New flow matching methods enhance generative modeling and RL
ByPulseAugur Editorial·[58 sources]·
Researchers are advancing flow matching techniques for generative modeling across various domains. New methods like Kinetic Path Energy (KPE) and Kinetic Trajectory Shaping (KTS) aim to improve generation quality by analyzing trajectory energy. PrismFlow introduces dynamical experts for better time-series generation, while Random Process Flow Matching (RP Flow) focuses on sparse data and uncertainty estimation. STFlow enhances trajectory simulation by incorporating data-dependent couplings, and Recursive Flow Matching (RecFM) offers speed-fidelity improvements for spatiotemporal dynamics. Additionally, Guided Flow Matching (FM4PDE) addresses PDE problems with sparse observations, and AdvantageFlow and Flow-OPD explore reinforcement learning applications within flow models for improved policy optimization and multi-task alignment.
AI
IMPACT
These advancements in flow matching techniques promise improved generative model performance, efficiency, and applicability across scientific and RL domains.
RANK_REASON
Multiple arXiv papers introducing novel methods and applications for flow matching.
arXiv:2606.11691v1 Announce Type: new Abstract: Latent diffusion and flow matching have emerged as leading approaches for synthetic turbulence generation, yet they systematically under-represent dissipation-range amplitudes. We introduce a latent flow matching framework with a sp…
arXiv:2606.11833v1 Announce Type: new Abstract: Flow matching and diffusion models enable conditional generation across domains ranging from images to proteins, with recent extensions to out-of-distribution contexts. Yet generative models of neural time series have largely remain…
Flow matching and diffusion models enable conditional generation across domains ranging from images to proteins, with recent extensions to out-of-distribution contexts. Yet generative models of neural time series have largely remained restricted to categorical conditioning, precl…
arXiv cs.LG
TIER_1English(EN)·Adam P. Generale, Andreas E. Robertson, Surya R. Kalidindi·
arXiv:2411.08314v5 Announce Type: replace Abstract: Learning to transform conditional probability densities over time is a fundamental challenge spanning probabilistic modeling and the natural sciences. This task is paramount when forecasting the evolution of stochastic nonlinear…
arXiv cs.LG
TIER_1English(EN)·Bhargav Sriram Siddani, John B. Bell, Alejandro L. Garcia, Ishan Srivastava·
arXiv:2606.06658v1 Announce Type: new Abstract: Hydrodynamic models of stochastic particle systems represented by coarse-grained stochastic partial differential equations (SPDE), such as the regularized Dean-Kawasaki (DK) equation, do not accurately capture the short-time system …
arXiv:2606.04092v1 Announce Type: cross Abstract: Flow matching models learn to transport samples from a simple prior distribution to a complex data distribution. When prior-data pairs are coupled via optimal transport (OT), the learned trajectories are straight and non-crossing,…
arXiv cs.LG
TIER_1English(EN)·Benjamin Honor\'e, Alba Carballo-Castro, Yiming Qin, Pascal Frossard·
arXiv:2602.18084v2 Announce Type: replace Abstract: Equivariance is central to graph generative models, as it ensures the model respects the permutation symmetry of graphs. However, strict equivariance can increase computational cost due to added architectural constraints, and ca…
arXiv cs.AI
TIER_1English(EN)·Junwan Kim, Jiho Park, Seonghu Jeon, Seungryong Kim·
arXiv:2602.05951v2 Announce Type: replace-cross Abstract: Flow matching has recently emerged as a promising alternative to diffusion-based generative models, particularly for text-to-image generation. Despite its flexibility in allowing arbitrary source distributions, most existi…
arXiv cs.LG
TIER_1English(EN)·Francesco M. Ruscio, T. Konstantin Rusch·
