We present Alignment-Free Text-Audiobox (Text-AB), a unified framework for high-quality voice dubbing and full-duplex dialogue synthesis. Building on a Diffusion Transformer trained with a flow-matching objective, Text-AB departs from the Audiobox system along three dimensions. First, it operates in a latent diffusion framework using DAC-VAE features that encode 48 kHz waveforms into a 25 Hz latent sequence, giving over 10x higher compression than previous EnCodec representations while improving resynthesis quality. Second, Text-AB is alignment-free: it consumes raw text via an off-the-shelf text encoder and learns text-speech alignment through cross-attention, removing the need for forced alignment and explicit duration prediction. Third, we scale model and data substantially, pretraining a 3B-parameter model on 480k hours of monolingual speech, followed by supervised fine-tuning on three downstream tasks: cross-lingual voice dubbing, full-duplex dialogue synthesis, and emotional full-duplex dialogue synthesis. At inference, Text-AB supports one-shot generation for up to ~1 min of speech and arbitrarily long-form generation via a multi-diffusion scheme, plus a multi-stage reranking strategy that enhances quality based on automated metrics. On a real-world dubbing benchmark, Text-AB delivers a step-change improvement over the latest internal dubbing system, with large gains in prosody similarity, voice similarity, naturalness, and shareability. For full-duplex dialogue synthesis, it approaches human recordings on short-form conversations and substantially outperforms the latest internal model on long-form human-likeness and expressivity, while natively modeling turn-taking, back-channeling, and emotional dynamics. For emotional dialogue synthesis, emotion conditioning significantly improves emotion alignment and emotional interaction quality over the unconditioned baseline.
Tomas Guija-Valiente, Blanca Rodriguez-Gonzalez, Norberto Malpica +1cs.CV cs.AI cs.LG
Medical image inpainting has the potential to improve automated brain MRI analysis by reconstructing healthy tissue within pathological regions. We introduce RARF, a task-agnostic region-aware rectified flow framework for masked data generation. We instantiate the framework for 3D brain MRI inpainting as our submission to the BraTS Inpainting Challenge 2026. RARF restricts the stochastic interpolation process to the inpainting region, while the observed voxels remain fixed and provide patient-specific anatomical context. A three-dimensional neural network receives the partially voided image, with Gaussian noise filling the missing region, together with the inpainting mask and the corresponding timestep. The model is trained using masked flow-matching and reconstruction-consistency objectives, combined with mask-aware preprocessing and data augmentation. During inference, the learned velocity field transports the initial noise toward a plausible reconstruction of the missing tissue, which is then combined with the unchanged observed anatomy. Experiments under the BraTS evaluation protocol show that the proposed approach produces competitive reconstructions while maintaining anatomical consistency. Source code is available at: https://github.com/TomasGuija/rarf.
Quantum generative models offer a promising framework for exploring whether quantum computation can enhance generative machine learning. Flow matching is a generative method in which samples are generated by transporting a simple, known distribution to the target data distribution with a learned velocity field. Its quantum counterpart, known as quantum flow matching (QFM), was introduced recently, and, like its classical counterpart, requires integrating an ordinary differential equation over many time steps during inference. As each step requires the output from the previous step, the circuit submission is sequential and a drawback on quantum computers as they have high input/output costs. To alleviate this problem, we introduce Quantum MeanFlow (QMF), the quantum analogue of the MeanFlow formulation, which allows single-step sample generation. While the QFM learns an instantaneous velocity field at each time step, QMF learns the average velocity over a time interval. We use a parameterized quantum circuit to learn these velocity fields and benchmark the two methods on the MNIST dataset. We show that while single-step QMF has lower image quality compared to multi-step QFM, it performs better than the single-step QFM sampling at every shot count. Both of our models are executed on IBM quantum computers and best-of-N rejection sampling recovers most of the accuracy lost to device noise without modifying the circuit. This is especially advantageous for QMF which has only one circuit evaluation per image. Here, We establish QMF as a viable method for single-step quantum generative sampling, saving on quantum circuit evaluations per generated sample.
Structural magnetic resonance imaging (MRI) images are sometimes corrupted over a contiguous set of slices, where acquisition, motion, hardware, or reconstruction effects leave a single slice or short interval inconsistent with its neighbors while the rest of the image remains usable. Such localized corruption can bias downstream morphometric analysis, yet discarding or reacquiring an otherwise usable image is costly. We formulate this as an image restoration problem: given the location of the affected interval, reconstruct those slices from the surrounding anatomical and imaging context. We propose SliceBridge, a framework for restoring corrupted slice intervals in T1-weighted MRI using rectified flow matching conditioned on the surrounding intact slices and their relative slice positions. Through-plane consistency is encouraged by coupling the slices within the interval through interval-correlated initial noise, a shared flow time, and synchronized sampling. The restored interval is then inserted back, leaving all other slices unchanged. We trained and validated the model on 9,877 T1-weighted brain MRI volumes from four datasets and evaluated it on 581 external subjects using clean interval withholding and controlled corruptions. Compared with a matched model that reconstructed target slices independently, SliceBridge reduced error in slice-to-slice changes within repaired intervals by 32.9%-41.3% across interval lengths and achieved higher SSIM at every interval length. In controlled-corruption cases, SliceBridge reduced the median error in regional brain volume estimates produced by a downstream segmentation model from 1.95% in corrupted volumes to 1.05%.
