Scientific Knowledge Emerges in LLMs and YOU CAN Access It (via sampling)!
🔥🔥🔥New blog to summarize what we have learned from evaluating LLMs for several optimization, decision-making, and planning problems in science with truly impressive performances!
#ICLR2025 Oral
LLMs often struggle with reliable and consistent decisions under uncertainty 😵💫 — largely because they can't reliably estimate the probability of each choice.
We propose BIRD 🐦, a framework that significantly enhances LLM decision making under uncertainty.
BIRD…
Built a new ML library? Maintain a crucial project? Improved OSS practices? Your work deserves recognition! Submit your contributions to the CODEML workshop @ #ICML2025. We're championing open-source in ML. 💻✨ Deadline May 19.
codeml-workshop.github.io/codeml2025/
If you know data live on a manifold, you can hardwire this prior knowledge in diffusion model to make generation more accurate & data efficient.
What if there is also a group structure, like in protein design & quantum problem? Use it to do even better -
itsdynamical.github.io/article/2025/0…
We are hiring a student researcher at Google DeepMind to work on fundamental problems in discrete generative modeling!
Examples of our recent work:
masked diffusion: arxiv.org/abs/2406.04329
learning-order AR: arxiv.org/abs/2503.05979
If you find this interesting, please send an…
RFdiffusion => generative binder design.
RFdiffusion2 => generative enzyme design.
It's rare to find scientists with deep knowledge in chemistry, machine learning, and software engineering like Woody. The complexity of enzymes matches the complexity of his skills. Check out RFD2
RFdiffusion => generative binder design.
RFdiffusion2 => generative enzyme design.
It's rare to find scientists with deep knowledge in chemistry, machine learning, and software engineering like Woody. The complexity of enzymes matches the complexity of his skills. Check out RFD2
Make sure to get your tickets to AABI if you are in Singapore on April 29 (just after #ICLR2025) and interested in probabilistic modeling, inference, and decision-making!
Tickets (free but limited!): lu.ma/5syzr79m
More info: approximateinference.org#ICLR2025#ML
I'm happy to announce that v2 of my RL tutorial is now online. I added a new chapter on multi-agent RL, and improved the sections on 'RL as inference' and 'RL+LLMs' (although latter is still WIP), fixed some typos, etc.
arxiv.org/abs/2412.05265…
🚀 Rising Star Workshops for Junior/Senior PhDs, and Postdocs!
🌟 Don't miss these career-boosting opportunities!
notion.so/List-of-Rising…
Please share with your peers, students, and anyone who might benefit! #PhD#Postdoc#Academia#RisingStars
🦋 Life update: I am joining the Dept. of ECE (@JHUECE) @JohnsHopkins
as an Assistant Professor in Fall 2025! I will also be part of the Data Science and AI Institute (@HopkinsDSAI), advancing AI for healthcare and biomedicine. More info on my website: peirong26.github.io.
Excited to share our new paper on "Reversal Blessing" - where thinking BACKWARDS makes language models smarter on some multiple-choice questions! We found that right-to-left (R2L) models consistently outperform traditional left-to-right (L2R) models on certain reasoning tasks.🧵
Interested in learning about Kernel
Discrepancies❓
Maximum Mean Discrepancy
Hilbert-Schmidt Independence Criterion
Kernel Stein Discrepancy
🧐 Don't know where to begin?
👀 Check out my Practical Introduction to Kernel Discrepancies: MMD, HSIC & KSD!
arxiv.org/abs/2503.04820
We present InverseBench, a framework for benchmarking plug-and-play diffusion approaches for inverse problems in physical sciences. (#ICLR2025 Spotlight)
PnP diffusion approaches are attractive for scientific inverse problems because they offer flexibility in incorporating…
What can swimming bacteria teach us about how the ocean’s layers mix? @PolymathicAI recently released two massive datasets for training artificial intelligence models to tackle problems across scientific disciplines, available on @huggingface. Learn more: simonsfoundation.org/2024/12/02/new……
A beautifully written paper extending the probability flow ODE used in modern diffusion models to infinite-dimensional spaces that tested to be more efficient on some PDEs!
It is concise and builds up very well to the ideas, also introduces preliminaries for completeness
Excited to attend my first #ACSSpring2025 in San Diego next week! I’ll be sharing some of our latest work and can’t wait to meet everyone! If you’ll be there, let’s connect and chat about all things AI & Chemistry!
As one of the people who popularized the field of diffusion models, I am excited to share something that might be the “beginning of the end” of it. IMM has a single stable training stage, a single objective, and a single network — all are what make diffusion so popular today.
