Single-minus gluon tree amplitudes are nonzero
Paper
โข
2602.12176
โข
Published
โข
6
smolagents
Team
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
lewtunย
submitted
a
paper
to Daily Papers
1 day ago
akseljoonasย
updated
a
Space
2 days ago
lewtunย
submitted
a
paper
to Daily Papers
3 days ago
tfrereย
updated
a
Space
3 days ago
albertvillanovaย
posted
an
update
4 days ago
Post
1428
5 years already working in democratizing AI ๐ค
Grateful to be part of such an awesome team making it happen every day.
Grateful to be part of such an awesome team making it happen every day.
Post
621
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 ๐
https://huggingface.co/blog/upskill
https://huggingface.co/blog/upskill
Post
249
Hugging Face MCP Server v0.3.1
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Streamable HTTP used for Gradio Connectivity
- SSE Transport (as Server) removed
- Proxy Configuration added for launch of sub-agent tools
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Streamable HTTP used for Gradio Connectivity
- SSE Transport (as Server) removed
- Proxy Configuration added for launch of sub-agent tools
akseljoonasย
published
a
Space
18 days ago
Post
3410
Nvidia is on a roll lately. Nemotron 3 Nano is my new fav local model, but here's the real flex: they published the entire evaluation setup. Configs, prompts, logs, all of it. This is how you do open models ๐ฅ
https://huggingface.co/blog/nvidia/nemotron-3-nano-evaluation-recipe
https://huggingface.co/blog/nvidia/nemotron-3-nano-evaluation-recipe
Post
2539
Hugging Face MCP Server v0.2.46
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Add "discover" to Dynamic Space tool. Recommend deselecting "space_search" if using dynamic spaces.
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Add "discover" to Dynamic Space tool. Recommend deselecting "space_search" if using dynamic spaces.
Post
3023
Hugging Face MCP Server v0.2.45
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- New! Experimental dynamic_space tool.
- Default Image Generator changed to Qwen-Image-Fast
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- New! Experimental dynamic_space tool.
- Default Image Generator changed to Qwen-Image-Fast
abidlabsย
authored
3
papers
3 months ago
Persistent Anti-Muslim Bias in Large Language Models
Paper
โข
2101.05783
โข
Published
โข
2
STG-MTL: Scalable Task Grouping for Multi-Task Learning Using Data Map
Paper
โข
2307.03374
โข
Published
โข
1
Gradio: Hassle-Free Sharing and Testing of ML Models in the Wild
Paper
โข
1906.02569
โข
Published
โข
1
Post
2250
Hugging Face MCP Server v0.2.40
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Improved progressive disclosure and descriptions for Jobs tool.
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Improved progressive disclosure and descriptions for Jobs tool.
Post
9708
Why I think local, open-source models will eventually win.
The most useful AI applications are moving toward multi-turn agentic behavior: systems that take hundreds or even thousands of iterative steps to complete a task, e.g. Claude Code, computer-control agents that click, type, and test repeatedly.
In these cases, the power of the model is not how smart it is per token, but in how quickly it can interact with its environment and tools across many steps. In that regime, model quality becomes secondary to latency.
An open-source model that can call tools quickly, check that the right thing was clicked, or verify that a code change actually passes tests can easily outperform a slightly โsmarterโ closed model that has to make remote API calls for every move.
Eventually, the balance tips: it becomes impractical for an agent to rely on remote inference for every micro-action. Just as no one would tolerate a keyboard that required a network request per keystroke, users wonโt accept agent workflows bottlenecked by latency. All devices will ship with local, open-source models that are โgood enoughโ and the expectation will shift toward everything running locally. Itโll happen sooner than most people think.
The most useful AI applications are moving toward multi-turn agentic behavior: systems that take hundreds or even thousands of iterative steps to complete a task, e.g. Claude Code, computer-control agents that click, type, and test repeatedly.
In these cases, the power of the model is not how smart it is per token, but in how quickly it can interact with its environment and tools across many steps. In that regime, model quality becomes secondary to latency.
An open-source model that can call tools quickly, check that the right thing was clicked, or verify that a code change actually passes tests can easily outperform a slightly โsmarterโ closed model that has to make remote API calls for every move.
Eventually, the balance tips: it becomes impractical for an agent to rely on remote inference for every micro-action. Just as no one would tolerate a keyboard that required a network request per keystroke, users wonโt accept agent workflows bottlenecked by latency. All devices will ship with local, open-source models that are โgood enoughโ and the expectation will shift toward everything running locally. Itโll happen sooner than most people think.
- 8 replies
Post
368
Hugging Face MCP Server v0.2.35
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
$HF_TOKEN is expanded in Jobs Secrets environment variables.
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
$HF_TOKEN is expanded in Jobs Secrets environment variables.
anditoย
authored
a
paper
4 months ago
Post
359
Hugging Face MCP Server v0.2.33
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Allow discovery of Product Documentation Library via the Search tool.
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Allow discovery of Product Documentation Library via the Search tool.
Post
2213
Finally, our new paper is out! "๐๐ถ๐ป๐ฒ๐ฉ๐ถ๐๐ถ๐ผ๐ป: ๐ข๐ฝ๐ฒ๐ป ๐๐ฎ๐๐ฎ ๐๐ ๐๐น๐น ๐ฌ๐ผ๐ ๐ก๐ฒ๐ฒ๐ฑ"! ๐ฅณ
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:
๐ finding and cleaning data at scale
๐งน removing excessive duplicates across sources
๐ค 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!
๐ To celebrate the paper, Iโm also releasing a concatenated and shuffled version of the full dataset! ๐
Itโs 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!
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:
๐ finding and cleaning data at scale
๐งน removing excessive duplicates across sources
๐ค 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!
๐ To celebrate the paper, Iโm also releasing a concatenated and shuffled version of the full dataset! ๐
HuggingFaceM4/FineVision_full_shuffled Itโs 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!