Proposes diffeomorphic optimization for manifold-constrained problems in generative models via flow maps, with Lie-group extensions for protein design showing metric improvements.
Se (3) diffusion model with application to protein backbone generation
5 Pith papers cite this work, alongside 71 external citations. Polarity classification is still indexing.
5
Pith papers citing it
71
external citations · external index
verdicts
UNVERDICTED 5representative citing papers
SurfDesign introduces surface-conditioned protein design via manifold modeling and equivariant message passing on surfaces integrated with pretrained language models, outperforming prior methods on binder and enzyme design benchmarks.
Feynman-Kac steering of RFdiffusion with ProteinMPNN-based guiding potentials improves predicted interface energetics and raises binder designability by 89.5%.
D-Flow applies multi-modality flow matching and a mirror-image data augmentation to generate D-peptides with 10.2% higher sequence identity and 24.31% top affinity on the PepMerge benchmark.
A JAX-implemented flow-based equivariant model for multi-embodiment grasping that deduces kinematics from geometry to support variable-DoF grippers with a new dataset of 25k scenes and 20M grasps.
citing papers explorer
-
Diffeomorphic Optimization
Proposes diffeomorphic optimization for manifold-constrained problems in generative models via flow maps, with Lie-group extensions for protein design showing metric improvements.
-
SurfDesign: Effective Protein Design on Molecular Surfaces
SurfDesign introduces surface-conditioned protein design via manifold modeling and equivariant message passing on surfaces integrated with pretrained language models, outperforming prior methods on binder and enzyme design benchmarks.
-
Controllable protein design with particle-based Feynman-Kac steering
Feynman-Kac steering of RFdiffusion with ProteinMPNN-based guiding potentials improves predicted interface energetics and raises binder designability by 89.5%.
-
D-Flow: Multi-modality Flow Matching for D-peptide Design
D-Flow applies multi-modality flow matching and a mirror-image data augmentation to generate D-peptides with 10.2% higher sequence identity and 24.31% top affinity on the PepMerge benchmark.
-
Towards a Multi-Embodied Grasping Agent
A JAX-implemented flow-based equivariant model for multi-embodiment grasping that deduces kinematics from geometry to support variable-DoF grippers with a new dataset of 25k scenes and 20M grasps.