Rishabh Anand @ NeurIPS
@rishabh16_
Followers
6K
Following
32K
Media
600
Statuses
9K
backpropagating @yale • geometric DL + generative modelling for proteins & RNA • prev @genentech @cambridge_cl @nusingapore 🧬🛠
🇺🇸🇸🇬
Joined June 2017
🚨 My Graph Deep Learning extended tutorial has a new home!!! It's finally up on my personal website: https://t.co/EdfHc18L75 Do RT, share, and tag your GDL buddies if you find it useful 🙌🏻🙌🏻
🚨NEW WEEKEND READING🚨 I'm publishing "Graph Neural Networks for Novice Math Fanatics" – a primer on the math behind GNNs using colourful drawings & diagrams https://t.co/6KT3B0y7QK (I hope this becomes the definitive guide to GDL for those hoping to enter the field!!!)
10
293
1K
Gina is a one-person army!! Very glad we managed to get MLSB again, super serendipitous timing/venue alongside NeurIPS too 😌 lots of fun posters + was great to meet so many cool people
Absolutely blown away by the turn out at @workshopmlsb today. Thank you to the >600 people who came through the venue, and >150 that joined over Zoom throughout the day. Truly an exciting time to be innovating in ML for Structural Biology ♥️
1
1
10
Absolutely blown away by the turn out at @workshopmlsb today. Thank you to the >600 people who came through the venue, and >150 that joined over Zoom throughout the day. Truly an exciting time to be innovating in ML for Structural Biology ♥️
3
7
63
That’s a wrap! Thank you all for coming to the AI for Science workshop. Big shout out to all our speakers, panelists, poster presenters, and organisers (not all pictured). See you at a future conference ✈️🦘
4
2
51
Amazing turnout 🤯
The MLSB poster session is 🔥🔥 A big thanks to all the folks that are joining us today, both as presenters and attendees. As a reminder - we are off campus from the NeurIPS main conference at UCSD Park and Market.
0
0
11
The MLSB poster session is 🔥🔥 A big thanks to all the folks that are joining us today, both as presenters and attendees. As a reminder - we are off campus from the NeurIPS main conference at UCSD Park and Market.
1
4
22
Re-running the Nipah designs with AF3 (as an academic researcher) to obtain AF3 ipSAE and ipTM based rankings. I also made a site to compare and rank the designs based on AF3/Boltz2 metrics. https://t.co/8A9JHslvxZ 🗳️ Vote for your favorites https://t.co/jisyu8fUGy
@adaptyvbio
7
23
99
Refreshing to meet increasingly more AI4Bio people (with predominantly computational backgrounds) at NeurIPS who're gradually looking towards wet-lab validation, not as a "complement" to the AI work, but as a necessary next-step Many fun convos the past few days on exactly
I think being held to high standards by experimentalists at the LMB and Stanford has been simply transformative! After this project, I stop seeing the experiments as an 'extra' step, and see bio design papers **without** experiments as incomplete!
3
0
23
Today, we report a method for design of active enzymes, RFdiffusion2, in @naturemethods. For the first time, we are able to design enzymes with native-range catalytic activity. We also are releasing our next frontier model, RFdiffusion3, code 👇
7
68
358
NeurIPS⛵️ Find me here on 12/6! Oral @unireps, S1: "Universally Converging Representations of Matter Across Scientific Foundation Models" @sathyaedamadaka will present our work! Oral @AI4Mat, 4:10PM: "Guided Diffusion for A Priori Transition State Sampling" I'll be presenting.
2
1
12
coolest event of the season fr
Coming to our AI for Science party! We have open bar, great food and game!
0
0
10
Coming to our AI for Science party! We have open bar, great food and game!
1
1
25
Proud to announce that @Ginkgo was awarded a $47M contract to kick off President Trump's new Genesis Mission and build the world's largest autonomous lab at Pacific Northwest National Lab! I was honored to join @SecretaryWright as he commissioned the first phase of the lab
56
142
978
👇🏻👇🏻
Will be presenting JAMUN, our conformational ensemble sampling method bridging molecular dynamics and diffusion models, at #NeurIPS2025 at 11 AM PT (Poster #1616) today!
0
0
8
Zoom link is live!! Make sure to register at the link below to get it! Looking forward to seeing you all there 🚀
Join us this Sunday Dec 7 for MLSB! We have a great lineup of invited talks, posters, and a panel with our invited speakers. Location: UCSD Park and Market Schedule: https://t.co/wv9C4wezso Can't make it? Make sure to register to join us live on Zoom! https://t.co/HbeFcxie3z
0
2
13
This is incredible. We have 1300+ people signed up to the AI4Science party at NeurIPS tonight. To everyone attending, enjoy the party! 🪩 To everyone on our waitlist, sorry we couldn’t party together this time, please enjoy our workshop and we’ll find a bigger venue next time.
AI for Science is throwing a party at NeurIPS in San Diego 💃! Come along for the science and stay for the good vibes. Sign up link below 👇 @AI_for_Science #neurips2025 Big thank you to our sponsors 👏@RenPhil21 @iambic_ai
1
3
45
🚨 For those training DL models on proteins, it's possible your "structural" train/test split might have leakage cus tools like foldseek/TMalign (and CATH/SCOP databases) do not always account for structural relationship of circularly permuted proteins:
Excited to share my recent work, CIRPIN 🐍 with @sokrypton and @MazAbulnaga on the discovery of thousands of naturally occurring circularly permuted protein domains
3
22
115
Happy to share that the @GoogleDeepMind Gemini team is starting a new research team in Singapore! This new team will be focused on advanced reasoning, LLM/RL and improving bleeding edge SOTA models such as Gemini, Gemini Deep Think and beyond. 🔥 This team will be led by yours
41
91
910
How can you evaluate agent trajectories with only black-box access to a verifier and the agent? Introducing E-valuator: Reliable Agent Verifiers with Sequential Hypothesis Testing ❌no finetuning ❌no additional GPU compute ⬛black-box access ✔️controllable error rates w/
2
7
24