I used to have a lot attention to detail before llms 😅 feel like gradually its declining 🤦♂️
Ramith Hettiarachchi
@ramith.fyi
PhD Student @CMUPittCompBio.bsky.social / @SCSatCMU.bsky.social Interested in ML for science/Compuational drug discovery/AI-assisted scientific discovery 🤞 from 🇱🇰🫶 https://new.ramith.fyi
Does AF2 structure module transport the zero initialized frames to the endpoints? Weight tied 8 blocks or so 🤔 Feels like a generative model to some degree
ChatGPT voice mode is really good. Was having several convos about some papers in the literature, asked it to clone the repo etc and asked questions..
been building an architecture explainer/explorer tool where you can go in varying depth of abstraction to understand: - started with the genie3 (in progress), then go towards AF2 Underneath, it's a compiler for turning model architecture descriptions into interactive diagrams scope.new.ramith.fyi
@wheelerlab.org is talking about his effort to build a resource for protein dynamics (PDB for MD). MDRepo is a repository to store simulation data. This is really needed to push the needle in design, function and more. Please help make it successful by sharing your MD data. #ismb2026 🌐 mdrepo.org
Interesting how ai generated music is easy to identify.. has something to do with the lyrics that sound like an essay and the frequency modulations of the voice🤔
is there a repo where esmfold is optimized for somewhat fast folding?
Glad to have worked with this amazing team in organizing the GenBio workshop! ❤️ (There’s lot more who helped behind the scenes and couldn’t join in this picture) GenBio has been a great venue to bring researchers and foster very interesting convos.. wish I had more time to talk to even more ppl 😆
Claude generated slides kinda give me the ick.. Slides are meant to be simple, somewhat imperfect and human
Registration line 😅 even after two days of registration.. ml conferences maybe reaching a breaking point 😆 i guess it makes more sense to have more decentralized events
Is there a simple way to add bookmarked posters (icml) to the phone’s calendar 🧐
First impression of SK: everything has a touch of cuteness ^_^
So ESMFold2 uses 3DRoPE to enforce a geometry like pairbias (without the mem complexity of the standard pairbias) in its atom transformer… Wonder if the next stage, token transformer could’ve survived a similar approach (rather than the ln proj of z)
damn Grant is an incredible teacher..
Designing Math ft. Grant Sanderson (3Blue1Brown) I Config 2026
YouTube video by Figma
youtu.be
Glad to have contributed to this study on the computational side.. 😃 Thanks to implosion carving, we can now build devices that operate in the visible wavelength regime for classification tasks. Machine learning driven physical device design is pretty exciting.. news.mit.edu/2026/powerfu...
Powerful shrinking technique could enable devices that compute with light
MIT researchers made 3D devices with nanoscale features that can perform optical computing tasks using visible light. They developed a technique that creates vacancies throughout a hydrogel, then shri...
news.mit.edu
Equivariance is dead! 😢 Or is it? 😈 Genie 3 is out! Our latest protein design model achieves SoTA results for binder design and motif scaffolding, greatly improving on BindCraft and Proteina-Complexa. It does so using all-atom SE(3)-equivariance based on a branched polymer representation👇
Yeqing Lin@yeqinglin.bsky.social · 4mo agoIntroducing Genie 3, a generative protein model that substantially advances the state-of-the-art for binder design, increasing in silico success rates by up to 20x on hard multimeric targets. It also debuts a form of inference-time scaling unobserved in other design models. 🧵1/8
claude is good at making posters through html.. feels like doing everything programmically is better 😅 used to love editing stuff on illustrator
La proteina’s autoencoder can be thought of as a inverse folder to some degree 🤔 Wonder if just giving Ca, along with a random partial latent acts as a inverse folder (true we get the all atom structure as well)
Consider submitting your work to the GenBio workshop at ICML 2026! We have an amazing set of speakers whose work spans generative and agentic AI. Deadline: May 1, 2026 genbio-workshop.github.io/2026/
GenBio ICML Workshop 2026
The 2026 workshop on Generative and Agentic AI for Biology at ICML 2026, Seoul, South Korea.
genbio-workshop.github.io
noticing that backbone design models trained on AFDB 588K, when sampled through ODE results in poor designability (~25%). But through a proper noise schedule in SDE it goes to 90% (as reported in lit.) this felt counterintuitive, wonder if the reason is, AFDB being just 42% designable to begin with
this [1] is nice, easier than having to type the passphrase of a ssh key all the time.. made a simpler guide [2] inspired by it [1] - gist.github.com/arianvp/5f59... [2] - gist.github.com/ramithuh/a7b...
Native Secure Enclaved backed ssh keys on MacOS
Native Secure Enclaved backed ssh keys on MacOS . GitHub Gist: instantly share code, notes, and snippets.
gist.github.com
In 10 years we might have an EEG headset that decodes thoughts, and routes to claude 😆 Would be a true brain computer interface 😅
