🔥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

I will miss #NAACL2025 unfortunately, but please check out our work on chemistry agents, "ChemToolAgent: The Impact of Tools on Language Agents for Chemistry Problem Solving" today (May 1) during 2:00-3:30pm (local time) at Hall 3, Poster Session 5! Some updates: We have renamed

⏳ Less than 1 day left to submit! 🔦 Speaker Spotlight Time! We’re thrilled to welcome Yu Su (Yu Su), Distinguished Assistant Professor at The Ohio State University, as an invited speaker at the ICML 2025 Workshop on Computer Use Agents! His work bridges LLM agents, memory,

Super excited to get funded by Schmidt Sciences to study computer-use agents (CUAs) under adversarial attacks. Many thanks to the student leads including Zeyi Liao, Jaylen Jones, Linxi Jiang, and amazing co-PIs Yu Su and Zhiqiang Lin. As the capabilities of CUAs improve,

Glad to get the 'little stamp' on my appointment letter one year ahead of the clock 🥰 It came just in time amid the peak of the AI hype week. With a bit more job security, now it's time to think about the next chapter of my career. How can one continue to make meaningful

🚀 Thrilled to unveil the most exciting project of my PhD: Explorer — Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web Agents TL;DR: A scalable multi-agent pipeline that leverages exploration for diverse web agent trajectory synthesis. 📄 Paper:

⁉️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

Realistic adversarial testing of Computer-Use Agents (CUAs) to identify their vulnerabilities and make them safer and more secure is … hard. Is Anthropic Claude 4 Opus more robust to indirect prompt injection than previous versions like Claude 3.7? Not really. Why hard?

🔬 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

Heading to #CVPR2025 to present our Oral paper with NVIDIA Robotics! 📅 June 14 (Sat) | 🕐 1:00 PM | 📍Oral Session 4B @ ExHall A2 I’ll also be at the 3D-VLA/VLM and EVAL-FoMo 2 workshops presenting the same work. Come say hi!

📈 Scaling may be hitting a wall in the digital world, but it's only beginning in the biological world! We trained a foundation model on 214M images of ~1M species (50% of named species on Earth 🐨🐠🌻🦠) and found emergent properties capturing hidden regularities in nature. 🧵

It’s so exciting to see BioCLIP 2 demonstrates a biologically meaningful embedding space while only trained to distinguish species. Can’t wait to see more applications of BioCLIP 2 in solving real world problems. I’m attending #CVPR2025 in Nashville. Happy to chat about it!

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)

Proud of Chan Hee (Luke) Song ‘s oral presentation at #CVPR2025!

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

🔥New Computer Agent Arena Leaderboard Updates (2k+ user votes)! 🤔Which VLMs act better as computer use agents (CUAs)? 1, Claude Sonnet 4 🥇 2, Claude 3.7 Sonnet 🥈 3, UI-TARS-1.5 🥉 4, Operator More insights in the thread 👇 arena.xlang.ai

Our group is known for producing widely adopted benchmarks (MMMU, Mind2Web, TravelPlaner, ScienceAgentBench etc.). Mind2Web 2 is probably the benchmark we spent the most time on ever. 26 authors spent over 6 months to tackle the emerging evaluation crisis head-on. Check it out!

Rigorously evaluating agentic systems has been one of our pursuits at OSU NLP Group, with prior efforts including Mind2Web and ScienceAgentBench. Today we introduce Mind2Web 2 to evaluate the emerging Deep Research-like agents: It features realistic and diverse long-horizon web

Thrilled to announce that our work Online-Mind2Web has been accepted to Conference on Language Modeling ! 🎉 It's my first PhD work and first paper at COLM. See you in Montreal! 🍁 Several teams are already testing their agents on Online-Mind2Web. If you're curious about how your agent performs, try