Author | Lightnews

Anirban Ray

@anirbanray.bsky.social

240 followers 350 following 50 posts

PhD Student working on bioimaging inverse problems with @florianjug.bsky.social at @humantechnopole.bsky.social + @tudresden.bsky.social | Prev: computer vision Hitachi R&D, Tokyo. 🔗: https://rayanirban.github.io/ Likes 🏸🏋️🏔️🏓 and ✈️

rayanirban.github.io

Posts Media Videos Starter Packs

Pinned

Anirban Ray @anirbanray.bsky.social · Nov 18

So exciting to see everyone here. A brief self-intro for others:

I am currently a PhD student with @florianjug.bsky.social. My work involves the application of AI in bioimage analysis. I am interested in the application of #GenAI to solve inverse problems with #DiffusionModels #FlowMatching #VAEs.

3 13

Reposted by Anirban Ray

Florian Jug @florianjug.bsky.social · 6h

I’m at #AIS25 today and tomorrow…
Where scientists, industry leaders, investors, and policymakers meet to explore the transformative impact of artificial intelligence on scientific discovery.
I think this is a very important conversation we must have NOW! 👍

4 1 16

Reposted by Anirban Ray

arxiv cs.CV @arxiv-cs-cv.bsky.social · 3d

Anirban Ray, Vera Galinova, Florian Jug
ResMatching: Noise-Resilient Computational Super-Resolution via Guided Conditional Flow Matching
https://arxiv.org/abs/2510.26601

Anirban Ray @anirbanray.bsky.social · 6d

needless to say! and much appreciated 😊

Anirban Ray @anirbanray.bsky.social · 7d

super cool work😎

mattie ✨ @mattierial.bsky.social · 7d

Generative Point Tracking with Flow Matching

My latest project with Adam W. Harley, @csprofkgd.bsky.social, Derek Nowrouzezahrai, @chrisjpal.bsky.social.

Project page: mtesfaldet.net/genpt_projpa...
Paper: arxiv.org/abs/2510.20951
Code: github.com/tesfaldet/ge...

1 1

Anirban Ray @anirbanray.bsky.social · 15d

“We may not win every battle, but we will win the war.” --- Such an appropriate characterization for posterior samplers. Each posterior sample fights its own battle against noise and degradation; some win, some lose. But the MMSE estimate wins the war 😉.
#iykuk #ImageRestoration

Reposted by Anirban Ray

lebellig @lebellig.bsky.social · 20d

Diffusion Transformers with Representation Autoencoders by Boyang Zheng, et al (arxiv.org/abs/2510.116...)

Unexpected result: swapping the SD-VAE for a pretrained visual encoder improves FID, challenging the idea that encoders' information compression is not suited for generative modeling!

1 15

Anirban Ray @anirbanray.bsky.social · Sep 23

👏👏👏

Anna Foix @afoix.bsky.social · Sep 23

Happy to share that ShapeEmbed has been accepted at @neuripsconf.bsky.social 🎉 SE is self-supervised framework to encode 2D contours from microscopy & natural images into a latent representation invariant to translation, scaling, rotation, reflection & point indexing
📄 arxiv.org/pdf/2507.01009 (1/N)

Reposted by Anirban Ray

OMIBS @ MBL @omibs-mbl.bsky.social · Aug 26

We had an awesome #OMIBS2025

Thanks to all the lecturers, staff members, vendor faculty, sponsors, and participants for making this an amazing course year!

1 1

Reposted by Anirban Ray

Simon Kohl @saakohl.bsky.social · Jul 22

Introducing Latent-X — our all-atom frontier AI model for protein binder design.

State-of-the-art lab performance, widely accessible via the Latent Labs Platform.

Free tier: platform.latentlabs.com
Blog: latentlabs.com/latent-x/
Technical report: tinyurl.com/latent-X

2 4 12

Anirban Ray @anirbanray.bsky.social · Jul 17

👏

Reposted by Anirban Ray

lebellig @lebellig.bsky.social · Jul 7

New episode in this line of work from @giannisdaras.bsky.social et al. on training diffusion models with mostly bad/low-quality/corrupted data (+few high-quality samples). This time for proteins!

📄 Ambient diffusion Omni: arxiv.org/pdf/2506.10038
📄 Ambient Proteins: www.biorxiv.org/content/10.1...

1 2 3

Anirban Ray @anirbanray.bsky.social · Jun 24

these are so beautiful 🤩.