As one of the people who popularized the field of diffusion models, I am excited to share something that might be the “beginning of the end” of it. IMM has a single stable training stage, a single objective, and a single network — all are what make diffusion so popular today.
141 Followers 334 FollowingPhD candidate in Machine Learning at @imperialcollege supervised by @markvanderwilk. Interested in causality and Bayesian machine learning.
582 Followers 1K FollowingAssistant Professor @EECS_UTK, PhD @CS_UVA. Focused on machine learning, security, and privacy. More at https://t.co/ZTNOPr69cL
167 Followers 218 FollowingFirst-year CS PhD student @Cornell @Cornell_Tech; Prev undergrad @Tsinghua_Uni; Working on ML and AI4Science. email: [email protected]
5K Followers 826 FollowingPostdoctoral fellow at @Harvard_Data | Former computer science PhD with @Blei_Lab at @Columbia University | Researching AI + world models
904 Followers 700 Following@BWFund CASI fellow | Postdoc @UWproteindesign | @NUChemistry @CHADNANO alum | De novo protein design for programmable self-assembly
2K Followers 2K FollowingJunior fellow at the Society of Fellows at @Harvard and @iaifi_news fellow, incoming Assistant Professor at @Harvard and the @KempnerInst views my own
75 Followers 149 FollowingPhD student @Columbia working towards approaching the theoretical upper bound of how much information we can read out from the brain 🧠
963 Followers 297 FollowingResearch scientist @nvidia | postdoc @caltech | PhD @univienna | former research intern @MetaAI and @nvidia | views are my own
7K Followers 3K FollowingInformation and news account for BWF, a private #foundation that supports #biomedical research, career development for scientists, and #stem education in N.C.
6K Followers 173 FollowingWe study mathematical principles of learning, perception & action in brains & machines. Funded by Gatsby Charitable Foundation.
Also on bluesky & mastodon.
1K Followers 2K FollowingI have worked in medical imaging analysis,statistical learning,machine learning,genetic analysis,mathematical psychology,and AI in two-sided markets。
4K Followers 2K FollowingAssistant Prof. @ Stanford BASE, Genetics & Computer Science (courtesy). Lead the predictive genomics lab of ML & single cell/spatial genomics, focus on heart
13K Followers 2K FollowingSVP and Head of Biomedical AI @Xaira_Thera; Associate Prof @UofT; Chief AI Officer @UHN; former PHD, CS @Stanford; opinions my own. #AI #healthcare #biology
170 Followers 210 FollowingBiophysics, information processing, collective behaviors. Associate research scientist at @FlatironInst. @HenryHMattingly.bsky.social. Views are my own.
3K Followers 178 FollowingResearch Scientist at Google Deepmind. Previous PhD with @wellingmax at the Univ. of Amsterdam, Research intern at Qualcomm AI Research and Google Brain.
396 Followers 242 FollowingRL with uncertainty foundation; Assistant Professor in JHU ECE&DSAI @JohnsHopkins; Postdoc in @Caltech; Ph.D. in CMU (@CMU_ECE); BEng in Tsinghua @Tsinghua_Uni
1K Followers 505 FollowingResearch Scientist at @GoogleDeepMind | Ex @apple MLR; Stat / ML PhD Oxford @oxcsml
Working on diffusions, optimal transport and Monte Carlo
Views are my own
2K Followers 149 FollowingProfessor at NYU; Scientific Director, Ctr for Computational Neurocience, Flatiron Institute. Research in Computational Vision (neurons, perception, machines).
4K Followers 159 Followingteaching machines🤖 to learn🔍 and fantasize🪄
now 🇬🇧@ImperialCollege @ICComputing
ex @MSFTResearch @CambridgeMLG
helping @aistats_conf 24-26
31K Followers 2K FollowingDirector, @knightcolumbia. Editor, @just_security. Formerly @ACLU. This is my personal account. Also: @jameeljaffer.bsky.social & @[email protected].
167 Followers 218 FollowingFirst-year CS PhD student @Cornell @Cornell_Tech; Prev undergrad @Tsinghua_Uni; Working on ML and AI4Science. email: [email protected]
21K Followers 321 FollowingAdvancing the frontiers of basic science through grantmaking, research and public engagement. Sign up for our newsletter: https://t.co/s7KhKAFrjE
2K Followers 24 FollowingThe Berger lab at @MIT_CSAIL works on a diverse set of problems in computational biology. Account run by lab members. Also @bergerlab.bsky.social.
2K Followers 408 FollowingCourant Institute of Mathematical Sciences, home of @NYUniversity's Math and Computer Science departments. https://t.co/rlQfyJ0l9l