DPhil student Emily Jin has co-authored OXtal, a generative model that predicts molecular crystal structures in seconds from a 2D graph - a major advance on brute-force methods. The team will present at ICLR 2026 in Brazil on 24 April. Read more: www.cs.ox.ac.uk/news/2519-fu...

🔮Introducing OXtal – a new all-atom diffusion model for crystal structure prediction!

We tackle a grand challenge in computational chemistry: predicting the structure of crystalline solids directly from their chemical composition.

Paper: arxiv.org/abs/2512.06987
Blog Post: oxtal.github.io

1/8

📢 Interested in doing a PhD in generative models 🤖, AI4Science 🧬, Sampling 🧑‍🔬, and beyond? I am hiring PhD students at Imperial College London for the next application cycle.

🔗See the call below:
joeybose.github.io/phd-positions/

✨ And a light expression of interest: forms.gle/FpgTiuatz9ft...

SuperDiff goes super big!
- Spotlight at #ICLR2025!🥳
- Stable Diffusion XL pipeline on HuggingFace huggingface.co/superdiff/su... made by Viktor Ohanesian
- New results for molecules in the camera-ready arxiv.org/abs/2412.17762
Let's celebrate with a prompt guessing game in the thread👇

Vienna science ball

Super super excited to share our work SuperDiff 🦹‍♀️ for superimposing pretrained diffusion models at inference time 💪

Check out the 🧵 to see how we superimposed proteins as well as images, all thanks to a fast new density estimator. Curious to see what 🍩 & 🗺️ would produce?

The Superposition of Diffusion Models The Cambrian explosion of easily accessible pre-trained diffusion models suggests a demand for methods that combine multiple different pre-trained diffusion models without incurring the significant...

2.) The Superposition of Diffusion Models Using the Itô Density Estimator: openreview.net/forum?id=2o5...

Steering Masked Discrete Diffusion Models via Discrete Denoising... Generative modeling of discrete data underlies important applications spanning text-based agents like ChatGPT to the design of the very building blocks of life in protein sequences. However...

1.) 1. Steering masked discrete diffusion models via discrete denoising posterior prediction: openreview.net/forum?id=Omb...

2/2 Papers accepted at #ICLR2025. Congrats to all my co-authors 🥳. Definitely check out these works if you're interested in fine-tuning/composing diffusion models!

Papers in thread 🧵 below 👇

The Superposition of Diffusion Models Using the Itô Density Estimator The Cambrian explosion of easily accessible pre-trained diffusion models suggests a demand for methods that combine multiple different pre-trained diffusion models without incurring the significant co...

🧵(3/7)This is all due to an amazing team: @martaowesyou.bsky.social @lazaratan.bsky.social @joeybose.bsky.social @alextong.bsky.social

📄Paper: arxiv.org/abs/2412.17762
💻Code: github.com/necludov/sup...
🤗HuggingFace: huggingface.co/superdiff

The Superposition of Diffusion Models Using the Itô Density Estimator The Cambrian explosion of easily accessible pre-trained diffusion models suggests a demand for methods that combine multiple different pre-trained diffusion models without incurring the significant co...

I had a blast working with such an amazing team! @martaowesyou.bsky.social @joeybose.bsky.social @alextong.bsky.social @k-neklyudov.bsky.social

Check out our linked for details and examples!

📄Paper: arxiv.org/abs/2412.17762
💻Code: github.com/necludov/sup...
🤗HuggingFace: huggingface.co/superdiff

The Superposition of Diffusion Models Using the Itô Density Estimator The Cambrian explosion of easily accessible pre-trained diffusion models suggests a demand for methods that combine multiple different pre-trained diffusion models without incurring the significant co...

Work with an absolute dream of a team: @lazaratan.bsky.social @joeybose.bsky.social @alextong.bsky.social and @k-neklyudov.bsky.social 🤗🚀⚡️

📄Paper: arxiv.org/abs/2412.17762
💻Code: github.com/necludov/sup...
🤗HuggingFace: huggingface.co/superdiff

🧵(1/7) Have you ever wanted to combine different pre-trained diffusion models but don't have time or data to retrain a new, bigger model?

