arXiv Machine Learning
Jul 2
Diffeomorphic Optimization
arXiv:2607. 00947v1 Announce Type: new Abstract: Generative models learn data distributions that reside on a low-dimensional manifold within a higher-dimensional ambient space.
SE(3)-MeanFlow: Few-Step Protein Backbone Generation on Lie Groups
arXiv:2607. 27431v1 Announce Type: new Abstract: Generative modeling of protein backbones promises the de novo design of proteins with prescribed structural and functional properties.
Related stories
arXiv Machine Learning
Sep 22
SPID: Distilled Protein Backbone Generation
arXiv:2510.03095v4 Announce Type: replace Abstract: Diffusion- and flow-based generative models have recently demonstrated strong performance in protein backbone generation tasks, offering unpreceden...
arXiv AI
Jun 19
Emyx: Fast and efficient all-atom protein generation
arXiv:2606. 19377v1 Announce Type: cross Abstract: Computational enzyme design requires generating proteins that scaffold catalytic residues and ligands, a task that demands both geometric accuracy and structural diversity from the underlying generative model.
arXiv AI
4d ago
SymDrift: One-Shot Generative Modeling under Symmetries
arXiv:2605.06140v3 Announce Type: replace-cross Abstract: Generative modeling of physical systems, such as molecules, requires learning distributions that are invariant under global symmetries, such...
arXiv Machine Learning
Jul 2
PETIMOT: A Novel Framework for Inferring Protein Motions from Sparse Data Using SE(3)-Equivariant Graph Neural Networks
arXiv:2504. 02839v2 Announce Type: replace-cross Abstract: Proteins move and deform to ensure their biological functions.
arXiv Machine Learning
Jun 9
Few-step Cofolding with All-Atom Flow Maps
arXiv:2606. 08375v1 Announce Type: new Abstract: All-atom generative modeling of 3D biomolecular complexes has emerged as the dominant paradigm for predicting the structure of proteins and protein-ligand systems.
arXiv AI
Sep 3
Schr\"odinger Bridges on Lie Group Manifolds for Probabilistic Intrinsic Generation
The paper introduces a probabilistic generative framework called Schr"odinger Bridges on Lie Group Manifolds, enabling direct modeling of non‑Euclidean data without flattening or coordinate inconsistencies. It develops two computational realizations—Wrapped‑Kernel Bridge Calibration for compact Abelian groups and Reciprocal Conditional‑Control Bridge Matching for compact non‑Abelian groups—while providing a modular error bound that separates various sources of approximation error. Experiments on protein, RNA torsions, SO(3), U(n), and protein conformational pathways demonstrate the method’s feasibility and consistency.
arXiv Machine Learning
Jun 11
ProHiFlo: Hierarchical Flow Matching with Functional Guidance for De Novo Protein Generation
arXiv:2606. 11243v1 Announce Type: new Abstract: De novo protein generation has transformative potential in therapeutic design, enzyme engineering, and synthetic biology.
arXiv Machine Learning
Aug 4
Refine Drugs, Don't Complete Them: Uniform-Source Discrete Flows for Fragment-Based Drug Discovery
arXiv:2509. 26405v2 Announce Type: replace Abstract: We introduce InVirtuoGen, a discrete flow generative model for fragmented SMILES for de novo and fragment-constrained generation, and target-property/lead optimization of small molecules.
arXiv Machine Learning
Jun 18
Riemannian MeanFlow for One-Step Generation on Manifolds
arXiv:2603. 10718v3 Announce Type: replace Abstract: Flow Matching enables simulation-free training of generative models on Riemannian manifolds, yet sampling typically still relies on numerically integrating a probability-flow ODE.
arXiv Machine Learning
Jul 13
Variable-Length Generative Protein Design via Generalized Poisson Flow
arXiv:2607. 09039v1 Announce Type: new Abstract: The ability to generate variable-length proteins is crucial in protein design, where the optimal length is often unknown and tightly coupled to designability.
arXiv Machine Learning
Jul 7
Stable Global Weighting of Flow Mixtures using Simplex Exponential Moving Average
arXiv:2607. 03809v1 Announce Type: new Abstract: Normalising flows provide a powerful variational family for approximate inference, yet individual architectures often fail to generalise across heterogeneous posterior geometries.