Imagen de Portada

Generalised Flow Maps for Few-Step Generative Modelling on Riemannian Manifolds

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Davis, Oscar, Albergo, Michael S., Boffi, Nicholas M., Bronstein, Michael M., Bose, Avishek Joey
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Fisher Flow Matching for Generative Modeling over Discrete Data
por: Davis, Oscar, et al.
Publicado: (2024)

Flow map matching with stochastic interpolants: A mathematical framework for consistency models
por: Boffi, Nicholas M., et al.
Publicado: (2024)

Stochastic Interpolants: A Unifying Framework for Flows and Diffusions
por: Albergo, Michael S., et al.
Publicado: (2023)

Metric Flow Matching for Smooth Interpolations on the Data Manifold
por: Kapuśniak, Kacper, et al.
Publicado: (2024)

Efficient Regression-Based Training of Normalizing Flows for Boltzmann Generators
por: Rehman, Danyal, et al.
Publicado: (2025)

Aligning Flow Map Policies with Optimal Q-Guidance
por: Ziakas, Christos, et al.
Publicado: (2026)

How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance
por: Huang, Jerry Y., et al.
Publicado: (2026)

How to build a consistency model: Learning flow maps via self-distillation
por: Boffi, Nicholas M., et al.
Publicado: (2025)

Coupling Models for One-Step Discrete Generation
por: Peng, Fred Zhangzhi, et al.
Publicado: (2026)

SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers
por: Ma, Nanye, et al.
Publicado: (2024)

RETRO SYNFLOW: Discrete Flow Matching for Accurate and Diverse Single-Step Retrosynthesis
por: Yadav, Robin, et al.
Publicado: (2025)

Scalable Equilibrium Sampling with Sequential Boltzmann Generators
por: Tan, Charlie B., et al.
Publicado: (2025)

Riemannian MeanFlow for One-Step Generation on Manifolds
por: Zhong, Zichen, et al.
Publicado: (2026)

Curly Flow Matching for Learning Non-gradient Field Dynamics
por: Petrović, Katarina, et al.
Publicado: (2025)

Stochastic interpolants with data-dependent couplings
por: Albergo, Michael S., et al.
Publicado: (2023)

Why Are DMD Students Lazy? Understanding the Copying Behavior in Few-Step Distillation
por: Li, Shucheng, et al.
Publicado: (2026)

Probabilistic Forecasting with Stochastic Interpolants and Föllmer Processes
por: Chen, Yifan, et al.
Publicado: (2024)

On the Stability of Iterative Retraining of Generative Models on their own Data
por: Bertrand, Quentin, et al.
Publicado: (2023)

A Few-Step Generative Model on Cumulative Flow Maps
por: Li, Zhiqi, et al.
Publicado: (2026)

SE(3)-Stochastic Flow Matching for Protein Backbone Generation
por: Bose, Avishek Joey, et al.
Publicado: (2023)

Planner Aware Path Learning in Diffusion Language Models Training
por: Peng, Fred Zhangzhi, et al.
Publicado: (2025)

Discrete Flow Maps
por: Potaptchik, Peter, et al.
Publicado: (2026)

Categorical Flow Maps
por: Roos, Daan, et al.
Publicado: (2026)

Sequence-Augmented SE(3)-Flow Matching For Conditional Protein Backbone Generation
por: Huguet, Guillaume, et al.
Publicado: (2024)

The Superposition of Diffusion Models Using the Itô Density Estimator
por: Skreta, Marta, et al.
Publicado: (2024)

Meta Flow Maps enable scalable reward alignment
por: Potaptchik, Peter, et al.
Publicado: (2026)

Test-time scaling of diffusions with flow maps
por: Sabour, Amirmojtaba, et al.
Publicado: (2025)

Self-Consuming Generative Models with Curated Data Provably Optimize Human Preferences
por: Ferbach, Damien, et al.
Publicado: (2024)

Feature Likelihood Divergence: Evaluating the Generalization of Generative Models Using Samples
por: Jiralerspong, Marco, et al.
Publicado: (2023)

Progressive Inference-Time Annealing of Diffusion Models for Sampling from Boltzmann Densities
por: Akhound-Sadegh, Tara, et al.
Publicado: (2025)

Model Compression with Exact Budget Constraints via Riemannian Manifolds
por: Helcig, Michael, et al.
Publicado: (2026)

Gradient Variance Reveals Failure Modes in Flow-Based Generative Models
por: Reu, Teodora, et al.
Publicado: (2025)

Predicting Drug Effects from High-Dimensional, Asymmetric Drug Datasets by Using Graph Neural Networks: A Comprehensive Analysis of Multitarget Drug Effect Prediction
por: Bose, Avishek, et al.
Publicado: (2024)

Model-free learning of probability flows: Elucidating the nonequilibrium dynamics of flocking
por: Boffi, Nicholas M., et al.
Publicado: (2024)

Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction
por: Rector-Brooks, Jarrid, et al.
Publicado: (2024)

Pre-Generating Multi-Difficulty PDE Data for Few-Shot Neural PDE Solvers
por: Choudhary, Naman, et al.
Publicado: (2025)

Generative Modeling on Manifolds Through Mixture of Riemannian Diffusion Processes
por: Jo, Jaehyeong, et al.
Publicado: (2023)

PairFlow: Closed-Form Source-Target Coupling for Few-Step Generation in Discrete Flow Models
por: Park, Mingue, et al.
Publicado: (2025)

A Monte Carlo estimator of flow fields for sampling and noise problems
por: Albergo, Michael S., et al.
Publicado: (2026)

SplitMeanFlow: Interval Splitting Consistency in Few-Step Generative Modeling
por: Guo, Yi, et al.
Publicado: (2025)