Happy to announce that SuperDiff got a spotlight at #ICLR2025! 🪩🪩 Can you guess the prompts that generated the images in our prompt guessing game?

Kirill Neklyudov@k-neklyudov.bsky.social · last yr.

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👇

To figure out what it takes to make flow matching models solve single-cell biology questions, I discussed with Alessandro Palma, Doron Haviv, and Lazar Atanackovic. The insights they shared are presented here: tinyurl.com/278s5m58 @dorontheviking.bsky.social @lazaratan.bsky.social

Matching flows to data

Models that fit like water in a vessel.

tinyurl.com

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 👇

We've been sharing these projects during the year, but today, they have been accepted at #ICLR2025 (1-3) and #AISTATS2025 (4)

"The Superposition of Diffusion Models using the Îto Density Estimator" (@martaowesyou.bsky.social, @lazaratan.bsky.social et al.) It's nice to see an easy-to-compute log-likelihood estimator for SDE sampling of diffusion models (not just ODE) 📄 arxiv.org/abs/2412.17762 🐍 github.com/necludov/sup...

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?

Kirill Neklyudov@k-neklyudov.bsky.social · 2y ago

🧵(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!

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

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...

arxiv.org

Thrilled to share our latest work, SuperDiff! 🚀 A principled way for combining pre-trained diffusion models solely at inference time! We provide a new way for estimating density (w/o divergence) and show its use for mixing concepts! Check out🧵 for details! bsky.app/profile/k-ne...

Kirill Neklyudov@k-neklyudov.bsky.social · 2y ago

🧵(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!