Hugging Face's logo

Huggingface Projects
company
https://huggingface.co/
huggingface
huggingface
Activity Feed

AI & ML interests

None defined yet.

Recent Activity

sergiopaniego  updated a dataset 1 day ago
huggingface-projects/Deep-RL-Course-Certification
andito  authored a paper 2 days ago
FineVision: Open Data Is All You Need
pcuenq  updated a dataset 6 days ago
huggingface-projects/drlc-leaderboard-data
View all activity

sergiopaniego 
posted an update 1 day ago
sergiopaniego 
updated a dataset 1 day ago
AdinaY 
posted an update 2 days ago
view post
Post
2329
HunyuanWorld Mirror🔥a versatile feed forward model for universal 3D world reconstruction by Tencent

tencent/HunyuanWorld-Mirror

✨ Any prior in → 3D world out
✨ Mix camera, intrinsics, depth as priors
✨ Predict point clouds, normals, Gaussians & more in one pass
✨ Unified architecture for all 3D task
andito 
authored a paper 2 days ago
andito 
posted an update 3 days ago
view post
Post
1480
Finally, our new paper is out! "𝗙𝗶𝗻𝗲𝗩𝗶𝘀𝗶𝗼𝗻: 𝗢𝗽𝗲𝗻 𝗗𝗮𝘁𝗮 𝗜𝘀 𝗔𝗹𝗹 𝗬𝗼𝘂 𝗡𝗲𝗲𝗱"! 🥳
FineVision: Open Data Is All You Need (2510.17269)

If you've ever trained a VLM, you know this problem: nobody shares their data mixtures. It's a black box, making replicating SOTA work impossible.
We wanted to change that.

FineVision unifies 200 sources into 24 million samples. With 17.3 million images and 9.5 billion answer tokens, it's the largest open resource of its kind.

In the paper, we share how we built it:
🔍 finding and cleaning data at scale
🧹 removing excessive duplicates across sources
🤗 decontaminating against 66 public benchmarks

My favorite part is Figure 6 (in the video!). It's our visual diversity analysis. It shows that FineVision isn't just bigger; it's more balanced and conceptually richer than other open datasets.
NVIDIA's Eagle 2 paper highlighted just how critical this visual diversity is, and our results confirm it: models trained on FineVision consistently outperform those trained on any other open dataset on 11 benchmarks!

🎉 To celebrate the paper, I’m also releasing a concatenated and shuffled version of the full dataset! 👉HuggingFaceM4/FineVision_full_shuffled

It’s ready to stream, so you can start training your own models right away:

from datasets import load_dataset
d = load_dataset("HuggingFaceM4/FineVision_full_shuffled", split="train", streaming=True)
print(next(iter(d)))

A big shoutout to the first authors: Luis Wiedmann and Orr Zohar. They are rockstars!
merve 
posted an update 4 days ago
view post
Post
4260
deepseek-ai/DeepSeek-OCR is out! 🔥 my take ⤵️
> pretty insane it can parse and re-render charts in HTML
> it uses CLIP and SAM features concatenated, so better grounding
> very efficient per vision tokens/performance ratio
> covers 100 languages
  • 2 replies
·
pcuenq 
updated a dataset 6 days ago
AdinaY 
posted an update 7 days ago
view post
Post
550
PaddleOCR VL🔥 0.9B Multilingual VLM by Baidu

PaddlePaddle/PaddleOCR-VL

✨ Ultra-efficient NaViT + ERNIE-4.5 architecture
✨ Supports 109 languages 🤯
✨ Accurately recognizes text, tables, formulas & charts
✨ Fast inference and lightweight for deployment
sergiopaniego 
posted an update 7 days ago
view post
Post
1816
New drop! 💥 The VLM Object Understanding Comparison Space now runs with Qwen3-VL-4B and moondream3.

You can compare how models reason about images 🧠

Bonus: thanks to @ariG23498 , you now get auto-suggested prompts to explore faster.

Let’s gooo

sergiopaniego/vlm_object_understanding
sergiopaniego 
posted an update 7 days ago
view post
Post
797
New drop! 💥 The VLM Object Understanding Comparison Space now runs with Qwen3-VL-4B and moondream3.



You can compare how models reason about images 🧠

Bonus: thanks to @ariG23498 , you now get auto-suggested prompts to explore faster.