Magnetic resonance images of the same subject look markedly different across field strengths, which complicates the comparison and pooling of data across sites. We address cross-field brain-MRI translation for the MRIxFields2026 challenge, and in particular its Task~3: a single model that translates between any directed pair of the five field strengths and across three contrasts. We phrase the problem as a conditional flow matching path: because the source and target volumes are spatially registered, we learn a velocity field that carries the source slice directly to the target slice, rather than starting from noise. To learn this mapping from only three paired subjects, the unified model is trained in three stages: a degradation-bridge pretraining that distills a restoration prior from the abundant unpaired retrospective cohort, a cross-field finetuning over all directed pairs on the paired cohort, and an adversarial refinement that sharpens the output. At inference, we integrate the learned velocity with a second-order Heun solver in a handful of steps. A restoration prior learned without any paired data already reaches a mean SSIM of 0.837, and each subsequent training stage improves on it. A single 6.3M-parameter model thereby covers all 60 field-pair and contrast combinations, with inference in five solver steps per slice. On the challenge evaluation set the model reaches a mean SSIM of 0.909, averaged over the three contrasts, outperforming regression and diffusion baselines built on the identical network on all three challenge metrics.
Solving multiphysics partial differential equations (PDEs) remains a major challenge in scientific computing, especially for highly complex $μ$m-scale tortuous geometries critical to energy and chemical engineering. We address this challenge by proposing a Geometry-aware Latent Autoregressive generative Model for PDEs (GeoLAMP) for solving physics within highly irregular and tortuous structures. GeoLAMP introduces a dual-encoder architecture on graph representations to jointly capture global topology and fine-scale geometric features, enabling an effective transition from real-space fields to compact latent representations. In the latent space, we propose a causal self-attention transformer with flow matching to model temporal dynamics, allowing stable and scalable block-wise autoregressive prediction. A flexible decoder reconstructs high-resolution physical fields on arbitrary points. We establish three multiphysics benchmark datasets in complex geometries, covering reactive flow, heat convection, and elasticity. GeoLAMP consistently achieves the most stable autoregression performance on these datasets, maintaining low errors throughout the entire rollout horizon. Our results provide a systematic study of geometry-aware learning for PDEs in $μ$m-scale complex geometries and offer new insights into block-wise time marching of latent autoregressive PDE modeling via a flow matching framework.
Modern explicit-time generative models, such as Flow Matching [Lipman et al., 2023] and Rectified Flow [Liu et al., 2023], are typically derived top-down via Optimal Transport and the continuity equation. This standard Eulerian approach focuses on the macroscopic transport of probability mass. In this paper, we present an alternative, bottom-up mechanical derivation grounded in a Lagrangian (particle-centric) perspective. By analyzing the local Taylor expansion of a continuous denoiser, we motivate a strict invariance condition required for optimal, singlestep generation: the conservation of target identity. Enforcing this condition yields a governing quasi-linear advection Partial Differential Equation (PDE). We demonstrate that solving this PDE via the Method of Characteristics analytically yields the straight-line trajectories of Flow Matching. This geometric perspective isolates the Jacobian of the denoiser as the primary source of trajectory curvature, providing a direct mathematical explanation for why straight-line flows enable massive step sizes, and why empirical models require distillation to flatten intersecting characteristics.
Real-world image super-resolution (Real-ISR) aims to preserve structures supported by the degraded observation while reconstructing perceptually realistic details. However, existing Real-ISR methods largely optimize fidelity and perceptual quality within a shared network, causing the two objectives to interfere throughout training and making their balance difficult to control. Recent one-step methods reduce sampling steps, yet often inherit both this coupled optimization behavior and the expensive high-resolution backbone of their multi-step predecessors. We argue that efficient Real-ISR requires not only a shorter sampling trajectory, but also specialized modeling of faithful reconstruction and perceptual detail synthesis. Based on this insight, we propose PixelIR, a fidelity-perception decoupling framework built upon pixel-space image-residual flow matching. PixelIR first learns an image flow that maps the degraded observation to a faithful reconstruction. Then, a residual flow synthesizes the missing perceptual details from noise without repeatedly relearning or overwriting the complete restoration solution. We further distill the teacher into a deployment-oriented one-step student within a coarse-to-fine pyramid architecture. Extensive experiments show that PixelIR achieves leading PSNR, SSIM, and LPIPS on both RealSR and DRealSR. The final model completes pixel-space restoration in a single evaluation with only 32.9M parameters, 89.7G MACs, and 8.5ms latency, demonstrating a strong practical fidelity-perception-efficiency balance.
