🔥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

In addition to the many valuable insights presented in the Absolute Zero Reasoner (AZR) paper, I found the discussion of the “uh-oh” moment particularly interesting, which is the generation/emergence of “some unusual and potentially concerning chains of thought from the Llama

⁉️Can you really trust Computer-Use Agents (CUAs) to control your computer⁉️ Not yet, Anthropic Opus 4 shows an alarming 48% Attack Success Rate against realistic internet injection❗️ Introducing RedTeamCUA: realistic, interactive, and controlled sandbox environments for

Excited to be at the workshop XLLM-Reason-Plan at Conference on Language Modeling! Many thanks to the organizers for the efforts! 👏👏👏

🔬 Introducing ChemMCP, the first MCP-compatible toolkit for empowering AI models with advanced chemistry capabilities! In recent years, we’ve seen rising interest in tool-using AI agents across domains. Particularly in scientific domains like chemistry, LLMs alone still fall

Check out ChemMCP by Botao Yu OSU NLP Group, an easy-to-use and extensible toolkit to augment LLMs and agents with chemistry tools, built on Model Context Protocol (#MCP Model Context Protocol (MCP)) and our earlier work on ChemToolAgent! Try it out for your chemistry co-scientist!

Great use case and addition to the MCP ecosystem!

I'm late to review the "Illusion of Thinking" paper, so let me collect some of the best threads by and critical takes by Lisan al Gaib in one place and sprinkle some of my own thoughts in as well. The paper is rather critical of reasoning LLMs (LRMs): x.com/MFarajtabar/st…

Quizzing BioClip about an animal/plant has been another fun activity we do at a zoo/garden. Most of the time, it does get things right! Now check out BioClip 2, with much stronger performance and nice properties!

📢 Introducing AutoSDT, a fully automatic pipeline that collects data-driven scientific coding tasks at scale! We use AutoSDT to collect AutoSDT-5K, enabling open co-scientist models that rival GPT-4o on ScienceAgentBench! Thread below ⬇️ (1/n)

Had a great time at this CVPR community-building workshop---lots of fun discussions and some really important insights for early-career researchers. I also gave a talk on "Research as an Infinite Game." Here are the slides: canva.com/design/DAGp0iR…

📢Excited to announce the first project of my PhD! Through our work we address the training data scarcity to develop AI co-scientist models via AutoSDT, a fully automatic pipeline that collects high quality scientific coding tasks at scale! Read more in the full post here 👇

Together AI Super cool work! We have also just released AutoSDT which also aims to build open co-scientist models for data-driven scientific coding via an automatic pipeline to collect training data at scale, and our model even surpasses GPT-4o! You can see more here x.com/HananeNMoussa/…

While #AI becomes a driving force for scientific discovery (#AIforScience), it is time to summarize our work on #GenAI and #LLMs for #DrugDiscovery over the past 5 years: 📌 𝐋𝐋𝐌-𝐛𝐚𝐬𝐞𝐝 𝐀𝐠𝐞𝐧𝐭 𝐟𝐨𝐫 𝐃𝐫𝐮𝐠 𝐃𝐢𝐬𝐜𝐨𝐯𝐞𝐫𝐲: 📍 "Liddia: Language-based

If you care about building AI co-scientists for data-driven discovery, check out our recent work on automatically collecting large-scale, authentic, high-quality scientific coding tasks at a low cost, led by Yifei Li Hanane Moussa OSU NLP Group. 🌟AutoSDT: Scaling Data-Driven