Check out PaperSearchQA, which I'll present at EACL in Morocco this March! We built an RL training environment for teaching LLMs to search and reason over scientific papers. 60k question-answer pairs 16M papers to search over benchmarks. RL training improves the model.

Excited to share that our lab’s latest work, Melan-Dx, a knowledge-enhanced vision-language framework for improving the differential diagnosis of melanocytic neoplasms in pathology, is now published in @npjDigitalMed! Read it at: nature.com/articles/s41746-0… @PennPathLabMed #DigitalPathology #Dermpath

We're hiring! The Nirschl & Kolb (@hckolb ) labs @UWMadison are seeking a Scientist I/II to help develop novel PET tracers for neurodegenerative diseases. - Tissue assays, autoradiography, SPR, protein biochem experience desired. Apply here: jobs.wisc.edu/jobs/nirschl-s… #PETimaging

Amazing work, Zhi!

📢 Excited to introduce TissueLab — the first co-evolving, open-source agentic AI ecosystem to transform medical image analysis, copilot clinical decisions & accelerate scientific discovery, with SOTA performance compared to other VLM and GPT-5. Simply ask any research/clinical question! TissueLab will: ✅ Design the workflow for you. ✅ Write the python code. ✅ Execute the workflow and generate answer. 🧵1/n Online portal: tissuelab.org Read preprint: arxiv.org/abs/2509.20279 Blog: linkedin.com/pulse/how-agent…

🧬 What if we could build a virtual cell to predict how it responds to drugs or genetic perturbations? Super excited to introduce CellFlux at #ICML2025 — an image generative model that simulates cellular morphological changes from microscopy images. yuhui-zh15.github.io/CellFlu… 💡 Key Innovation: We frame perturbation prediction as a distribution-to-distribution learning problem, mapping control cells to perturbed cells within the same batch to mitigate biological batch artifacts, and solve it using flow matching. 📊 Results: ✅ 35% higher image fidelity ✅ 12% greater biological accuracy ✅ New capabilities: batch effect correction & trajectory modeling 🎯 Impact: Paving the way for faster drug discovery and deeper biological insights. 📍 Poster: Tue 7/15, 11:00 AM – 1:30 PM, #301 🙏Huge thanks to all my brilliant collaborators: @hhhhh2033528 (co-lead; now Harvard AIM PhD! 🎉) @ChenyuW64562111 @TianhongLi6 @zoewefers @jnirsch @jmhb0 @DaisyYDing @Ale9806_ @Prof_Lundberg @yeung_levy! #MachineLearning #ComputerVision #ComputationalBiology #DrugDiscovery #AIforScience #CVforScience

"Dr. Dirk Keene, a professor and the director of neuropathology at UW Medicine who leads the brain bank, said if federal funding dries up, he’ll go to almost any end to 'honor the gift' of people's donation." nbcnews.com/health/health-ne…

Today, the Wisconsin Brain Donor Program and Wisconsin ADRC join the national observance of #BrainDonorAwarenessDay to recognize and honor the individuals and families who have made the extraordinary decision to donate their brains to science. Learn more at adrc.wisc.edu/brain-donation.

My closed collaborator Prof. Jeff Nirschl @jnirsch has started his research lab at University of Wisconsin!!🎉 Dr. Nirschl has a rare combination of deep expertise in both medicine/pathology and AI/ML. Please check out the two open positions in his lab: Scientific software developer jobs.wisc.edu/jobs/digital-p… Researcher and Laboratory Manager - Computational Neuropathology jobs.wisc.edu/jobs/researche…

Introducing MicroVQA: A Multimodal Reasoning Benchmark for Microscopy-Based Scientific Research #CVPR2025 ✅ 1k multimodal reasoning VQAs testing MLLMs for science 🧑‍🔬 Biology researchers manually created the questions 🤖 RefineBot: a method for fixing QA language shortcuts 🧵

🚨Large video-language models LLaVA-Video can do single-video tasks. But can they compare videos? Imagine you’re learning a sports skill like kicking: can an AI tell how your kick differs from an expert video? 🚀 Introducing "Video Action Differencing" (VidDiff), ICLR 2025 🧵

🚀 Introducing Temporal Preference Optimization (TPO) – a video-centric post-training framework that enhances temporal grounding in long-form videos for Video-LMMs! 🎥✨ 🔍 Key Highlights: ✅ Self-improvement via preference learning – Models learn to differentiate well-grounded from inaccurate responses without manual annotations. ✅ Multi-level temporal grounding – Effectively captures both localized segments and comprehensive video sequences. ✅ Efficient and scalable – Utilizes only 10k video QA pairs for post-training and can scale seamlessly to larger datasets. ✅ Proven performance – TPO enhances two state-of-the-art Video-LMMs on LongVideoBench, MLVU, and Video-MME. 🔥 LLaVA-Video-TPO is now the top-performing 7B model on Video-MME, highlighting TPO's potential in advancing temporal reasoning. This work was co-led with the talented undergraduate @rui__li, alongside fantastic collaborators @Zhang_Yu_hui and Zeyu Wang, and advised by @yeung_levy!

Biomedical datasets are often confined to specific domains, missing valuable insights from adjacent fields. To bridge this gap, we present BIOMEDICA: an open-source framework to extract and serialize PMC-OA. 📄Paper: lnkd.in/dUUgA6rR 🌐Website: lnkd.in/dnqZZW4M

1. When you hit your 40’s, you’ll see 2 types of people: Those who took care of themselves and those who did not. 2. Lifting weights is investing in your future self. Start now to be functional well into your 80s while increasing your attractiveness.

How can we build an Al Virtual Cell 🔮🧬 that simulates all functions and interactions of a cell? How will it transform research and drive breakthroughs in programmable biology, drug discovery and personalized medicine? 🚀 Take a look at our Perspective! arxiv.org/pdf/2409.11654