At #CVPR2026? Come by ExHall F 508 on Sun, Jun 7, 11:45 AM–1:45 PM MDT to chat about cryoSENSE — using compressive sensing with sparse and diffusion priors to enable higher-throughput cryo-EM while preserving structural resolution. #CryoEM #ComputationalImaging

🚨 New paper by my PhD student William Yuan. Conventional wisdom: stochasticity slows down sampling. Our result: in discrete diffusion, stochasticity can actually correct errors. 📌 We show this through strong data processing inequalities, proving that increasing stochasticity can contract accumulated sampling errors. ⚡ Inspired by this, we introduce Discrete Churn and Restart Sampling (DCRS) a training-free inference algorithm that leverages controlled stochasticity for error correction. 🔥 Up to 10× faster sampling on benchmarks while maintaining competitive quality. Paper: arxiv.org/abs/2605.26582

Sharing a thoughtful LessWrong piece by my colleague @darin_tsui on AI as biology’s digital microscope: how mechanistic interpretability can help turn biological AI models from black boxes into tools for discovery: lesswrong.com/posts/BxziXpLC… #LessWrong #MechInterp

Can we learn how protein language models (pLMs) work?👀 As a matter of fact, yes! I'm excited to shared that our paper, "Protein Circuit Tracing via Cross-layer Transcoders", has been accepted into ICML 2026! Check out our findings at protmech.github.io/ (1/n)

Thrilled to share that cryoSENSE has been accepted to #CVPR2026 🎉. Thanks to the amazing team: @zain_shabeeb, @saeedi_daniel, @darin_tsui, and @amiraliagz @gatechengineers @GTChBE @GeorgiaTech_ECE

Proud of this work from our lab; moving closer to a mechanistic understanding of protein language models.

🚨Excited to share ProtoMech: a framework for discovering the computational circuits inside protein language models (pLMs)! pLMs like ESM2 are powerful, but the computational mechanisms, or circuits, underlying their predictions remain poorly understood. (1/n)

New preprint🚨: cryoSENSE. We show that diffusion models as generative priors, along with sparse priors, can boost electron microscopy data throughput by reconstructing high-resolution cryo-EM images from compressed measurements arxiv.org/abs/2511.12931

It’s here! #Agents4Science recording is now on YouTube! 🏆 3 Best Paper talks ⚡️ 11 Spotlights 🧠 Panel on the future of AI agent-driven science 📚 Lessons surprises from this first-of-its kind conf Full analysis of submissions reviews coming soon! youtube.com/watch?v=7pXqAeed…

AstroAgents: A Multi-Agent AI for Hypothesis Generation from Mass Spectrometry Data astrobiology.com/2025/04/ast… #astrobiology #astrochemistry #AI