Scaling Atomistic Protein Binder Design with Generative Pretraining and Test-Time Compute

ICLROral2026

Authors
Kieran Didi, Zuobai Zhang, Guoqing Zhou, Danny Reidenbach, Zhonglin Cao, Sooyoung Cha, Tomas Geffner, Christian Dallago, Jian Tang, Michael M. Bronstein, Martin Steinegger, Emine Kucukbenli, Arash Vahdat, Karsten Kreis
Affiliation
NVIDIA
Venue
ICLR 2026
Track
Oral

TL;DR

We introduce a novel method for state-of-the-art structure-based protein binder design that combines flow matching-based generative pretraining with inference-time compute scaling techniques.

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

flow matching pretraining protein

← All ICLR 2026 Oral papers · Browse the whole archive