Physically Valid Biomolecular Interaction Modeling with Gauss-Seidel Projection

ICLR 2026 Conference Submission14624 Authors

19 Sept 2025 (modified: 08 Oct 2025)ICLR 2026 Conference SubmissionEveryoneRevisionsBibTeXCC BY 4.0
Keywords: Biomolecular Interaction Modeling, Physical Validity
TL;DR: We introduce a differentiable Gauss-Seidel projection module that allows generative models to produce physically valid and highly accurate biomolecular structures in just two steps, achieving a 10x speedup over state-of-the-art baselines.
Abstract: Biomolecular interaction modeling has been substantially advanced by foundation models, yet they often produce all-atom structures that violate basic steric feasibility. We address this limitation by enforcing physical validity as a strict constraint during both training and inference with a unified module. At its core is a differentiable projection that maps the provisional atom coordinates from the diffusion model to the nearest physically valid configuration. This projection is achieved using a Gauss-Seidel scheme, which exploits the locality and sparsity of the constraints to ensure stable and fast convergence at scale. By implicit differentiation to obtain gradients, our module integrates seamlessly into existing frameworks for end-to-end finetuning. With our Gauss-Seidel projection module in place, two denoising steps are sufficient to produce biomolecular complexes that are both physically valid and structurally accurate. Across six benchmarks, our $2$-step model achieves the same structural accuracy as state-of-the-art $200$-step diffusion baselines, delivering ${\sim}10\times$ wall-clock speedups while guaranteeing physical validity.
Primary Area: applications to physical sciences (physics, chemistry, biology, etc.)
Submission Number: 14624
Loading