Researchers advance flow matching for faster, more versatile AI generation and control
ByPulseAugur Editorial·
Summary by gemini-2.5-flash-lite
from 36 sources
Researchers are exploring novel applications and improvements for flow matching, a generative modeling technique. New methods like Action-to-Action flow matching (A2A) aim to reduce inference latency in robotics by using previous actions as initialization. Other advancements include deterministic adjoint matching for human preference alignment, similarity-driven flow matching for time series generation, and frequency-heterogeneous flow matching for image generation. Additionally, studies are investigating the theoretical underpinnings of flow matching, its use in graph domain adaptation, and its potential for efficient adaptation to unseen distributions.
AI
IMPACT
Advances in flow matching techniques could lead to faster, more efficient, and versatile generative models across robotics, time series, image generation, and domain adaptation.
RANK_REASON
Multiple arXiv papers introduce novel techniques and applications for flow matching models.
Flow Matching is a powerful framework for learning transport maps between probability distributions. Yet its standard single-parameter formulation is not designed to capture multi-parameter variations where the resulting transport should be path-independent. Path independence is …
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 deterministic interpolants, the velocity field is solely govern…
Tackling the task of materials generation, we aim to enhance the previously proposed All-atom Diffusion Transformer (ADiT) by introducing SymADiT, a symmetry-aware variant. To do so, we use a representation of materials based on Wyckoff positions. We follow ADiT and perform gener…
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 optimizing heterogeneous objectives, which together give rise…
Discrete flow matching generates text by iteratively transforming noise tokens into coherent language, but may require hundreds of forward passes. Distillation uses the multi-step trajectory to train a student to reproduce the process in a few steps. When the student underperform…
Continuous diffusion and flow matching models could represent a powerful alternative to autoregressive approaches for language modelling (LM), as they unlock a host of advantages currently reserved for continuous modalities, including accelerated sampling and tilting. Recently, s…
Standard flow matching scales well but typically relies on an unstructured source distribution, limiting its ability to learn interpretable latent structure. Latent-variable models, by contrast, capture structure but often sacrifice generative quality. We bridge this gap by propo…
Estimating counterfactual distributions under interventions is central to treatment risk assessment and counterfactual generation tasks. Existing approaches model the counterfactual distribution as a standalone generative target, without exploiting its relationship to the observa…
We study Flow Matching in a semi-discrete setting where a Gaussian source is transported toward a discrete target supported on finitely many points. This semi-discrete regime is the theoretical setting behind the use of Flow Matching for generative modeling, where the target dist…
arXiv cs.AI
TIER_1·Jindou Jia, Gen Li, Xiangyu Chen, Tuo An, Yuxuan Hu, Jingliang Li, Xinying Guo, Jianfei Yang·
arXiv:2602.07322v2 Announce Type: replace-cross Abstract: Diffusion-based policies have recently achieved remarkable success in robotics by formulating action prediction as a conditional denoising process. However, the standard practice of sampling from random Gaussian noise ofte…
arXiv:2605.05975v1 Announce Type: new Abstract: Reconstructing high-fidelity flow fields from low-fidelity observations is a central problem in scientific machine learning, yet recent diffusion and flow-matching models typically rely on iterative sampling, making them costly for …
arXiv cs.LG
TIER_1·Tyler Ingebrand, Ruihan Zhao, Kushagra Gupta, David Fridovich-Keil, Sandeep P. Chinchali, Ufuk Topcu·
arXiv:2605.06272v1 Announce Type: new Abstract: While generative modeling has achieved remarkable success on tasks like natural language-conditioned image generation, enabling model adaptation from example data points remains a relatively underexplored and challenging problem. To…
arXiv:2605.06364v1 Announce Type: new Abstract: We introduce a new generative modeling framework, \textbf{Flow Matching with Arbitrary Auxiliary Paths (AuxPath-FM)}, which generalizes conditional flow matching by incorporating an auxiliary variable drawn from an arbitrary distrib…
arXiv:2605.06421v1 Announce Type: cross Abstract: Pixel-space diffusion has re-emerged as a promising alternative to latent-space generation because it avoids the representation bottleneck introduced by VAEs. Yet most existing methods still treat image generation as a frequency-h…
arXiv cs.LG
TIER_1·Yingxu Wang, Xinwang Liu, Mengzhu Wang, Siyang Gao, Nan Yin·
arXiv:2602.00656v2 Announce Type: replace Abstract: Graph Domain Adaptation (GDA) aims to transfer graph classifiers across domains with both semantic and topological shifts. Existing Euclidean adversarial methods face two challenges: Structural Degeneration, where domain confusi…
arXiv cs.LG
TIER_1·Soon Hoe Lim, Shizheng Lin, Michael W. Mahoney, N. Benjamin Erichson·
arXiv:2602.08318v2 Announce Type: replace-cross Abstract: Flow matching (FM) is increasingly used in scientific domains for time series generation and forecasting, where data often arise from underlying dynamical systems. However, it is not well-understood whether it learns trans…
