🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Why are there so many different methods for using diffusion models for inverse problems? 🤔 And how do these methods relate to each other? In this survey, we review more than 35 different methods and we attempt to unify them into common mathematical formulations.

🎉🎉Excited to share that “CryoSPIN” has been accepted to #NeurIPS2024! Special thanks to my amazing collaborators and supervisors David Lindell, Marcus Brubaker, and David Fleet Paper: arxiv.org/abs/2406.10455 Webpage: shekshaa.github.io/semi-amortized… Code is also released! 🧵[1/7]

I've been beyond stoked today about the Chemistry Nobel prize to my colleagues and to our field of AI for structural biology. And then my group surprised me with such a thoughtful gift!! I have the best lab! My heart is melting 🥹🥂🍾

Representation matters. Representation matters. Representation matters, even for generative models. We might've been training our diffusion models the wrong way this whole time. Meet REPA: Training Diffusion Transformers is easier than you think! sihyun.me/REPA/(🧵1/n)

We're developing and using AI to revolutionize scientific discovery - from predicting protein structures with #AlphaFold, to materials discovery with GNoME. Join our VP Science, Pushmeet Kohli, and Professor @fryrsquared as they explore how AI could lead to a new era of breakthroughs

This perspective can also be applied in science settings. After all, you don't want your AI system to hallucinate a result, leading to a Nature paper retraction 😅 One cool result here is by Zihui (Ray) Wu on developing principled plug-and-play Bayesian inversion approaches using

1/ 🔍 Wonder about the answer? cryo-EM ✖️ Foundation Model 🟰 ❓ cryo-EM ✖️ Flow Matching 🟰 ❓ cryo-EM ✖️ Diffusion Transformer 🟰 ❓ Excited to introduce our new work--cryoFM, the first cryo-EM foundation model for protein densities with flow matching, which generalizes to

#Tokenization is undeniably a key player in the success story of #LLMs but we poorly understand why. I want to highlight progress we made in understanding the role of tokenization, developing the core incidents and mitigating its problems. 🧵👇

Excited to share our AI+cryo-EM work! 🧬 🔬 Cryo-IEF: Foundation model trained on 65M particles 🤖 CryoWizard: automated structure pipeline 🎯 Making cryo-EM accessible to more labs Preprint: biorxiv.org/content/10.110… Code: github.com/westlake-repl/… #CryoEM #AI #StructuralBiology

I will be at NeurIPS and presenting our paper, 'CryoBench: Datasets and Benchmarks for Heterogeneous Cryo-EM Reconstruction' I would love to connect and discuss topics such as Generative Models for 3D Vision, Cryo-EM, AI4Science (Biology) or anything else! Please DM :)

BioEmu is out! 🎉 Very happy to see my internship project, integrating experimental data into biomolecular emulator training (PPFT), featured in the paper. Working with Yu Xie, Frank Noe and the amazing team was such a privilege🥰 Enjoy the paper!! 👇

CryoBench 🧊🪑is accepted at NeurIPS as a Spotlight! Poster session happening now! Minkyu Jeon We’ve been making a lot of improvements to the code and docs to make it as easy as possible to compute metrics ➡️ ez-lab.gitbook.io/cryobench The heterogeneity problem in cryo-EM is

#NeurIPS2024 check out our work: Cryo-EM images are intrinsically low dimensional at the MLSB workshop with Luke Evans Octavian-Vlad Murad Lars Dingeldein Roberto Covino & Marina Meila mlsb.io/papers_2024/Cr…

🚨New paper at #NeurIPS2024! We present Hydra, a mixture of neural fields 🐉🐉🐉 for ab initio cryo-EM reconstruction of complex mixtures. Hydra is our attempt at pushing the boundaries for even more extreme forms of heterogeneity in cryo-EM 🤯. This was joint work with an

Excited to share our work MatchAnything: We pre-train strong universal image matching models that exhibit remarkable generalizability on unseen multi-modality matching and registration tasks. Project page: zju3dv.github.io/MatchAnything/ Huggingface Demo: huggingface.co/spaces/LittleF…

How to use only 10% of training data to maintain 100.18% of the performance, and improve 94% on complex questions!

The proteome (189 proteins) of Ca. Sukunaarchaeum mirabile, a putative new phyla with the smallest known genome to date for an archaea. Its name honors the 🇯🇵god of sake and healing, called Sukunabikona genome ncbi.nlm.nih.gov/nuccore/AP0401… Alphafold2 preds zenodo.org/records/152719…

Excited to present CryoBoltz ❄️⚡, a multiscale guidance approach for steering AlphaFold3/Boltz-1 to sample structures that are consistent with experimental cryo-EM density maps. 🧵1/7 arxiv.org/abs/2506.04490 Joint work with Axel Levy Gordon Wetzstein & Ellen Zhong!