Yifei Li
@YifeiLiPKU
Ph.D. student @osunlp | Prev MSc @PKU1898 | BEng @NEUChina | Prev Intern @MSFTResearch (MSRA) | LLM & NLPer
📢📢Postdoc opportunity at OSUNLP!
🚨 Postdoc Hiring: I am looking for a postdoc to work on rigorously evaluating and advancing the capabilities and safety of computer-use agents (CUAs), co-advised with @ysu_nlp @osunlp. We welcome strong applicants with experience in CUAs, long-horizon reasoning/planning,…
🔎Agentic search like Deep Research is fundamentally changing web search, but it also brings an evaluation crisis⚠️ Introducing Mind2Web 2: Evaluating Agentic Search with Agents-as-a-Judge - 130 tasks (each requiring avg. 100+ webpages) from 1,000+ hours of expert labor -…
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!
📈 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. 🧵
🔬 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…
Realistic adversarial testing of Computer-Use Agents (CUAs) to identify their vulnerabilities and make them safer and more secure is … hard. Is @AnthropicAI Claude 4 Opus more robust to indirect prompt injection than previous versions like Claude 3.7? Not really. Why hard?…
⁉️Can you really trust Computer-Use Agents (CUAs) to control your computer⁉️ Not yet, @AnthropicAI Opus 4 shows an alarming 48% Attack Success Rate against realistic internet injection❗️ Introducing RedTeamCUA: realistic, interactive, and controlled sandbox environments for…
🚀 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:…
Tired of editing methods that require training, handcrafted subjects, or external memory? 🚀 #UltraEdit — Training-, subject-, and memory-free, for Lifelong Model Editing Compare to the prior best ✅New SOTA on 4 datasets and 6 models 🏎️7× faster – 20K samples within 5 mins on a…
Proud moment for @OhioStateCSE! Prof. @hhsun1 has been awarded funding from @SchmidtSciences' for AI Safety initiative — a first for Ohio State. Her work will help defend AI agents from adversarial attacks. engineering.osu.edu/news/2025/05/h…
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…
It's a great honor to give a keynote at the @Molecule_Maker symposium at UIUC! Many thanks to Prof. @hengjinlp and Prof. Jiawei Han for invitation. The symposium’s theme this year is “AI scientist? What would it take?”, which I hold close to heart and made a talk titled “Language…
🔧What if your web agent could abstract its experience into programmatic skills—and improve itself autonomously? 🌟 Introducing SkillWeaver: a framework to enable self-improvement through autonomous exploration and constructing an ever-growing library of programmatic skills. 🧠…
LLMs exhibit the Reversal Curse, a basic generalization failure where they struggle to learn reversible factual associations (e.g., "A is B" -> "B is A"). But why? Our new work uncovers that it's a symptom of the long-standing binding problem in AI, and shows that a model design…