Chaitanya K. Joshi

Stanford Data Science Fellow & Postdoctoral Scholar

I'm a Stanford Data Science Fellow and postdoc with Rhiju Das at the Department of Biochemistry. I build lab-in-the-loop AI for RNA biology, pairing deep learning with wet-lab experiments at scale.

I did my PhD in Computer Science at the University of Cambridge with Pietro Liò, on geometric deep learning for molecular design. I built gRNAde, the first 3D generative model for RNA, and validated it in the wet lab as a visiting researcher in Phil Holliger's group at the MRC LMB. I've also interned at Prescient Design (Genentech) and FAIR Chemistry (Meta AI), and my work has been recognized by the Qualcomm Innovation Fellowship and the A*STAR National Science Scholarship.

Download CV

News

Jun 2026
Attending the 75th Lindau Nobel Laureate Meeting as a Young Scientist.
May 2026
De novo design of RNA pseudoknots is on bioRxiv, including cryo-EM 3D structure of gRNAde-designed Mol9.
Feb 2026
Started as a Stanford Data Science Fellow in the Das Lab.
Dec 2025
Wet-lab validated ribozyme design with gRNAde is on bioRxiv, with the Holliger Lab at MRC LMB.
May 2025
All-atom Diffusion Transformers accepted at ICML 2025, with FAIR Chemistry at Meta AI.
Apr 2025
gRNAde is a Spotlight at ICLR 2025; also co-organised the AI for Nucleic Acids workshop.

Recent talks

How to design RNA · The Pauling Principle podcast

All-atom Diffusion Transformers · ICLR 2025 AI4Mat

Research focus

Deep learning foundations

Molecules are life's building blocks, but hard for neural networks to grasp. The question at the heart of my research: how do we build models that are expressive and general across molecular systems and scales?

Lab-in-the-loop AI

At Stanford, I close the loop between deep learning and the wet lab, combining generative models with high-throughput experiments to continuously improve biomolecule designs.

Programmable RNA Design

RNA can sense, regulate, catalyze, and even compute. I design RNAs with new-to-nature functions, moving beyond static structure toward programmable biology.

Selected publications

Generative inverse design of RNA structure and function with gRNAde

Chaitanya K. Joshi*, Edoardo Gianni*, Samantha L. Y. Kwok*, Simon V. Mathis, Pietro Liò, Philipp Holliger

bioRxiv, December 2025 • Accompanying methods paper (ICLR 2025 Spotlight)

Wet-lab validated generative RNA design, including functional ribozymes and new-to-nature 3D structures.

Molecules, a crystal, and a protein–DNA complex — the molecular systems modelled by ADiT

All-atom Diffusion Transformers: Unified Generative Modelling of Molecules and Materials

Chaitanya K. Joshi, Xiang Fu, Yi-Lun Liao, Vahe Gharakhanyan, Benjamin Kurt Miller, Anuroop Sriram, Zachary W. Ulissi

ICML 2025 • ICLR 2025 AI4Mat Workshop Spotlight

First unified generative model for molecules and materials, showing transfer learning across chemical space.

Rotation equivariance of a geometric GNN on a 3D atomic graph

A Hitchhiker's Guide to Geometric GNNs for 3D Atomic Systems

Alexandre Duval*, Simon V. Mathis*, Chaitanya K. Joshi*, Victor Schmidt*, Santiago Miret, Fragkiskos D. Malliaros, Taco Cohen, Pietro Liò, Yoshua Bengio, Michael Bronstein

arXiv, December 2023 • Companion theory paper (ICML 2023)

A widely used introduction to GNNs for molecules; part of course material at Stanford, Cambridge, and Oxford.

All publications on Google Scholar →