🚀 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

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.

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!

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

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 Hugging Face. Learn more: simonsfoundation.org/2024/12/02/new…

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

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.🧵

📢Join our next talk by Saif Syed: Scalable sampling of multi-modal distributions using sequential Monte Carlo samplers 🗓️ Mar 25 | 9:30am PT • 12:30pm ET • 4:30pm London 📍Zoom us06web.zoom.us/j/82032740738?… 🎬Youtube youtube.com/@MonteCarloSem… 📧Mailinglist groups.google.com/u/0/g/internat…

🦋 Life update: I am joining the Dept. of ECE (JHU ECE) Johns Hopkins University as an Assistant Professor in Fall 2025! I will also be part of the Data Science and AI Institute (Johns Hopkins Data Science and AI Institute), advancing AI for healthcare and biomedicine. More info on my website: peirong26.github.io.

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…

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

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

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…

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/

#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

Make sure to get your tickets to #AABI2025 if you are in Singapore on April 29 (just after #ICLR2025) and interested in probabilistic ML, inference, and decision-making! Tickets (free but limited!): lu.ma/5syzr79m More info: approximateinference.org #ProbML #Bayes #UQ

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!

We have a fantastic lineup of speakers who have made deep contributions to open-source in ML, e.g. Sara Hooker, Dr. Chris Rackauckas, Matthew Johnson, Tri Dao, Stella Biderman @ ICML, and Evan Shelhamer!