Jianyang Gu
@vimar_gu
Postdoc @ the Ohio State University
I'm excited to bring the Imageomics workshop to NeurIPS 2025! Consider submitting your work on ai4ecology, ai4conservation and general ai4science--if you're using images to learn something about the natural world, chances are it's a good fit for the imageomics workshop!
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
🚨 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,…
We're already using AI search systems every day for more and more complex tasks, but how good are they really? Challenge: evaluation is hard with no fixed ground truth! In Mind2Web 2, we use agents to evaluate agents. Really excited! Thanks to everyone who made this possible!
🔎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 -…
🔎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 -…
📢 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)
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…
🚨We just released the data generation code for RoboSpatial! 💾 github.com/NVlabs/RoboSpa… 📢 And yes, RoboSpatial is a #CVPR2025 Oral 🏆🔥
🔥 VLMs aren’t built for spatial reasoning — yet. They hallucinate free space. Misjudge object fit. Can’t tell below from behind We built RoboSpatial to tackle that — a dataset for teaching spatial understanding to 2D/3D VLMs for robotics. 📝 Perfect review scores @CVPR 2025
What's actually different between CLIP and DINOv2? CLIP knows what "Brazil" looks like: Rio's skyline, sidewalk patterns, and soccer jerseys. We mapped 24,576 visual features in vision models using sparse autoencoders, revealing surprising differences in what they understand.
Such an honor to be part of the 2025 Sloan Research Fellow cohort #SloanFellow! Excited to represent LLM + agent research and @OhioState. Grateful for the support from my family, all the great colleagues and students at @osunlp, and my mentors and collaborators! Thx…
🎉Congrats to the 126 early-career scientists who have been awarded a Sloan Research Fellowship this year! These exceptional scholars are drawn from 51 institutions across the US and Canada, and represent the next generation of groundbreaking researchers. sloan.org/fellowships/20…
❓Wondering how to scale inference-time compute with advanced planning for language agents? 🙋♂️Short answer: Using your LLM as a world model 💡More detailed answer: Using GPT-4o to predict the outcome of actions on a website can deliver strong performance with improved safety and…
People into agents, let me pitch something to you: 🌟 An agent that works across every platform (web, desktop & mobile) 🌟 Visual perception only, no messy & often incomplete HTML or a11y tree 🌟 SOTA performance across 6 agent benchmarks Sounds too good to be true? Continue ⬇️…
🚀 Can language agents automate data-driven scientific discovery? Not yet. But we're making strides. Introducing **ScienceAgentBench**: a new benchmark to rigorously evaluate language agents on 102 tasks from 44 peer-reviewed publications across 4 scientific disciplines. (1/10)
Is generation always the best way to use LLMs? 🤔 At least not for re-ranking! Excited to share our latest work: Attention in LLMs yields efficient zero-shot re-rankers. Introducing In-Context Re-ranking (ICR) - an efficient zero-shot re-ranking method leveraging LLM’s…