🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

JOURNEY TO 1 MILLION DEVELOPERS 5 years ago, we launched Gradio as a simple Python library to let researchers at Stanford easily demo computer vision models with a web interface. Today, Gradio is used by >1 million developers each month to build and share AI web apps. This

💸We expand the economic framework of cost-of-production to quantify the benefits of different LLMs arxiv.org/pdf/2504.13359 Llama3 8B + o1-mini really stand out as milestone jumps in efficiency and capability resp! Great job Mehmet Hamza Erol Mert Yuksekgonul Batu El Mirac Suzgun👏

Introducing OpenBiomedVid: open dataset of >1000 hours of diverse medical videos w/ expert voice-over discussion + annotation🩺 Finetuning VLMs on these educational videos increase its biomedical understanding by 20% - 90% 📰arxiv.org/abs/2504.14391 🌐github.com/zou-group/Open…

🎉 Thrilled to share that OctoTools won the Best Paper Award at KnowledgeNLP Workshop @NAACL 2025 #NAACL! 🏆 OctoTools is a flexible, easy-to-use framework that equips LLMs with diverse tools for complex reasoning—just customize your agent by mixing modular “tool cards” like building with Lego 🧩

🚀 Excited to share that “#FactTest: Factuality Testing in Large Language Models with Finite-Sample and Distribution-Free Guarantees” has been accepted to #ICML25 ! 🎉 📄 Paper: arxiv.org/abs/2411.02603 💻 Code: github.com/fannie1208/Fac… 1/N

Our new #ICML2025 paper formulates #LLM hallucination as hypothesis testing to provide statistical guarantees on factuality. #FactTest is a distribution free and model agnostic approach to improve LLM accuracy. Great job Fan Nie Xiaotian Hou, Shuhang Lin Huaxiu Yao

OctoTools won the Best Paper Award at #NAACL2025 KnowledgeNLP Workshop @NAACL 2025!

SyntheMol-RL: a flexible reinforcement learning framework for designing novel and synthesizable antibiotics １．SyntheMol-RL is a reinforcement learning-based generative framework designed to create novel, easily synthesizable antibiotics targeting drug-resistant bacteria such

This is awesome. These guys used AI to discover a new molecule for treating MRSA and then instead of just going 'Look, we found a potentially helpful molecule' they went and tested it. It actually worked at suppressing bacterial growth. Nowadays, you can just cure things.

It has begun! In the near future, most new drugs will be AI designed and they will save millions of lives!

This isn’t just a scientific win. It’s a signal of what AI can do: Discover new drugs. Fight resistance. Save lives. The future of medicine is not just human. It’s human + AI.

🚨 Call for submission at our workshop on Computer Vision for Automated Medical Diagnosis #ICCV2025 in 🌴 Honolulu, Hawaii! Join us at #ICCV2025 to present your work on 🤖multimodal LLMs, 🧠 agents, & ⚖️ fair, reliable AI for healthcare and medicine. 🗓️ Deadline: June 21,

🚀 Introducing Mixture-of-Agents Alignment (MoAA), a new method to "distill" the collective intelligence of open-source LLMs into a single, efficient model. MoAA outperforms GPT-4o as a teacher, boosting smaller models like Llama3.1-8B to rival models 10x their size!

Data Science Agent – implemented from scratch in code! In this notebook, we share our Data Science Agent implementation & go over how it works step-by-step. We use an iterative ReAct workflow capable of reasoning, code execution, and self-correction. Link below!🔽

Our new #icml2025 paper w/Together AI shows how to use synthetic data from Mixture-of-Agents to boost LM fine-tuning + RL. Turns out a mixture of small agents is much more effective/cheaper than using a large LM as teacher 🌐together.ai/blog/moaa 📜arxiv.org/abs/2505.03059

Fully open source and capable Data Science Agent that you can run in CoLab! Great job by Federico Bianchi Zain Shang Zhu 👏 github.com/togethercomput…