arXiv:2606.02177v1 Announce Type: new Abstract: Flow Matching typically relies on white noise sources, a choice often misaligned with the power spectra of natural data, which tend to decay with frequency. To address this, we introduce Low-Pass Flow Matching, a variant of Flow Mat…
arXiv cs.LG
TIER_1English(EN)·Rania Briq, Michael Kamp, Ohad Fried, Sarel Cohen, Stefan Kesselheim·
arXiv:2605.08398v2 Announce Type: replace Abstract: In this work, we show that Latent Flow-Matching (LFM) models are robust to different types of perturbations, including data reduction and model capacity shrinkage. We characterize this stability by these models' tendency to gene…
arXiv cs.AI
TIER_1English(EN)·Jonas Henry Grebe, Tobias Braun, Anna Rohrbach, Marcus Rohrbach·
arXiv:2606.00140v1 Announce Type: cross Abstract: While the rapid adoption of multimodal generative models offers immense potential, it has also increased the risks of harmful content synthesis, deepfakes, and copyright infringements. To address these challenges, concept erasure …
arXiv cs.LG
TIER_1English(EN)·T. Konstantin Rusch·
Flow Matching typically relies on white noise sources, a choice often misaligned with the power spectra of natural data, which tend to decay with frequency. To address this, we introduce Low-Pass Flow Matching, a variant of Flow Matching based on an operator-modulated interpolant…
arXiv:2602.07928v2 Announce Type: replace-cross Abstract: Flow-based generative models can be viewed through a physics lens: sampling transports a particle from noise to data by integrating a learned velocity field, and each sample corresponds to a trajectory with its own dynamic…
arXiv cs.AI
TIER_1English(EN)·Junru Zhang, Lang Feng, Jinbo Wang, Xu Guo, Yucheng Wang, Han Yu, Min Wu, Yabo Dong, Duanqing Xu·
arXiv:2605.28867v1 Announce Type: cross Abstract: Generating high-quality time-series data is challenging because real-world signals often exhibit multimodal patterns and multiscale dynamics, including oscillations and high-frequency variations. Flow Matching (FM) offers an effic…
arXiv cs.LG
TIER_1English(EN)·Julien Lalanne, David Picard, Lionel Boillot, Lina-Mar\'ia Guayac\'an-Carrillo, Leon Barens, Jean-Michel Pereira·
arXiv:2605.28625v1 Announce Type: new Abstract: Generative modeling provides a powerful framework for learning data distributions. These models initially relied on probabilistic methods such as Gaussian Processes (GP) for uncertainty-aware predictions and shifted towards larger t…
arXiv cs.AI
TIER_1English(EN)·Kiet Bennema ten Brinke, Koen Minartz, Vlado Menkovski·
arXiv:2505.18647v3 Announce Type: replace-cross Abstract: Simulating trajectories of dynamical systems is a fundamental problem in a wide range of fields such as molecular dynamics, biochemistry, and pedestrian dynamics. Machine learning has become an invaluable tool for scaling …
Generative modeling provides a powerful framework for learning data distributions. These models initially relied on probabilistic methods such as Gaussian Processes (GP) for uncertainty-aware predictions and shifted towards larger trainable models to learn more complex distributi…
arXiv cs.AI
TIER_1English(EN)·Jiahe Huang, Sihan Xu, Sharvaree Vadgama, Rose Yu·
arXiv:2605.26535v1 Announce Type: cross Abstract: Generative models have emerged as a powerful paradigm for solving physics systems and modeling complex spatiotemporal dynamics. However, achieving high physical accuracy without incurring high computational cost remains a fundamen…
arXiv:2603.17685v3 Announce Type: replace Abstract: Balancing policy expressiveness with the exploration-exploitation trade-off is a core challenge in online Reinforcement Learning (RL). While Stochastic Differential Equation (SDE)-based diffusion policies can represent complex, …
arXiv:2605.08063v5 Announce Type: replace-cross Abstract: Existing Flow Matching (FM) text-to-image models suffer from two critical bottlenecks under multi-task alignment: the reward sparsity induced by scalar-valued rewards, and the gradient interference arising from jointly opt…
