Hugging Face's logo
Activity Feed

AI & ML interests

Exploring foundation models for DNA and beyond 🧬

Recent Activity
cgeorgiawΒ  updated a dataset 4 days ago
HuggingFaceBio/vepqa
cgeorgiawΒ  published a dataset 5 days ago
HuggingFaceBio/vepqa
lewtunΒ  submitted a paper 5 months ago
Single-minus gluon tree amplitudes are nonzero
View all activity
abidlabsΒ 
posted an update 2 days ago
cgeorgiawΒ 
updated a dataset 4 days ago
cgeorgiawΒ 
published a dataset 5 days ago
lewtunΒ 
submitted 2 papers to Daily Papers 5 months ago
cgeorgiawΒ 
posted an update 7 months ago
abidlabsΒ 
authored 3 papers 8 months ago
abidlabsΒ 
posted an update 8 months ago
view post
Post
11527
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 β€œsmarter” 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 won’t accept agent workflows bottlenecked by latency. All devices will ship with local, open-source models that are β€œgood enough” and the expectation will shift toward everything running locally. It’ll happen sooner than most people think.
  • 8 replies
Β·
merveΒ 
posted an update 8 months ago
view post
Post
13321
deepseek-ai/DeepSeek-OCR is out! πŸ”₯ 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
  • 4 replies
Β·
thomwolfΒ 
authored a paper 9 months ago
lvwerraΒ 
authored a paper 9 months ago
abidlabsΒ 
posted an update 9 months ago
merveΒ 
posted an update 9 months ago
view post
Post
7053
large AI labs open-sourced a ton of models last week πŸ”₯
here's few picks, find even more here merve/sep-16-releases-68d13ea4c547f02f95842f05 🀝
> IBM released a new Docling model with 258M params based on Granite (A2.0) πŸ“ ibm-granite/granite-docling-258M
> Xiaomi released 7B audio LM with base and instruct variants (MIT) XiaomiMiMo/mimo-audio-68cc7202692c27dae881cce0
> DecartAI released Lucy Edit, open Nano Banana 🍌 (NC) decart-ai/Lucy-Edit-Dev
> OpenGVLab released a family of agentic computer use models (3B/7B/32B) with the dataset πŸ’» OpenGVLab/scalecua-68c912cf56f7ff4c8e034003
> Meituan Longcat released thinking version of LongCat-Flash πŸ’­ meituan-longcat/LongCat-Flash-Thinking
  • 2 replies
Β·
merveΒ 
posted an update 9 months ago
view post
Post
3564
IBM just released small swiss army knife for the document models: granite-docling-258M on Hugging Face πŸ”₯

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

model: ibm-granite/granite-docling-258M
demo: ibm-granite/granite-docling-258m-demo πŸ’—
merveΒ 
posted an update 10 months ago
view post
Post
1306
a ton of image/video generation models and LLMs from big labs πŸ”₯

> Meta released facebook/mobilellm-r1-68c4597b104fac45f28f448e, smol LLMs for on-device use πŸ’¬
> Tencent released tencent/SRPO, high res image generation model and tencent/POINTS-Reader, cutting edge OCR πŸ“
> ByteDance released bytedance-research/HuMo, video generation from any input ⏯️

find more models, datasets, demos here merve/sep-11-releases-68c7dbfa26bea8cd921fa0ac
merveΒ 
posted an update 10 months ago
view post
Post
1091
fan-favorite vision LM Florence-2 is now officially supported in transformers πŸ€—

find all the models in
florence-community org 🫑
merveΒ 
posted an update 10 months ago
merveΒ 
posted an update 10 months ago