Flow matching

Timeline

1. Oct 8, 2026 · Research paper · 1 source
   Bi-FORK: Generative Modeling of High-Dimensional Bifurcating Systems
   Bifurcations are ubiquitous in physical systems, from structural buckling to fluid and climate dynamics, yet they remain largely unexplored in deep learning.
2. Oct 8, 2026 · Research paper · 1 source
   Generative Neural Retargeting for Human-to-Robot Dexterous Manipulation
   Human demonstrations are a scalable data source for learning dexterous manipulation, but the embodiment gap prevents human motion from being executed directly on robots.
3. Oct 8, 2026 · Research paper · 1 source
   LeWAM: A JEPA World Action Model with Diffusion-Steering-Based MPC
   We introduce LeWAM, a bidirectional transformer for forward, backward, inverse dynamics and policy prediction, on a decoder-free JEPA latent trained end-to-end through all four modes.
4. Oct 8, 2026 · Research paper · 1 source
   Controllable Exaggeration for Generative Motion Models via Training-Time Adaptation and Inference-Time Guidance
   Recent motion generative models have demonstrated strong capabilities in synthesizing physically plausible character motion, but often overlook established animation principles used by professional animators to ground and design their animation work.
5. Oct 8, 2026 · Research paper · 1 source
   La-Ribo: RNA Co-Design via Geometry-Latent Flow Matching
   We introduce La-Ribo, a generative framework for RNA sequence-structure co-design via geometry-latent flow matching.
6. Oct 8, 2026 · Research paper · 1 source
   Residual Modeling Closes the Regression and Generative Policy Gap in Robot Learning
   We revisit this gap from the perspective of statistical modeling: how action-prediction residuals shape policy optimization.
7. Oct 8, 2026 · Research paper · 1 source
   Few-Step Generation via Data-Space Iteration
   Flow matching has emerged as a scalable paradigm for training high-quality generative models, but sampling from the learned probability flow requires many network evaluations.
8. Oct 8, 2026 · Research paper · 1 source
   Dino Forcing Flow Models: Do not denoise what you can predict
   Co-denoising pretrained representations such as DINO can substantially improve the training speed and quality of flow matching models, but it introduces a second denoising trajectory and requires carefully designed schedules.
9. Oct 8, 2026 · Research paper · 1 source
   Learning Language-Conditioned Traversability Representations for Adaptive Visual Navigation
   We present LaTraNav, a framework that learns language-conditioned traversability representations for adaptive visual navigation.
10. Oct 8, 2026 · Research paper · 1 source
    $C_4$-Equivariant Flow Matching on Anisotropic Power-Diagram Graphs for Microstructure Generation
    We introduce a generative model for synthesising realistic polycrystalline microstructures using flow matching and graph neural networks.
11. Oct 8, 2026 · Research paper · 1 source
    An Efficient Quantum Circuit for Flow Model Execution Using Quantum Neural Networks
    Wavefunction flow establishes a formal connection between flow models and quantum dynamics by introducing a continuity Hamiltonian, which drives the Schrödinger evolution of quantum states.
12. Oct 8, 2026 · Research paper · 1 source
    Zatom-2: Multitask Pretraining on Atomistic Data for Generative Modeling across Domains
    To this end, we introduce Zatom-2, an atomistic generative model pretrained on approximately five million structures from the OMol25 and OMat24 electronic structure datasets.
13. Oct 8, 2026 · Research paper · 1 source
    Finsler Flow Matching: Dynamics-Aware Geodesic Interpolation for Single-Snapshot Trajectory Inference
    We introduce Finsler Flow Matching (FFM), a framework for learning continuous stochastic dynamics from discrete Markov transition graphs.
14. Oct 7, 2026 · Research paper · 1 source
    Velocity Scaling in Flow Matching
    Scaling a learned flow-matching velocity field $vθ$ by a gain $γ(t)$ was recently shown to greatly improve generation quality.
15. Oct 7, 2026 · Research paper · 1 source
    RoboPrompt: Intuitive Robot Policy Steering with Sparse Human Input
    We present RoboPrompt, a general-purpose, lightweight robot policy steering system that enables users to guide policy behavior through intuitive, sparse inputs, including drawn traces, target points, and coarse directional instructions.
16. Oct 7, 2026 · Research paper · 1 source
    Conditional Flow Matching for Generation of 3D Multi-variable Instantaneous Urban Microclimate Fields