🚀 Introducing SuperDiff 🦹‍♀️ – a principled method for efficiently combining multiple pre-trained diffusion models solely during inference!

New paper just dropped! How do you combine pre-trained diffusion models without having to train a new one 🤓?

Turns out you can use our all new Ito density estimator 🔥 to compute densities under a diffusion model efficiently 🚀!

exciting new workshop announcement!! join us in Singapore for Frontiers in Probabilistic Inference: Learning Meets Sampling 🌏⚡️😃 details below 👇 #ICLR2025

This #ICLR2025 workshop on modern probabilistic inference sounds absolutely stunning! 🙌

Learning Sampling
🤝
Probabilistic Inference

Come join us in Singapore at #ICLR2025 to discuss the latest developments everywhere where Learning meets Sampling!

Organizers continued:

Michael Bronstein @mmbronstein.bsky.social
Max Welling
Arnaud Doucet @arnauddoucet.bsky.social
Aapo Hyvärinen

Part 2/2

🙏 Of course, this is co-organized with a dream team

Tara Akhound-Sadegh
Marta Skreta@martaowesyou.bsky.social
Yuanqi Du
Sarthak Mittal@sarthmit.bsky.social
Alex Tong@alextong.bsky.social
Kirill Neklyudov@k-neklyudov.bsky.social

Part 1/2

⚡We have an electric lineup of speakers and panelists:

Sitan Chen(Harvard)
Rianne Van Den Berg(MSR)
Ricky Chen(Meta)
Anna Korba(ENSAE Paris, CREST)
Marylou Gabrié(ENS)
Emtiyaz Khan(RIKEN)
Grant Rotskoff(Stanford)
Francisco Vargas(Xaira, Cambridge)
Kyle Cranmer (University of Wisconsin-Madison)

🚨 We invite submissions on sampling, Bayesian inference, accelerating sampling in AI4Science, Generative models in Probabilistic inference, and more!

🤖 We invite submissions along 3 tracks:

1.) Research Papers

2.) Challenges and Reflections

3.) Benchmarks and Datasets

Deadline is Deb 3 AOE!

🔊 Super excited to announce the first ever Frontiers of Probabilistic Inference: Learning meets Sampling workshop at #ICLR2025 @iclr-conf.bsky.social!

🔗 website: sites.google.com/view/fpiwork...

🔥 Call for papers: sites.google.com/view/fpiwork...

more details in thread below👇 🧵

Self Consuming Generative Models under Curated Data Provably Optimize Human Preferences (Spotlight), led by Damien Ferbach

arxiv.org/abs/2407.09499

Metric Flow Matching for Smooth Interpolations on the Data Manifold, led by Kacper Kapusniak

arxiv.org/abs/2405.14780

Fisher Flows for discrete generative modeling led by Oscar Davis

arxiv.org/abs/2405.14664

FoldFlow-2 for sequence-conditioned protein structure design. Led by Guillaume Huguet and James Vuckovic

arxiv.org/abs/2405.20313

I'll be at #NeurIPS2024 next week presenting 4 papers all on generative models!

Happy to meet old friends and new ones at all the fun events!

Papers in thread 🧵

Mila is such a large community. One starter pack just isn’t enough! After @josephdviviano.bsky.social’s Mila list filled up, I decided to make another one. Will continue to add members until this one is full too.

go.bsky.app/9nXTDHo

LoG Conference Tutorial on Geometric Generative Models -- Happening now with @joeybose.bsky.social , @alextong.bsky.social and Heli Ben-Hamu.

Livestream: www.youtube.com/@learningong...

#LoG2024

Attending the Learning on Graphs conference (logconference.bsky.social) this year? Come check our introductory tutorial to building Geometric Generative Models co-delivered with Heli Ben-Hamu and
Alex Tong (alextong.bsky.social)

More details and forthcoming code: sites.google.com/view/ggm-log...