Assistant Professor @GTChBE, @UCBerkeley @RiceUniversity Alumni, #Nanoscience #ElectronMicroscopy #AI4Science 👩🏻🔬🔬🤖
Atlanta, GA
Joined September 2013
- Tweets353
- Following647
- Followers1.2K
- Likes2.4K
Happy to share a new preprint from my group on polarity-resolved imaging of active Janus nanoparticles in liquid-phase TEM, led by @isabelpanicker and in collaboration with @katy_requejo, @moshe_assaf, and colleagues at UC Berkeley, UChicago, and the @molecularfndry.
If you have ever wondered which direction the catalytic side of a nanomotor is pointing when it makes active jumps, we can now visualize that directly for ~100 nm particles. Using the power of liquid-phase TEM together with SAM-EM, we can distinguish the high-contrast Pt side from the low-contrast polystyrene side and correlate particle polarity with its motion in the presence of chemical fuel.
If you want to read more, check out the manuscript!
doi.org/10.26434/chemrxiv.15…
@gatechengineers @GTChBE
Vida Jamali retweeted
Lab meetings don’t always have to be so formulaic
go.nature.com/4gb59mk
Vida Jamali retweeted
7 teams funded in final year of #Scialog: Automating Chemical Laboratories, co-sponsored by Beckman Foundation, Research Corporation for Science Advancement @RCSA1, and Frederick Gardner Cottrell Foundation. Congrats! Read the full announcement: rescorp.org/2026/07/7-teams-…
Vida Jamali retweeted
Protein fitness landscapes are simpler under evolutionary distributions!
We show that much of the high-order epistasis observed in fitness landscapes is substantially diminished when analyzed under their natural evolutionary distributions. biorxiv.org/content/10.64898… (1/n)
Vida Jamali retweeted
🚀 New preprint: What happens when AI agents investigate the origins of life?
We introduce ASTRA, a multi-agent system that reconstructed 2,850 plausible pathways for amino acid synthesis.
📄 chemrxiv.org/doi/abs/10.2643…
🌐 astraagents.github.io/
Vida Jamali retweeted
Proud of our ProtoMech team! Excited to see ProGenMech bring circuit tracing to autoregressive protein language models at the @icmlconf Mechanistic Interpretability Workshop.
Excited to share that our paper, ProGenMech, has been accepted to the Mechanistic Interpretability Workshop at ICML 2026!
Here, we bring circuit tracing to life in ProGen3, an autoregressive protein language model! (1/n)
Paper: arxiv.org/abs/2606.16044
Vida Jamali retweeted
Excited to share that our paper, ProGenMech, has been accepted to the Mechanistic Interpretability Workshop at ICML 2026!
Here, we bring circuit tracing to life in ProGen3, an autoregressive protein language model! (1/n)
Paper: arxiv.org/abs/2606.16044
Vida Jamali retweeted
A PhD's success depends more on the fit between the student, the advisor, and the lab than on the specific topic being studied (it barely matters at all).
Similarly, a lab's success depends more on how excited (or miserable) its researchers are than on the precise project they are working on (it could be virtually anything).
This information isn't in papers or in grant proposals, you have to ask the researchers.
Vida Jamali retweeted
🚨 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
Vida Jamali retweeted
The landscape of AI x bio is quickly changing. In this LessWrong piece, I give my perspective on leveraging AI as biology's digital microscope and how we can leverage mechanistic interpretability for scientific discovery
lesswrong.com/posts/BxziXpLC…
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
Vida Jamali retweeted
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
Vida Jamali retweeted
Happy to share our new work published in @acsnano "Quantifying Photochemical Propulsion in Light-Powered Janus Micromotors". A collaboration among @BustamanteLab, Alivisatos lab and the Molecular Foundry
pubs.acs.org/doi/10.1021/acs…
Vida Jamali retweeted
Happy to share that our latest work at UC Berkeley is now published in @acsnano. A collaboration among @BustamanteLab, Alivisatos lab and the Molecular Foundry @molecularfndry.
Quantifying Photochemical Propulsion in Light-Powered Janus Micromotors
pubs.acs.org/doi/10.1021/acs…
Vida Jamali retweeted
Excited to share that ProtoMech, our mechanistic interpretability tool for protein language models, has been accepted to ICML 2026! 🎉
#ICML #ICML2026 #MechanisticInterpretability #ProteinLanguageModels #AI4Science #ComputationalBiology #MachineLearning #Interpretability #BioAI #DeepLearning
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)
Vida Jamali retweeted
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)
Happy to share a collaborative project from my postdoctoral work that is now published in ACS Nano, with @katy_requejo leading the work as the first author.
This was the last project I worked on during my postdoc at Berkeley, and it continued over the past few years while I have been at Georgia Tech, making it especially exciting to finally see it published.
We investigated the mechanics of photochemical propulsion in Janus micromotors and quantified the propulsion forces at the single-particle level. 🔬 🚀
It was a pleasure to be part of this collaboration.
Happy to share that our latest work at UC Berkeley is now published in @acsnano. A collaboration among @BustamanteLab, Alivisatos lab and the Molecular Foundry @molecularfndry.
Quantifying Photochemical Propulsion in Light-Powered Janus Micromotors
pubs.acs.org/doi/10.1021/acs…
Vida Jamali retweeted
Precision is the heart of nanotechnology. Nowhere is that more evident than in the work of University of Chicago President and renowned chemist Paul Alivisatos, whose latest study in ACS Nano provides a definitive look at the mechanics of photochemical propulsion.
Joining with a team of researchers from UC Berkeley, the group explored the dynamics of Janus micromotors—asymmetric particles that convert light into directed motion. By moving beyond bulk observations to a single-particle framework, the team has quantified the exact force behind the "swim," capturing measurements in the 4.5–6.2 pN range.
The Result: A new blueprint for bridging the gap between chemical energy and mechanical work. Link: shorturl.at/hyAS8
#UChiChemistry #UChicago #UCBerkeley #AlivisatosLab #Nanoscience #ResearchInnovation #Janusmicromotors #nano
Vida Jamali retweeted
As the final meeting of #Scialog: Automating Chemical Laboratories comes to a close, many thanks to our participants and cosponsors for a fun and fruitful initiative! – with @BeckmanFnd, Frederick Gardner Cottrell Foundation, Walder Foundation
Excited to share our new paper "Thinking Microscopes: Agentic AI and the Future of Electron Microscopy" nature.com/articles/s41524-0…
A couple of months back, @amiraliagz , Josh Kacher, and I started on this idea that what if microscopes didn’t just collect data, but also helped design experiments, adaptively control the experiments in real time, and come up with new scientific hypotheses? Then we started putting this article together. How agentic AI can turn electron microscopes into a partner in discovery.
We also talk about what is needed to get there.
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
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