arXiv:2512.23956v2 Announce Type: replace-cross Abstract: Flow Matching (FM) has emerged as a powerful paradigm for continuous normalizing flows, yet standard FM implicitly performs an unweighted $L^2$ regression over the entire ambient space. In high dimensions, this leads to a …
arXiv cs.LG
TIER_1English(EN)·Xuyang Li, Rui Li, Teng Man, Yimin Lu·
arXiv:2604.04453v2 Announce Type: replace-cross Abstract: Granular flows govern many natural and industrial processes, yet their interior kinematics and mechanics remain largely unobservable, as experiments access only boundaries or free surfaces. Conventional numerical simulatio…
arXiv:2512.20063v3 Announce Type: replace Abstract: We introduce $\texttt{PairFlow}$, a lightweight preprocessing step for training Discrete Flow Models (DFMs) to achieve few-step sampling without requiring a pretrained teacher. DFMs have recently emerged as a new class of genera…
arXiv cs.LG
TIER_1English(EN)·Xifeng Zhang, Jin Zhao·
arXiv:2605.25509v1 Announce Type: cross Abstract: Reconstructing PDE solutions from sparse observations is a core challenge in scientific computing. We present FM4PDE, a flow-matching generative framework that learns the joint distribution of PDE coefficients (or initial states) …
arXiv:2605.26013v1 Announce Type: cross Abstract: We introduce AdvantageFlow, a forward-process reinforcement learning algorithm for rectified flow models. Unlike Flow-GRPO, which optimizes the reverse process, we optimize an advantage-weighted forward-process prediction loss. Th…
arXiv cs.LG
TIER_1English(EN)·Pedro M. P. Curvo, Maksim Zhdanov, Floor Eijkelboom, Jan-Willem van de Meent·
arXiv:2605.10302v3 Announce Type: replace Abstract: Existing approaches to controllable generation typically rely on fine-tuning, auxiliary networks, or test-time search. We show that flow matching admits a different control interface: adaptation through examples. For determinist…
We introduce AdvantageFlow, a forward-process reinforcement learning algorithm for rectified flow models. Unlike Flow-GRPO, which optimizes the reverse process, we optimize an advantage-weighted forward-process prediction loss. This optimization problem is unstable when advantage…
We introduce AdvantageFlow, a forward-process reinforcement learning algorithm for rectified flow models. Unlike Flow-GRPO, which optimizes the reverse process, we optimize an advantage-weighted forward-process prediction loss. This optimization problem is unstable when advantage…
Reconstructing PDE solutions from sparse observations is a core challenge in scientific computing. We present FM4PDE, a flow-matching generative framework that learns the joint distribution of PDE coefficients (or initial states) and solutions (or final states), enabling both for…
arXiv:2605.23341v1 Announce Type: cross Abstract: Embodied trajectories, such as the executable motion sequences of robotic manipulators, underwater vehicles, and mobile robots, are a fundamental output of embodied AI. Modern generative models often treat them as a dense, monolit…
arXiv:2605.23522v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become an effective way to improve prompt alignment and perceptual quality in diffusion and flow-matching generators. A critical step for applying online RL to flow matching is turning the determini…
arXiv cs.AI
TIER_1English(EN)·Zhong Li, Qi Huang, Lincen Yang, Jiayang Shi, Zhao Yang, Niki van Stein, Thomas B\"ack, Matthijs van Leeuwen·
arXiv:2502.17119v2 Announce Type: replace-cross Abstract: Deep generative models have made rapid progress in image, text, audio, and video generation, and are increasingly being applied to structured records. For tabular data, however, generative modeling remains difficult: a dat…
Geometry-aware generative models leveraging spherical manifolds and optimal transport techniques outperform traditional Euclidean approaches for natural image synthesis.
