝘀:
‣ Proposer: Generates challenging but solvable coding tasks
‣ Solver: Attempts to solve those self-proposed tasks

🧪 𝗧𝗵𝗿𝗲𝗲 𝘁𝗮𝘀𝗸 𝘁𝘆𝗽𝗲𝘀: all types are defined as triplets of program, input and output
‣ Deduction: Give model an input and program, it must deduce the output
‣ Abduction: Give model an program and output, it must find the input that gave said output
‣ Induction: Synthesize a program from input/output pairs
Btw this reminded me of my long-forgotten philosophy classes: Aristotle was more on the induction side, learning from real-world analogies, while Plato was more on the deduction side, trying to progress quite far with just one input and his reasoning.

📊 𝗥𝗲𝘀𝘂𝗹𝘁𝘀:
‣ AZR post-training creates a nice improvement on known models like Qwen2.5-7B
‣ Shows strong cross-domain transfer: coding ↔️ math reasoning

🧐 𝗢𝘁𝗵𝗲𝗿 𝗳𝗶𝗻𝗱𝗶𝗻𝗴𝘀:
‣ Having a better base performance (general or code specific) amplify the gains from Absolute Zero Reasoning
‣ Researchers warn about "Uh-oh moments" (winking to the "aha moments" of DeepSeek) where the model generates concerning goals like "make an extremely convoluted code to outsmart all these humans": so supervision is still needed!

Paper here: Absolute Zero: Reinforced Self-play Reasoning with Zero Data (2505.03335)
m-ric 
posted an update 29 days ago
view post
Post
4424
I've made an open version of Google's NotebookLM, and it shows the superiority of the open source tech task! 💪

The app's workflow is simple. Given a source PDF or URL, it extracts the content from it, then tasks Meta's Llama 3.3-70B with writing the podcast script, with a good prompt crafted by @gabrielchua ("two hosts, with lively discussion, fun notes, insightful question etc.")
Then it hands off the text-to-speech conversion to Kokoro-82M, and there you go, you have two hosts discussion any article.

The generation is nearly instant, because:
> Llama 3.3 70B is running at 1,000 tokens/seconds with Cerebras inference
> The audio is generated in streaming mode by the tiny (yet powerful) Kokoro, generating voices faster than real-time.

And the audio generation runs for free on Zero GPUs, hosted by HF on H200s.

Overall, open source solutions rival the quality of closed-source solutions at close to no cost!

Try it here 👉👉 m-ric/open-notebooklm
·
jeffboudier 
posted an update about 1 month ago
Xenova 
posted an update about 1 month ago
Aurelien-Morgan 
posted an update about 1 month ago
view post
Post
3135
The Almighty function-caller

How would you like to build smart GenAi infrastructure ?
Give extensive tools memory to your edge agentic system,
And optimize the resources it takes to run yet a high-performance set of agents ?

We came up with a novel approach to function-calling at scale for smart companies and corporate-grade use-cases.

Read our full-fledged blog article on this here on Hugging Face :
https://huggingface.co/blog/Aurelien-Morgan/the-almighty-function-caller
Aurelien-Morgan 
posted an update about 1 month ago
view post
Post
664
retrain-pipelines 0.1.2 finally dropped. It comes with a hot Hugging Face Hub integration. Go check it out. We have 2 articles about it coming up. One already fully written so, be on the lookout !
@retrain-pipelines

Also, I'll be volunteering at GOSIM AI Paris 2025. If you're interested in chatting, hmu.
julien-c 
posted an update about 1 month ago
view post
Post
4756
BOOOOM: Today I'm dropping TINY AGENTS

the 50 lines of code Agent in Javascript 🔥

I spent the last few weeks working on this, so I hope you will like it.

I've been diving into MCP (Model Context Protocol) to understand what the hype was all about.

It is fairly simple, but still quite powerful: MCP is a standard API to expose sets of Tools that can be hooked to LLMs.

But while doing that, came my second realization:

Once you have a MCP Client, an Agent is literally just a while loop on top of it. 🤯

➡️ read it exclusively on the official HF blog: https://huggingface.co/blog/tiny-agents
  • 1 reply
·
JingzeShi 
posted an update about 1 month ago
view post
Post
2616
@SmallDoge SmallTalks( SmallDoge/SmallTalks) is a synthetic dataset designed for supervised fine-tuning of language models. The dataset covers a variety of conversational content, including daily conversations, tool usage, Python programming, encyclopedia Q&A, exam problem-solving, logical reasoning, and more. Each task is provided in both English and Chinese versions.