Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up

All HF Hub posts
salma-remyx 
posted an update 2 days ago
view post
Post
2895
Reproducing research code shouldn't take longer than reading the paper.
For papers that include code, setting up the right environment often means hours of dependency hell and configuration debugging.

At Remyx AI, we built an agent that automatically creates and tests Docker images for research papers, then shares them publicly so anyone can reproduce results with a single command.

We just submitted PR #908 to integrate this directly into arXiv Labs.

If you believe in making reproducible research accessible to everyone, give it a bump!: https://github.com/arXiv/arxiv-browse/pull/908
  • 3 replies
·
vikhyatk 
posted an update 1 day ago
salma-remyx 
posted an update 1 day ago
view post
Post
1772
Mark you calendars for Thursday Sept 25th at 9am PST 📆
We're joining the @ag2 team in discord to present a deep-dive into how we've used the framework to build GitRank in their Community Talks

The GitRank pipeline is used to:
📰 power personalized paper recommendations
🐳 build environments as Docker Images
🎯 implement core-methods as PRs for your target repo

Attached is a draft outlining what we plan to cover in the talk.
Would love to gather your feedback to make this insightful for all: https://docs.google.com/presentation/d/1S0q-wGCu2dliVWb9ykGKFz61jZKZI4ipxWBv73HOFBo/edit?usp=sharing
takarajordan 
posted an update 1 day ago
view post
Post
1822
Are we really back to storing access tokens in plain text again?
{
  "mcpServers": {
    "hf-mcp-server": {
      "url": "https://huggingface.co/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_HF_TOKEN>"
      }
    }
  }
}

·
Tanaybh 
posted an update about 22 hours ago
view post
Post
820
The Bias is YOU - LLMs Mirror Your Own Assumptions

AI doesn't just have bias - it reflects yours.

When you ask a question with positive framing, you get positive answers. Ask with negative framing, you get negative answers. The AI becomes a mirror of your own assumptions.

Your framing determines the answer - The same topic yields opposite responses based on how you ask

AIs amplify your sentiment - Negative questions often get even MORE negative responses

This affects everyone - From students doing research to professionals making decisions

Why This Matters

This isn't a technical glitch - it's fundamental to how these systems work. They're trained on human language, and humans frame things with bias. The AI learned to match that framing.

Think about the implications:
- Medical professionals seeking second opinions
- Students researching controversial topics
- Business leaders evaluating strategies
- Anyone using AI for important decisions

The Stochastic Mirror Effect

Let's call this the "Stochastic Mirror" - the AI doesn't give you objective truth, it gives you a probabilistic reflection of your own framing.

You're not querying a neutral database. You're looking into a mirror that reflects and amplifies your assumptions.
  • 1 reply
·
Monica997 
posted an update about 17 hours ago
view post
Post
998
Turn Your Dog’s Photo into a 3D Figurine with Nano Banana 🐶✨

Just tested out the new Nano Banana feature, and I’m honestly impressed. I uploaded a single photo of my corgi, and within minutes, it generated a detailed 3D figurine model.

What makes this really interesting for tech and design folks:

AI-powered 2D → 3D conversion (no manual modeling required)

Preserves character consistency even with multiple images

Export options for 3D printing or digital use (OBJ, FBX, STL)

Works with pets, people, and even illustrated characters

For anyone into 3D modeling, collectibles, or architecture visualization, this is a game-changer. Imagine transforming static photos into tangible 3D assets with just a few clicks.

Here’s the link if you want to try it out: https://imini.com/nano-banana

Has anyone else here tested Nano Banana for pets or other personal projects? Would love to hear your results!
  • 1 reply
·
prithivMLmods 
posted an update 3 days ago
view post
Post
1309
Many of 'em pinged me asking to make the nano-banana-aio to available on hf.co/spaces, so I’ve transferred the app’s tech stack to make it compatible for deployment on Spaces. (Can be accessed with your own Gemini API) 🤗⭐️

✦ Yes, it is now available on Spaces: prithivMLmods/Nano-Banana-AIO

Nano Banana AIO (All-in-One) App, which offers seamless image manipulation features, including single/multiple image adaptation, a canvas for free-style drawing to creative image generation, and standard text-to-image generation.

All in One Banana for you! 😉
freddyaboulton 
posted an update 3 days ago
dimentox 
posted an update 2 days ago
view post
Post
1780
⚡ Big things are moving.

Witchborn Systems (newly recognized nonprofit) is forging the cornerstone of something we believe the world needs: a **public, governed AI layer**.

Not closed.
Not for sale.
Not hidden.

A Constitutional Layer for AI — transparent, amendable, incorruptible.
Every decision logged, every amendment public, every voice accountable.

This is only the beginning. The Codex is open. The forge is hot. 🔥

#AI #Transparency #CollectiveIntelligence #Nonprofit #Witchborn
merve 
posted an update 2 days ago
view post
Post
2673
IBM just released small swiss army knife for the document models: granite-docling-258M on Hugging Face 🔥

> not only a document converter but also can do document question answering, understand multiple languages 🤯
> best part: released with Apache 2.0 license 👏 use it with your commercial projects!
> it supports transformers, vLLM and MLX from the get-go! 🤗
> built on SigLIP2 & granite-165M

model: ibm-granite/granite-docling-258M
demo: ibm-granite/granite-docling-258m-demo 💗
Recently active users