Embodied trajectories, such as the executable motion sequences of robotic manipulators, underwater vehicles, and mobile robots, are a fundamental output of embodied AI. Modern generative models often treat them as a dense, monolithic signal generated point by point, fitting an in…
arXiv cs.AI
TIER_1English(EN)·Jingxuan Wu, Zhenglin Wan, Xingrui Yu, Yuzhe Yang, Bo An, Ivor Tsang, Yang You·
arXiv:2510.09060v2 Announce Type: replace Abstract: Flow-based text-to-image models follow deterministic trajectories, making it costly to explore diverse modes under limited sampling budgets. Existing approaches to improving diversity often rely on retraining or degrade image fi…
arXiv cs.LG
TIER_1English(EN)·Jaihoon Kim, Rajarshi Saha, Minhyuk Sung, Youngsuk Park·
arXiv:2510.17991v3 Announce Type: replace Abstract: Flow Matching (FM) underpins many state-of-the-art generative models, yet recent results indicate that Transition Matching (TM) can achieve higher quality with fewer sampling steps. This work answers the question of when and why…
arXiv cs.AI
TIER_1English(EN)·Yifu Luo, Haoyuan Sun, Xinhao Hu, Penghui Du, Keyu Fan, Bo Li, Sinan Du, Xu Wan, Zhiyu Chen, Bo Xia, Tiantian Zhang, Yongzhe Chang, Changqian Yu, Kun Gai, Xueqian Wang·
arXiv:2510.21583v2 Announce Type: replace-cross Abstract: Recent Progress in post-training flow matching for text-to-image (T2I) generation with Group Relative Policy Optimization (GRPO) has demonstrated strong potential. However, it is hindered by a critical limitation: inaccura…
This paper tackles the task of learning to generate signals over triangle meshes in a triangulation-agnostic manner, meaning the trained model can be applied to different meshes and triangulations effectively. Practically, the paper adapts the flow matching (FM) paradigm to a mes…
arXiv stat.ML
TIER_1English(EN)·Raghav Kansal, David Crair, Nghia Nguyen, Scott Pope, Bradley Parry·
arXiv:2606.05327v1 Announce Type: cross Abstract: Flow matching (FM) has emerged as a powerful framework for learning dynamic transport maps between two empirical distributions. However, less explored is the setting with intermediate observed marginals that can help constrain the…
arXiv cs.CV
TIER_1English(EN)·Qilin Huang, Quynh Anh Huynh, Long Le, Chen Wang, Chuhao Chen, Ryan Lucas, Eric Eaton, Lingjie Liu·
arXiv:2606.05399v1 Announce Type: new Abstract: Existing feed-forward networks excel at predicting a single set of physical properties from visual appearance, but this point-estimate paradigm fundamentally fails to capture the real world's inherent physical ambiguity. We address …
arXiv stat.ML
TIER_1English(EN)·Pierre-Louis Ruhlmann, Michael Arbel, Florence Forbes, Pedro L. C. Rodrigues·
arXiv:2509.23385v5 Announce Type: replace Abstract: Simulation-based inference (SBI) is transforming experimental sciences by enabling parameter estimation in complex non-linear models from simulated data. A persistent challenge, however, is model misspecification. In a Bayesian …
Flow matching (FM) has emerged as a powerful framework for learning dynamic transport maps between two empirical distributions. However, less explored is the setting with intermediate observed marginals that can help constrain the flows between the endpoints. This "multimarginal"…
arXiv cs.CV
TIER_1English(EN)·Onkar Susladkar, Tushar Prakash, Gayatri Deshmukh, Kiet A. Nguyen, Jiaxun Zhang, Adheesh Juvekar, Tianshu Bao, Lin Chai, Sparsh Mittal, Inderjit S Dhillon, Ismini Lourentzou·
arXiv:2602.12221v2 Announce Type: replace Abstract: We propose UniDFlow, a unified discrete flow-matching framework for multimodal understanding, generation, and editing. It decouples understanding and generation via task-specific low-rank adapters, avoiding objective interferenc…
arXiv:2603.28759v2 Announce Type: replace Abstract: We present FlowIt, a novel architecture for optical flow estimation that combines global matching with confidence and occlusion-guided refinement. At its core, FlowIt leverages a hierarchical transformer architecture that captur…