    Rapid and accurate prediction of urban wind and temperature fields is important for urban microclimate design and climate adaptation.
17. Oct 7, 2026 · Research paper · 1 source
    HuLiGen: Human LiDAR Generation from Parametric Body Models
    In contrast, we introduce HuLiGen, a generative model that generates human LiDAR point clouds from a parametric body model, using a point transformer trained with a flow-matching objective.
18. Oct 7, 2026 · Research paper · 1 source
    MUNITE: Unified Multimodal Latent Inference for Any-to-Any Multimodal Generation
    We introduce MUNITE, a latent-variable framework for flexible any-to-any multimodal generation that treats encoding and latent generation as the same inference problem under different amounts of observed evidence.
19. Oct 7, 2026 · Research paper · 1 source
    Unrolled Flow Models for Reasoning
    Flow matching enables language generation in few steps, but whether additional integration steps improve reasoning remains unclear.
20. Oct 7, 2026 · Research paper · 1 source
    MeshCarve: Artisan Mesh Generation with Flow Matching in Compact Latent Spaces
    We present MeshCarve, a flow matching method that generates entirely in compact latent spaces, generating vertex positions and edge connections separately and sidestepping the difficulty of a joint compact latent.
21. Oct 7, 2026 · Research paper · 1 source
    EC-EarthFlow: Probabilistic emulation of daily transient global climate model simulations with flow matching
    We introduce EC-EarthFlow, a generative flow matching model that emulates simulations from the physical climate model EC-Earth3.
22. Oct 7, 2026 · Research paper · 1 source
    Point It, Strike It: Direction-Conditioned Dynamic Manipulation of Deformable Linear Objects
    Goal-conditioned dynamic manipulation of deformable linear objects has mainly specified goals as positions for a rope tip to reach.
23. Oct 7, 2026 · Research paper · 1 source
    RobotAPO: Adversarial Physics Preference Optimization for Robotic Manipulation Video Generation
    Robotic manipulation videos are increasingly used as visual plans for embodied agents, but optimizing purely for visual plausibility often fails to capture the fragile physical manifold of real-world interactions.
24. Oct 7, 2026 · Research paper · 1 source
    One Frame, Full Heartbeat: ECG-Free Cardiac Cine MRI Synthesis via Phase-Conditioned Flow Matching
    Cine cardiovascular magnetic resonance (CMR) analysis relies on multi-frame sequences capturing the full cardiac cycle.
25. Oct 7, 2026 · Research paper · 1 source
    Self-attention summary networks for subsurface velocity-model building from common-image gathers
    In this work, we propose a multiscale self-attention summary network that maps high-dimensional 3D CIG volumes into compact conditioning embeddings for probabilistic subsurface velocity inversion.
26. Oct 7, 2026 · Research paper · 1 source
    Twist Flow for Inverse Problems
    Direct conditional generative models introduce latent noise to model this ambiguity, but paired inverse-problem training can still encourage an almost deterministic map from the observation to the target.
27. Oct 6, 2026 · Research paper · 1 source
    One Frame, Full Heartbeat: ECG-Free 4D Cardiac Cine MRI Synthesis via Radial-Decomposed Flow Matching
    We present PhaseFlow3D, a generative framework that synthesizes a complete 4D cine sequence from a single end-diastolic (ED) three-dimensional (3D) volume without ECG.
28. Oct 6, 2026 · Research paper · 1 source
    Domain-informed Adaptive Sampling for Generalizable PINNs in Metal Additive Manufacturing via Conditional Flow Matching
    Accurate thermal modeling is essential in metal additive manufacturing (AM) for understanding the process-structure-property chain.
29. Oct 6, 2026 · Research paper · 1 source
    LASER: Latent Space Adjoint Matching for Support-Constrained Entropy-Regularized Offline RL
    We introduce LASER, a novel offline RL algorithm that applies latent-space adjoint matching to achieve entropy-regularized latent-space RL with expressive flow policies while avoiding backpropagation through time.
30. Oct 6, 2026 · Research paper · 1 source
    Zero-Shot Brain MRI Inpainting with 2.5D Unconditional Flow Priors
    We propose a zero-shot brain MRI inpainting framework utilizing 2.5D unconditional flow priors to capture spatial context along the superior-inferior axis without the overhead of full 3D convolutions.

Often appears with