lazaratan.bsky.social
Lazar Atanackovic
@lazaratan.bsky.social
50 followers 130 following 3 posts
Incoming Assistant Prof, University of Alberta. Research Fellow at Amii. Currently, postdoc fellow the Broad Institute.
Posts Media Videos Starter Packs
lazaratan.bsky.social
Lazar Atanackovic @lazaratan.bsky.social · Mar 6
Happy to announce that SuperDiff got a spotlight at #ICLR2025! 🪩🪩

Can you guess the prompts that generated the images in our prompt guessing game?
k-neklyudov.bsky.social
Kirill Neklyudov @k-neklyudov.bsky.social · Mar 6
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👇
1
Reposted by Lazar Atanackovic
khrovatin.bsky.social
khrovatin.bsky.social @khrovatin.bsky.social · Feb 24
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
1 3
Reposted by Lazar Atanackovic
joeybose.bsky.social
Joey Bose @joeybose.bsky.social · Jan 22
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 👇
4 2 16
Reposted by Lazar Atanackovic
k-neklyudov.bsky.social
Kirill Neklyudov @k-neklyudov.bsky.social · Jan 22
We've been sharing these projects during the year, but today, they have been accepted at #ICLR2025 (1-3) and #AISTATS2025 (4)
1 1 6
Reposted by Lazar Atanackovic
lebellig.bsky.social
lebellig @lebellig.bsky.social · Jan 5
"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...
4 22
Reposted by Lazar Atanackovic
martaowesyou.bsky.social
Marta Skreta @martaowesyou.bsky.social · Dec 28
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?
k-neklyudov.bsky.social
Kirill Neklyudov @k-neklyudov.bsky.social · Dec 28
🧵(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!
1 3 23
Reposted by Lazar Atanackovic
martaowesyou.bsky.social
Marta Skreta @martaowesyou.bsky.social · Dec 28
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
2 6
lazaratan.bsky.social
Lazar Atanackovic @lazaratan.bsky.social · Dec 28
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...
arxiv.org
1 6
lazaratan.bsky.social
Lazar Atanackovic @lazaratan.bsky.social · Dec 28
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...
k-neklyudov.bsky.social
Kirill Neklyudov @k-neklyudov.bsky.social · Dec 28
🧵(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!
1 2