Let’s gooo

sergiopaniego/vlm_object_understanding
AdinaY 
posted an update 8 days ago
multimodalart 
posted an update 8 days ago
view post
Post
1167
Want to iterate on a Hugging Face Space with an LLM?

Now you can easily convert any HF entire repo (Model, Dataset or Space) to a text file and feed it to a language model!

multimodalart/repo2txt
AdinaY 
posted an update 9 days ago
sergiopaniego 
posted an update 9 days ago
view post
Post
2243
@Qwen released their new small and dense VLMs (Qwen3-VL).

They're incredibly capable and one of my all-time favourite VLMs.

🤗 We’ve prepared some resources to help you get started.

> Fine-tune Qwen3-VL-4B with SFT or GRPO (free Colab notebooks):
> SFT: https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/sft_qwen_vl.ipynb
> GRPO: https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/grpo_qwen3_vl.ipynb

> Compare object detection vs. Moondream3:
sergiopaniego/vlm_object_understanding

> Fine-tune from the CLI using TRL:
https://github.com/kashif/Qwen3-VL/blob/trl-sft/qwen-vl-finetune/README.md#trl-based-training-single-gpu
AdinaY 
posted an update 11 days ago
view post
Post
449
Ring-1T🔥 the trillion-parameter thinking model released by Ant group, the company behind Alipay

inclusionAI/Ring-1T

✨ 1T params (50B active)- MIT license
✨ 128K context (YaRN)
✨ RLVR, Icepop, and ASystem make trillion-scale RL stable
akhaliq 
authored a paper 11 days ago
AdinaY 
posted an update 14 days ago
view post
Post
479
KAT-Dev-72B-Exp🔥 Kuaishou's ( the company behind Kring AI ) new open model for software engineering

Kwaipilot/KAT-Dev-72B-Exp

✨ 72B - Apache2.0
✨ Redesigned attention kernel & training engine for efficient context-aware RL
✨ 74.6% accuracy on SWE-Bench Verified
sergiopaniego 
posted an update 14 days ago
view post
Post
1430
Super nice intro to fine-tuning with TRL, just dropped by @google (runs free on Colab)!

They use SFT + QLoRA to fine-tune the tiny Gemma 3 270M model for emoji generation

Here’s what the fine-tuned model generates for the prompt: “I'm learning to tweet” → 🐦🗣💻

Colab: https://colab.research.google.com/github/google-gemini/gemma-cookbook/blob/main/Demos/Emoji-Gemma-on-Web/resources/Fine_tune_Gemma_3_270M_for_emoji_generation.ipynb
Try it out: google/emoji-gemma
Learn more: https://developers.googleblog.com/en/own-your-ai-fine-tune-gemma-3-270m-for-on-device/
giadap 
posted an update 15 days ago
view post
Post
4343
🌎 AI ethics and sustainability are two sides of the same coin.

In our new blog post with Dr. Sasha Luccioni, we argue that separating them (as is too often the case) means missing the bigger picture of how AI systems impact both people and the planet.

Ethical and sustainable AI development can’t be pursued in isolation. The same choices that affect who benefits or is harmed by AI systems also determine how much energy and resources they consume.

We explore how two key concepts, evaluation and transparency, can serve as bridges between these domains:

📊 Evaluation, by moving beyond accuracy or performance metrics to include environmental and social costs, as we’ve done with tools like the AI Energy Score.

🔍 Transparency, by enabling reproducibility, accountability, and environmental reporting through open tools like the Environmental Transparency Space.

AI systems mirror our priorities. If we separate ethics from sustainability, we risk building technologies that are efficient but unjust, or fair but unsustainable.

Read our blog post here: https://huggingface.co/blog/sasha/ethics-sustainability

AIEnergyScore/Leaderboard
sasha/environmental-transparency
  • 1 reply
·
AdinaY 
posted an update 16 days ago
view post
Post
4386
At the close of the National Holiday🇨🇳, Antgroup drops a new SoTA model.

Ling-1T 🔥 the trillion-parameter flagship of the Ling 2.0 series.

inclusionAI/Ling-1T

✨1T total / 50B active params per token
✨20T+ reasoning-dense tokens (Evo-CoT)
✨128K context via YaRN
✨FP8 training: 15%+ faster, same precision as BF16
✨Hybrid Syntax-Function-Aesthetics reward for front-end & visual generation
  • 1 reply
·