Can #LLMs excellently handle various table-based tasks? 📢Introducing TableLlama and TableInstruct: the FIRST open-source generalist #LLMs and instruction tuning dataset for tables. 🌟Strong performance on both in-domain & out-of-domain settings. #NLProc

Important work on AI4S, co-led by @hhsun1 @osunlp

Life update: I moved to silicon valley to tackle agents' biggest challenges: plasticity and reliability. Today's agents are smart but brittle. They lack plasticity (continual learning and adaptation) and reliability (stable, predictable behavior with bounded failures). These two

Computer Use: Modern Moravec's Paradox A new blog post arguing why computer-use agents may be the biggest opportunity and challenge for AGI. https://t.co/6fZfTdx710 Table of Contents > Moravec’s Paradox > Moravec's Paradox in 2025 > Computer use may be the biggest opportunity

I am humbled and grateful to receive two grants from Open Philanthropy @open_phil to advance the safety of AI systems, co-led with my colleague @ysu_nlp. I'm also honored to be the first at @OhioState to receive Open Philanthropy funding. Most credit goes to the amazing students

🙏 Huge thanks to my amazing collaborators: @kunqian_us @sidthekidder @bestaskwisher @ShaddyGarg @hhsun1 @yunyao_li - couldn’t have done this without you! Also appreciate all discussions from @osunlp !

On average, open-source LLMs fine-tuned with EvoSchema outperform different baseline methods, highlighting a path towards more resilient NL2SQL systems that adapt as database schemas evolve over time.

💡 Why it matters: Database schemas are not static — they evolve 🔄. 🌍🌍 Big picture 🔸EvoSchema defines 10 schema perturbations (column- & table-level) and shows how schema shifts can break SOTA models. 🔸Column-level changes hurt a bit. 🔸Table-level schema changes hurt a lot.

🎉 Excited to share that our paper EvoSchema: Towards Text-to-SQL Robustness Against Schema Evolution was accepted at VLDB 2025! 🚀 📢 Reminder: join us at VLDB 2025 in London! 🗓️ Sept 2 (Tue), 10:45 AM – 12:15 PM 📍 Room Wordsworth 4F 📄 https://t.co/ZNAav4ZtoX #VLDB2025 #LLMs

Remember “Son of Anton” from the Silicon Valley show(@SiliconHBO)? The experimental AI that “efficiently” orders 4,000 lbs of meat while looking for a cheap burger and “fixes” a bug by deleting all the code? It’s starting to look a lot like reality. Even 18 months ago, my own

Announcing the @NeurIPSConf 2025 workshop on Imageomics: Discovering Biological Knowledge from Images Using AI! The workshop focuses on the interdisciplinary field between machine learning and biological science. We look forward to seeing you in San Diego! #NeurIPS2025

Attending #ICML2025 🇨🇦 this week! I’ll be co-organizing the Computer Use Agent Workshop @workshopcua on July 19th! Happy to chat about anything related to language agents — especially world modeling, scaling RL for agents, and multi-turn RL. Excited to meet old friends and

🚨 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 -

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 @YifeiLiPKU @HananeNMoussa @osunlp. 🌟AutoSDT: Scaling Data-Driven

Systematic reviews (SRs) drive evidence-based medicine, but months-long workflows can’t keep pace with today’s literature flood. Fully autonomous solutions promise speed, but the magic often fizzles - these models still skip pivotal trials, hallucinate findings, and bury the

⁉️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

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.

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

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