arXiv Machine Learning
Jun 9
Active Flow Expansion for Out-of-Distribution Discovery: from Theory to Molecules
arXiv:2606. 08802v1 Announce Type: new Abstract: Standard flow and diffusion pre-training matches the distribution of available data (e.
Branching Flows: Discrete, Continuous, and Manifold Flow Matching with Splits and Deletions
arXiv:2511. 09465v4 Announce Type: replace-cross Abstract: Diffusion and flow matching approaches to generative modeling have shown promise in domains where the state space is continuous, such as image generation or protein folding & design, and discrete, exemplified by diffusion large language models.
Related stories
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 AI
Jun 12
HD-Prot: A Protein Language Model for Joint Sequence-Structure Modeling with Continuous Structure Tokens
arXiv:2512. 15133v3 Announce Type: replace-cross Abstract: Proteins inherently possess a consistent sequence-structure duality.
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
Sep 15
Branched Optimal Transport Amortization
arXiv:2609.15072v1 Announce Type: cross Abstract: Methods of Branched Optimal Transport (BOT) mimic the economy and efficiency of natural tree-like structures, such as those found in rivers and biolo...
arXiv Computer Vision
3d ago
Multimodal Flow: Unified Flow Modeling of Language and Vision in Embedding Spaces
arXiv:2609.40362v1 Announce Type: new Abstract: We present Multimodal Flow, a fully continuous generative model of language and vision. Most unified multimodal models either model both language and q...
arXiv Machine Learning
Sep 11
Particle GFlowNets: Rethinking Generative Marginalization Models
The paper introduces Particle GFlowNets, showing that Generative Marginalization Models (MaMs) are equivalent to Generative Flow Networks. It extends MaMs to non‑autoregressive sampling and proposes an automatic full‑state rejuvenation criterion based on the Gelman‑Rubin statistic to accelerate learning. Experiments demonstrate significant training speedups in large combinatorial spaces.
arXiv Machine Learning
1d ago
dFlowGRPO: Rate-Aware Policy Optimization for Discrete Flow Models
The paper introduces dFlowGRPO, a reinforcement learning framework tailored for discrete flow models (DFMs). It generalizes previous work on diffusion large language models by supporting various probability paths and non-masked source distributions, and formulates denoising as a Markov decision process that leverages transition rates and posterior models. Experiments on the multimodal DFM FUDOKI show that dFlowGRPO outperforms existing GRPO methods on text‑to‑image generation and matches continuous flow models on multimodal understanding tasks.
arXiv Machine Learning
Jul 31
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.
arXiv Machine Learning
Jul 24
Context-weighted Discrete Flow Matching
arXiv:2607. 21427v1 Announce Type: new Abstract: Discrete flow matching provides a flexible framework for generative modeling on discrete structures.
arXiv Machine Learning
2d ago
RW-Flow: One-Step Generation on Compact Manifolds via Wasserstein Gradient Flows
RW-Flow presents a new one‑step generative framework for data on compact manifolds, leveraging Wasserstein gradient flows. The authors derive a necessary and sufficient identifiability condition for velocity fields on compact, connected Riemannian manifolds, showing that a symmetric, Lipschitz‑continuous cost function yields identifiability iff its Gibbs kernel is nondegenerate. Experiments on geospatial events, protein and RNA torsion angles, and discretized manifolds demonstrate that RW‑Flow surpasses existing one‑step methods across most benchmark settings.
arXiv AI
Jun 8
STREAM: Stochastic Riemannian Flow Matching with Anisotropic Decoder for Digital Histopathology Image Generation
arXiv:2606. 07036v1 Announce Type: cross Abstract: Synthetic histopathology image generation addresses critical challenges in computational pathology, including patient privacy and the growing need for large-scale training data for foundation models.