Isabelle Zane @isabellease.bsky.social · Jun 24

Smita Krishnaswamy at #AIxBio25

Reposted by Anirban Ray

Mathurin Massias @mathurinmassias.bsky.social · Jun 18

New paper on the generalization of Flow Matching www.arxiv.org/abs/2506.03719

🤯 Why does flow matching generalize? Did you know that the flow matching target you're trying to learn *can only generate training points*?

w @quentinbertrand.bsky.social @annegnx.bsky.social @remiemonet.bsky.social 👇👇👇

2 17 55

Anirban Ray @anirbanray.bsky.social · Jun 16

Congratulations 🎉 🤩

Reposted by Anirban Ray

Albert Dominguez Mantes @albertdm.bsky.social · Jun 6

Spotiflow, our deep learning based spot detection method for microscopy, is now published in @natmethods.nature.com!
Since the pre-print, we have added many features, notably native 3D detection!
@maweigert.bsky.social @gioelelamanno.bsky.social @epfl-brainmind.bsky.social
Paper: rdcu.be/epIB7
(1/N)

Spotiflow: accurate and efficient spot detection for fluorescence microscopy with deep stereographic flow regression

Nature Methods - Spotiflow uses deep learning for subpixel-accurate spot detection in diverse 2D and 3D images. The improved accuracy offered by Spotiflow enables improved biological insights in...

rdcu.be

3 24 55

Anirban Ray @anirbanray.bsky.social · Jun 6

Really cool and clean idea 😇👏

arxiv cs.CV @arxiv-cs-cv.bsky.social · Jun 6

George Stoica, Vivek Ramanujan, Xiang Fan, Ali Farhadi, Ranjay Krishna, Judy Hoffman
Contrastive Flow Matching
https://arxiv.org/abs/2506.05350

Reposted by Anirban Ray

HMS Image Analysis Collaboratory @hms-iac.bsky.social · Jun 6

🎀✨Recording now available ✨🎀

youtu.be/jtDunWK8g1o?...

8 21

Reposted by Anirban Ray

Jia-Bin Huang @jbhuang0604.bsky.social · Jun 4

Kullback–Leibler (KL) divergence is a cornerstone of machine learning.

We use it everywhere, from training classifiers and distilling knowledge from models, to learning generative models and aligning LLMs.

BUT, what does it mean, and how do we (actually) compute it?

Video: youtu.be/tXE23653JrU

1 5 31

Anirban Ray @anirbanray.bsky.social · Jun 3

Very interesting. Congrats! 😀

Anirban Ray @anirbanray.bsky.social · May 27

Always found the connection between rectified flows and optimal transport a bit confusing. Glad to see some clarity. TL;DR: Rectified flows ≠ optimal transport. arxiv.org/abs/2505.19712

On the Relation between Rectified Flows and Optimal Transport

This paper investigates the connections between rectified flows, flow matching, and optimal transport. Flow matching is a recent approach to learning generative models by estimating velocity fields th...

arxiv.org

1 5

Reposted by Anirban Ray

lebellig @lebellig.bsky.social · May 21

"Energy Matching: Unifying Flow Matching and
Energy-Based Models for Generative Modeling" by Michal Balcerak et al. arxiv.org/abs/2504.10612
I'm not sure EBM will beat flow-matching/diffusion models, but this article is very refreshing.

2 8

Reposted by Anirban Ray

Julian Tachella @tachellajulian.bsky.social · May 19

New Feature in DeepInverse (deepinv.github.io):

🚀 Custom Diffusion Solver Design
DeepInverse now simplifies the process with:

✔ Standard SDEs (VP, VE, etc.)
✔ Pretrained denoisers for multiple noise levels
✔ ODE/SDE solvers (Euler, Heun)
✔ Noisy data fidelity terms for guidance

Redirecting to https://deepinv.github.io/deepinv/

deepinv.github.io

2 6

Reposted by Anirban Ray

Oliver Harschnitz @harschnitz.bsky.social · May 19

We will be kicking off the Neurogenomics Conference with two sessions on Neurodevelopment with talks from Wieland Huttner, @bassemh.bsky.social, @mareikealbert.bsky.social, @naelnadifkasri-lab.bsky.social, Yukiko Gotoh, @boyanbonev.bsky.social and others! #neurogen25

Oliver Harschnitz @harschnitz.bsky.social · May 17

Monday is the big day! Very much looking forward to welcoming all participants and speakers of the Neurogenomics Conference to @humantechnopole.bsky.social in Milan. It promises to be an exciting few days filled with amazing science.

1 4 18

Anirban Ray @anirbanray.bsky.social · May 19

Really interesting paper on per-frequency control in diffusion models: arxiv.org/abs/2505.112.... They tackle the frequency degradation rate imbalance of the forward process by enforcing Equal SNR across Fourier components. Finally, someone’s taking @sedielem.bsky.social blogs to heart 👀🔥

A Fourier Space Perspective on Diffusion Models

Diffusion models are state-of-the-art generative models on data modalities such as images, audio, proteins and materials. These modalities share the property of exponentially decaying variance and mag...

arxiv.org

Reposted by Anirban Ray

Sander Dieleman @sedielem.bsky.social · May 14

Here's the third and final part of Slater Stich's "History of diffusion" interview series!

The other two interviewees' research played a pivotal role in the rise of diffusion models, whereas I just like to yap about them 😬 this was a wonderful opportunity to do exactly that!

History of Diffusion - Sander Dieleman

YouTube video by Bain Capital Ventures

www.youtube.com

7 21