AI Professor @UCIrvine | Associate Director, AI in Science Institute | Formerly @blei_lab, @Princeton | Chair @aistats_conf 2025 | AI Resident @ChanZuckerberg
Irvine, California
Joined March 2015
- Tweets516
- Following606
- Followers3K
- Likes1.1K
The last few years have been tough for those applying for faculty positions. I'm happy to announce that my department has an opening in AI and ML.
AI has historically been one of our strengths. Statistics is literally just two floors below, and we have centers and institutes like the AI in Science Institute and the Center for Machine Learning.
Perks include: a great research environment, a politics-free work environment, proximity to the tech hubs in LA and Orange County, ... did I mention the beach?
recruit.ap.uci.edu/JPF10341
Stephan Mandt retweeted
Objects in robot demos are awfully patient 🙃
We’ve spent months on tasks where they aren’t. Catching balls, pouring into a moving pot, taking a bottle from someone walking by.
Two additions helped π0.5, RTC, & VLASH handle dynamic manipulation! More from our CoRL'26 oral in 🧵
Daniel & Jimin ran 1,500+ physical robot evaluations to put it to the test, with 50 runs per reported success rate.
As always, we’re making everything public: tempo-robot.github.io/
Diffusion models can do more than generate images: they can save us from transmitting all their detail.
Our IEEE BITS article reviews generative compression and near-optimal rate–distortion–realism tradeoffs. Led by @YiboYang, who did the lion’s share.
arxiv.org/pdf/2601.18932
Our paper "Trading off Controllability and Realism in Generative Physics Emulators" received an Outstanding Paper Award at the AI4Physics Workshop at #ICML 2026. Congrats to my co-authors, especially lead authors @f_immorlano and Elijah Tavares!
What diffusion guidance should *really optimize: the Bayesian posterior. #ICML2026
Promoted from Associate to Full Professor. Fewer letters, more committees. 🙂 Thanks to all the graduate students, postdocs, and colleagues. I wouldn't have made it here without you!
Thanks for having me, @kchonyc and Rajesh! It was a pleasure visiting the new AI Frontier Lab @ NYU.
If I had to bet on LLM infrastructure impact, this might become the most important paper from my lab. This ICLR paper intrinsically parallelizes language models, building on ideas from normalizing flows. 🚀
LLMs are autoregressive and slow? No! Parallel Token Prediction decodes multiple consistent tokens in one model call. PTP allows arbitrary dependencies in one call, unlike discrete diffusion. Practical: 2.4x speedup
github.com/mandt-lab/ptp
ICLR: Apr 23, morning poster P3-#608
Excited to see seven years of work come together: we can now consistently predict thermodynamic properties of fluid mixtures directly from molecular structure using machine learning. 🧪🤖
Our latest work just got accepted at Nature Communications: nature.com/articles/s41467-0… (1/4)
Our latest model takes this to a new level: predicting excess Gibbs energies of mixtures from the SMILES representations of their constituents. This enables predictions across temperatures and compositions, central to chemical process and solvent design. (3/4)
Huge congrats to my former postdoc and now professor of thermodynamics, Fabian Jirasek, for driving this research! (4/4)mv.rptu.de/en/dpts/ltd/chair…
Interested in Diffusion Models for data compression? Check out our new review paper 👇
We've known that diffusion models are theoretically very good lossy data compressors , but how can we actually implement this idea in practice? I discuss this and related topics in a new review article on diffusion-based generative compression arxiv.org/abs/2601.18932
Stephan Mandt retweeted
ProbML 2026 (formerly AABI) invites submissions on probabilistic ML (Bayesian & beyond), July 5 in Seoul (co-located with ICML). Website: probml.cc. Tracks: proceedings (PMLR), workshop, fast track. New focus includes healthcare & climate!
Submit by: 20 March 2026
Excited to see AABI evolve into ProbML, with plans to become a full conference next year!
linkedin.com/posts/probml_pr…
Excited to contribute to a growing scientific ecosystem in SoCal through our new AI in Science Institute at UCI.
Scientific AI raises long-term questions—central to our inaugural symposium, from agentic co-scientists to weather to biology.
Join us next year—sun included ☀️
Many thanks to our invited speakers for the great discussions:
Søren Brunak, @jmtomczak, @kchonyc, @jenssen_robert, @Tkaraletsos, Michael Mahoney, @SciPritchard, and @yuqirose.
Photo credit: Jakub Tomczak.
Congrats to @FelixDrRelax, Yang Meng, and Lukas Laskowski on a NeurIPS Spotlight! 🎉
A simple idea made practical, demonstrated on event sequences, for efficiently modeling mixed discrete-continuous data with transformers.
Check out our #Neurips Spotlight paper. Point process modeling made simple. 👇
How to model event sequences with real world variety: mixed data types, different lengths, …?
Meet FlexTPP, a unified transformer framework with discrete & continuous heads for health care, complex annotations and more!
NeurIPS spotlight, Fri 11am #2102!
openreview.net/forum?id=Mtws…
Recently gave a LEAP lecture at @Columbia and at @UCLA on a question I’m excited about: How can we design diffusion models for scientific inference—uncertainty-aware, calibrated, steerable, and heavy-tailed? youtube.com/watch?v=QeLZI4FR…