arXiv:2602.05435v2 Announce Type: replace Abstract: While flow matching is elegant, its reliance on single-sample conditional velocities leads to high-variance training targets that destabilize optimization and slow convergence. By explicitly characterizing this variance, we iden…
arXiv stat.ML
TIER_1English(EN)·Etrit Haxholli, Yeti Z. Gurbuz, Ogul Can, Eli Waxman·
arXiv:2411.00759v5 Announce Type: replace-cross Abstract: Discrete flow matching, a recent framework for modeling categorical data, has shown competitive performance with autoregressive models. However, unlike continuous flow matching, the rectification strategy cannot be applied…
arXiv stat.ML
TIER_1English(EN)·S. David Mis, Maarten V. de Hoop·
arXiv:2603.20329v2 Announce Type: replace Abstract: We study the ill-posed problem of recovering a probability measure flow from finitely many moving localized sensors using a Bayes Hilbert framework. Relative to a fixed reference probability measure, a probability law is represe…
arXiv:2509.21906v3 Announce Type: replace-cross Abstract: Discrete flow models offer a powerful framework for learning distributions over discrete state spaces and have demonstrated superior performance compared to the discrete diffusion models. However, their convergence propert…
arXiv:2601.22519v2 Announce Type: replace Abstract: Discrete flow models (DFMs) have been proposed to learn the data distribution on finite state space, offering a flexible framework as an alternative to discrete diffusion models. A line of recent work has studied samplers for di…
arXiv cs.CV
TIER_1English(EN)·Junho Lee, Kwanseok Kim, Joonseok Lee·
arXiv:2605.25294v1 Announce Type: new Abstract: Recent advances in generative models highlight the power of geometry-aware modeling in manifold-constrained settings. Yet, for natural images, the field remains confined to Euclidean assumptions, failing to exploit the potential of …
arXiv cs.CV
TIER_1English(EN)·Hansheng Chen, Jan Ackermann, Minseo Kim, Gordon Wetzstein, Leonidas Guibas·
arXiv:2605.12964v2 Announce Type: replace Abstract: Flow-based generation in high-dimensional spaces is difficult because velocity prediction requires modeling high-dimensional noise, even when data has strong low-rank structure. We present Asymmetric Flow Modeling (AsymFlow), a …
arXiv cs.CV
TIER_1English(EN)·Cuong Le, Pavlo Melnyk, Bastian Wandt, M{\aa}rten Wadenb\"ack·
arXiv:2601.16763v2 Announce Type: replace Abstract: Recovering 3D human poses from a monocular camera view is a highly ill-posed problem due to the depth ambiguity. Earlier studies on 3D human pose lifting from 2D often contain incorrect-yet-overconfident 3D estimations. To mitig…
Reconstructing PDE solutions from sparse observations is a core challenge in scientific computing. We present FM4PDE, a flow-matching generative framework that learns the joint distribution of PDE coefficients (or initial states) and solutions (or final states), enabling both for…
arXiv:2605.23070v1 Announce Type: new Abstract: We propose Flow Mismatching, an unsupervised anomaly detection method that deliberately avoids reconstruction-based paradigms. Instead, we treat flow matching as geometric dynamics and leverage a key insight: anomalies occur at plac…
Reinforcement learning (RL) has become an effective way to improve prompt alignment and perceptual quality in diffusion and flow-matching generators. A critical step for applying online RL to flow matching is turning the deterministic sampling trajectory into a stochastic policy,…
arXiv:2605.20068v1 Announce Type: new Abstract: Standard generative models struggle with heavy-tailed data: Lipschitz architectures cannot produce power-law tails from Gaussian noise, and interpolating between heavy-tailed data and Gaussians is ill-posed. We propose a simple fix:…
Standard generative models struggle with heavy-tailed data: Lipschitz architectures cannot produce power-law tails from Gaussian noise, and interpolating between heavy-tailed data and Gaussians is ill-posed. We propose a simple fix: apply the soft-log transform $φ(x) = \mathrm{si…
