Pokee released PokeeResearch-7B, an open-source 7B deep research agent model that reasons, retrieves, and self-verifies. Among 10 benchmarks, PokeeResearch-7B outperforms all other open 7B deep research models. Available via Pokee AI, API, and Hugging Face.
OPEN SOURCE
-
PyTorch Framework Continues Growth While Maintaining Core Values
By
–
. @PyTorch has snowballed into something never imagined, while still keeping our core values intact!
feels incredible.
-with @ezyang and @apaszke -
Datalab’s State-of-the-Art Text Extraction Models Now Available
By
–
Datalab's models are state-of-the-art for text extraction, and are based on the popular open-source Marker and Surya projects. They're fast and cost between $2-$6 per 1000 pages.
-
Reflex Build: Open-Source Framework for Web Applications
By
–
Checkout Reflex: https://
github.com/reflex-dev/ref
lex
… Try out Reflex Build here: -
Regex bottleneck in tokenizer requires expert optimization
By
–
Yep, the use of regex is both a huge dependency and huge bottleneck in the tokenizer. I think it's a beautiful project to try to do this correctly, but I'd need someone who is really familiar with regex to pitch in and also a large test suite to make sure. I'd love to merge such
-
Open Science and JEPA: Future of AI Research with Yann LeCun
By
–
Fun breakfast with @ylecun
. We chatted about open science and open source (grateful for his tireless advocacy of these for decades), JEPA and where AI research and models might go next! -
PyTorch Conference Talk on LLM Landscape 2025
By
–
Excited to be (finally) heading to the PyTorch Conference! I’ll be giving a talk tomorrow at 11:00 AM on “The LLM Landscape 2025”, where I’ll discuss the key components behind this year’s most prominent open-weight LLMs, and highlight a few architectural developments that go
-
Qwen3 Small Models: Faster and Cheaper Alternative to GPT
By
–
Interesting that they mentioned faster & cheaper compared to OpenAI’s latest models not “customizable”. That makes me think they are specifically referring to gpt-oss, This in turn means they are using the small, dense Qwen3 models, maybe 0.6 to 4B range. And this is
-
Training multilingual cultural model improves multimodal benchmark performance
By
–
Thank you so much and appreciate you taking time to check the paper. We trained a model(
https://
huggingface.co/neulab/Cultura
lPangea-7B
…) on the subset of the dataset and were able to improve performance on many multilingual/cultural multimodal benchmarks. Yeahhh, would be great too if you could also -
Stable Audio 2.5 live chat with ComfyUI demonstrates inpainting
By
–
We joined our friends at @ComfyUI for a live chat about what's new with Stable Audio 2.5 🥁
— Stability AI (@StabilityAI) 21 octobre 2025
Check out CJ Carr from our Audio Research team demoing the model’s inpainting capability.
You can watch the full episode here for more insights and examples 👉 https://t.co/430lf6kve3 pic.twitter.com/2A0KHZieQBWe joined our friends at @ComfyUI for a live chat about what's new with Stable Audio 2.5 🥁 Check out CJ Carr from our Audio Research team demoing the model’s inpainting capability. You can watch the full episode here for more insights and examples 👉 bit.ly/43nRa5x
→ View original post on X — @stabilityai, 2025-10-21 19:31 UTC