arXiv:2605.05736v1 Announce Type: new Abstract: Vector quantization (VQ) with autoregressive (AR) token modeling is a widely adopted and highly competitive paradigm for time-series generation. However, such models are fundamentally limited by exposure bias: during inference, erro…
arXiv cs.AI
TIER_1·Zhengyi Guo, Jiayuan Sheng, David D. Yao, Wenpin Tang·
arXiv:2605.06583v1 Announce Type: new Abstract: We propose a deterministic adjoint matching framework that formulates human preference alignment for flow-based generative models as an optimal control problem over velocity fields. One can directly regress the control toward a valu…
We propose a deterministic adjoint matching framework that formulates human preference alignment for flow-based generative models as an optimal control problem over velocity fields. One can directly regress the control toward a value-gradient-induced target under the current poli…
We introduce a new generative modeling framework, \textbf{Flow Matching with Arbitrary Auxiliary Paths (AuxPath-FM)}, which generalizes conditional flow matching by incorporating an auxiliary variable drawn from an arbitrary distribution into the probability path. Unlike prior me…
arXiv cs.LG
TIER_1·Hongxu Chen, Yanghao Wang, Bowei Zhu, Hongxiang Li, Zhen Wang, Ziqi Jiang, Lin Li, Rui Liu, Long Chen·
arXiv:2605.05054v1 Announce Type: cross Abstract: Recent flow matching (FM) methods improve the few-shot adaptation of vision-language models, by modeling cross-modal alignment as a continuous multi-step flow. In this paper, we argue that existing FM methods are inherently constr…
arXiv:2605.03588v1 Announce Type: new Abstract: We introduce a general framework for training flow matching models on Riemannian symmetric spaces, a large class of manifolds that includes the sphere, hyperbolic space and Grassmannians. We exploit their algebraic structure to refo…
We introduce a general framework for training flow matching models on Riemannian symmetric spaces, a large class of manifolds that includes the sphere, hyperbolic space and Grassmannians. We exploit their algebraic structure to reformulate flow matching on symmetric spaces as flo…
arXiv:2602.10420v3 Announce Type: replace Abstract: Flow matching has emerged as a powerful framework for generative modeling, with recent empirical successes highlighting the effectiveness of signal-space prediction ($x$-prediction). In this work, we investigate the transfer of …
We propose Coreset-Induced Conditional Velocity Flow Matching (CCVFM), a generative model that augments hierarchical rectified flow with a data-informed source distribution. Hierarchical flow matching models the full conditional velocity law in velocity space, but its inner flow …
Diffusion and flow-matching models scale because pretraining is supervised regression: a clean sample is noised analytically, and a model regresses against a closed-form target. RL post-training aligns the model with a reward. In image generation, this makes samples compose objec…
arXiv:2605.07746v1 Announce Type: new Abstract: High-dimensional count data arise in applications such as single-cell RNA sequencing and neural spike trains, where mapping between distributions across successive batches or time points form critical components of data analysis. Th…
arXiv stat.ML
TIER_1·Hugh Dance, Johnny Xi, Peter Orbanz, Benjamin Bloem-Reddy·
arXiv:2605.07665v1 Announce Type: new Abstract: Estimating counterfactual distributions under interventions is central to treatment risk assessment and counterfactual generation tasks. Existing approaches model the counterfactual distribution as a standalone generative target, wi…
Density estimation and reliable prediction regions for outputs are crucial in supervised and unsupervised learning. While conformal prediction effectively generates coverage-guaranteed regions, it struggles with multi-dimensional outputs due to reliance on one-dimensional nonconf…
High-dimensional count data arise in applications such as single-cell RNA sequencing and neural spike trains, where mapping between distributions across successive batches or time points form critical components of data analysis. The recent success of diffusion- and flow-based de…
Pixel-space diffusion has re-emerged as a promising alternative to latent-space generation because it avoids the representation bottleneck introduced by VAEs. Yet most existing methods still treat image generation as a frequency-homogeneous process, overlooking the distinct roles…
Recent flow matching (FM) methods improve the few-shot adaptation of vision-language models, by modeling cross-modal alignment as a continuous multi-step flow. In this paper, we argue that existing FM methods are inherently constrained by incompatible geometric priors on pre-trai…
arXiv cs.CV
TIER_1·Jiarui Xing, Song Wang, Jian Wang·
arXiv:2605.00941v1 Announce Type: cross Abstract: Flow matching has become a leading framework for generative modeling, but quantifying the uncertainty of its samples remains an open problem. Existing approaches retrain the model with auxiliary variance heads, maintain costly ens…
arXiv cs.CV
TIER_1·George Stoica, Sayak Paul, Matthew Wallingford, Vivek Ramanujan, Abhay Nori, Winson Han, Ali Farhadi, Ranjay Krishna, Judy Hoffman·
arXiv:2605.00825v1 Announce Type: new Abstract: Flow matching (FM) trains a time-dependent vector field that transports samples from a simple prior to a complex data distribution. However, for high-dimensional images, each training sample supervises only a single trajectory and i…
Flow matching (FM) trains a time-dependent vector field that transports samples from a simple prior to a complex data distribution. However, for high-dimensional images, each training sample supervises only a single trajectory and intermediate point, yielding an extremely sparse …