1. X
  2. Aakarsh Vermani
Log inSign up
Aakarsh Vermani
43 posts
user avatar
Aakarsh Vermani
@aakarshv1
Incoming PhD @Stanford CS | Prev @UCBerkeley EECS | AI + Bio
San Diego, CA
aakarshv1.github.io
Joined May 2020
289
Following
270
Followers
RepliesRepliesMediaMedia
  • Pinned
    user avatar
    Aakarsh Vermani
    @aakarshv1
    Jun 8
    Affinity maturation is how naive antibodies evolve into strong binders, but most antibody LMs ignore it. @stephenzlu and I built CoSiNE to learn this, beating antibody LMs on VEP and reframing design as guiding evolution, not de novo generation. Excited to present at ICML!
    user avatar
    Stephen Lu
    @stephenzlu
    Jun 8
    Antibody LMs learn what looks antibody-like, but not how selection turns naive germline antibodies into strong binders. @aakarshv1 and I are excited to share CoSiNE, a model that learns this germline-to-mature process for variant effect prediction and antibody design. (1/8)
    Image
    00:00
  • user avatar
    Aakarsh Vermani
    @aakarshv1
    May 9
    Had a lot of fun working on this project! Particularly excited by our "convergent hotspots" heuristic for binder design, which iteratively refines the target interface at inference time. Simple yet effective! Try it out: github.com/aqlaboratory/g… Preprint: biorxiv.org/content/10.648…
    user avatar
    Mohammed AlQuraishi
    @MoAlQuraishi
    May 8
    Equivariance is dead😢 Or is it?😈 Genie 3 is out! Our latest protein design model yields SoTA results for binder design & motif scaffolding, greatly improving on BindCraft & Proteina-Complexa It does so using all-atom SE(3)-equivariance on a branched polymer representation👇
  • user avatar
    Aakarsh Vermani
    @aakarshv1
    Apr 23
    We'll be closing out this semester's Berkeley BioML Seminar on 4/28 with a talk from @antoinekoehl on PEINT, a powerful deep learning framework for both phylogenetic inference and protein engineering. Sign up below!
    Image
    BioML Seminar 4.5 - Deep Models of Protein Evolution in Time · Zoom · Luma
    From luma.com
  • user avatar
    Aakarsh Vermani
    @aakarshv1
    Feb 5
    Another semester, another Berkeley BioML Seminar! We're excited to kick off this semester with a talk from @jeffruffolo from Profluent Bio on designing proteins with language models. Join us Monday night!
    Image
    BioML Seminar 4.1 - Designing proteins with language models · Luma
    From luma.com
  • user avatar
    Aakarsh Vermani
    @aakarshv1
    Nov 20, 2025
    Exciting news! We have 3 consecutive Berkeley BioML seminars to close out the semester, starting with a talk on 11/24 from Stanford Prof @brianltrippe on recent progress in generative models for protein design.
    luma.com
    BioML Seminar 3.5 - Recent progress in generative methods for protein structure modeling and design...
    [IN PERSON EVENT IN BERKELEY] Join us for a new seminar from the BioML group in Machine Learning at Berkeley, sponsored by Amplify Partners. This week we're…

Log in or sign up for X

See what’s happening and join the conversation

Continue with phone
or
Log in with username or email
Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
Advertisement
Advertisement