Lightnews — Scholar-powered news

Joey Bose @joeybose.bsky.social · 27d

📢 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...

Joey Bose

Personal website powered by Jekyll

joeybose.github.io

2 5

Reposted by Joey Bose

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 4 14

Reposted by Joey Bose

Michael Bronstein @mmbronstein.bsky.social · Jan 26

Vienna science ball

1 43

Reposted by Joey Bose

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?

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

Joey Bose @joeybose.bsky.social · Jan 22

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

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...

openreview.net

5

Joey Bose @joeybose.bsky.social · Jan 22

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

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...

openreview.net

1 1 4

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 Joey Bose

Kirill Neklyudov @k-neklyudov.bsky.social · Dec 28

🧵(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...

arxiv.org

1 3 15

Reposted by Joey Bose

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

Reposted by Joey Bose

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

Reposted by Joey Bose

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 7 44

Joey Bose @joeybose.bsky.social · Dec 28

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 🚀!

Kirill Neklyudov @k-neklyudov.bsky.social · Dec 28

🧵(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...

arxiv.org

5 20

Reposted by Joey Bose

Marta Skreta @martaowesyou.bsky.social · Dec 18

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

Joey Bose @joeybose.bsky.social · Dec 18

🔊 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👇 🧵

2 9

Reposted by Joey Bose

Marvin Schmitt @marvin-schmitt.com · Dec 18

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

Learning Sampling
🤝
Probabilistic Inference

Joey Bose @joeybose.bsky.social · Dec 18

🔊 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👇 🧵

1 16

Reposted by Joey Bose

Kirill Neklyudov @k-neklyudov.bsky.social · Dec 18

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

Joey Bose @joeybose.bsky.social · Dec 18

🔊 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👇 🧵

1 10

Joey Bose @joeybose.bsky.social · Dec 18

Organizers continued:

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

Part 2/2

3

Joey Bose @joeybose.bsky.social · Dec 18

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

Tara Akhound-Sadegh
Marta [email protected]
Yuanqi Du
Sarthak [email protected]
Alex [email protected]
Kirill [email protected]

Part 1/2

1 3

Joey Bose @joeybose.bsky.social · Dec 18

⚡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)

1 1 5

Joey Bose @joeybose.bsky.social · Dec 18

🚨 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!

1 6

Joey Bose @joeybose.bsky.social · Dec 18

🔊 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👇 🧵

2 19 84

Joey Bose @joeybose.bsky.social · Dec 7

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

arxiv.org/abs/2407.09499

1 3

Joey Bose @joeybose.bsky.social · Dec 7

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

arxiv.org/abs/2405.14780

1 1 3

Joey Bose @joeybose.bsky.social · Dec 7

Fisher Flows for discrete generative modeling led by Oscar Davis

arxiv.org/abs/2405.14664

1

Joey Bose @joeybose.bsky.social · Dec 7

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

arxiv.org/abs/2405.20313

1 1

Joey Bose @joeybose.bsky.social · Dec 7

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 🧵

1 2 20