Direct vision-language-action policies generate continuous robot actions efficiently, but standard behavior cloning leaves two complementary gaps: their representations are not explicitly required to describe how the scene evolves over multiple time scales, and deployment trajectories of unequal quality are often reused without separating useful dynamics from undesirable behavior. We introduce \method, a direct world-action policy that combines outcome-agnostic predictive learning with outcome-aware policy improvement. \method first retains a local fixed-offset JEPA objective and adds trajectory-relative multi-horizon transition alignment at 25%, 50%, 75%, and 100% of the remaining episode. These training-only targets require the current policy representation to preserve both local physical changes and longer-range task progress, without supplying explicit future tokens to the action head. \method then trains an independent distributional value critic on cumulative deployment trajectories, computes action-chunk-aligned $N$-step advantages, and converts them into positive, negative, or null text conditions for a flow-matching actor. Thus, every valid trajectory can teach what physically happened, while the actor is deployed only under the condition associated with relatively better actions. The multi-horizon predictor and critic are removed from online execution, preserving direct action generation from the current observation, language instruction, and proprioception. \redclaim{Across the three simulation benchmarks, \method achieves the strongest overall performance while preserving the direct actor's online execution path.}
Mohammad Nazeri, Alexandyr Card, Samira Huber +6cs.RO cs.CV
World models let robots imagine possible futures, but exploiting this capability for real-time control is bottlenecked by a representation misalignment: the generative model and the planner operate on decoupled manifolds, so the planner has no shared structure to search over and must instead decode every candidate back into high-dimensional pixel space to evaluate it. This decoding step is a major obstacle to real-time control on physical hardware. In this paper, we present Hydra, a discrete World Action Model that closes this gap by moving the planner, both the sampler and the evaluator, inside the model. Hydra establishes a unified latent manifold over visual states, physical poses, and control actions, then compresses this manifold through modality-specific Vector-Quantized bottlenecks into discrete vocabularies of kinodynamic intents and visual states. Because candidates are now drawn directly from this shared manifold, sampling is informed by the model's own understanding of the observation rather than proposed blind, and evaluation happens natively within the discrete space: candidates are ranked by a Kinematic-Perceptual Cost, without ever decoding to pixels. We term this Discrete Latent Planning (DLP). Because planning over discrete intents alone cannot supply the smooth, continuous commands physical actuation requires, Hydra pairs DLP with conditional Flow Matching, which maps each selected intent to a continuous trajectory for execution. Evaluated on two physical robotic platforms, Hydra outperforms state-of-the-art world models in goal-directed planning, while matching or exceeding the closed-loop execution capabilities of leading reactive foundation policies.
Flow matching enables likelihood-free training, yet alignment methods increasingly reuse conditional flow matching (CFM) losses as endpoint negative log-likelihoods (NLLs) and their old/new differences as log-likelihood ratios. We characterize when these substitutions are valid. For linear Gaussian paths, we exactly decompose endpoint NLL into entropy, a weighted CFM objective, an interior velocity--score residual, and a boundary residual. Thus CFM-only estimates and differences are exact only when the corresponding residuals cancel. At the off-policy population optimum, ordinary CFM is not generally a pointwise NLL estimator, whereas \(w_{\mathrm{sc}}(t)=(1-t)/t\) removes the interior residual; this positive result does not extend generally to training or on-policy alignment. On-policy log-ratios can remain biased even for identical endpoint laws or after surrogate optimization. Experiments across dimensions, distributions, and geometries support these conclusions and the mechanisms that make inexact ratios useful. **More broadly, the decomposition provides a theoretical basis for adapting likelihood-based LLM methods to flow matching, while distinguishing exact substitutions from controlled surrogates.**
Dynamic contrast-enhanced breast MRI is central to cancer diagnosis and monitoring, but requires gadolinium-based contrast agents. In this work, we address pre-to-post contrast breast MRI synthesis for the MAMA-SYNTH challenge. We propose MAMA-FLUX.2, a conditional latent flow-matching approach based on FLUX.2-Klein-4B. The pre-contrast image is encoded as spatial conditioning, while the model predicts the flow field associated with the post-contrast target latent. To adapt the pretrained model efficiently, we use LoRA fine-tuning and introduce a regional training objective combining global flow matching, tumor-region supervision, and stable foreground regularization. We further investigate LoRA rank, intensity windowing, and regional loss weights on axial slices, prioritizing clinically relevant tumor-focused metrics. Our ablation study shows that moderate tumor and stable-foreground weighting improves the trade-off between image fidelity and tumor-region accuracy. The final model achieves the best overall balance with LoRA rank/$α=64/64$, $\mathrm{MHA}_{\max}=25$, $λ_{\mathrm{tumor}}=0.25$, and $λ_{\mathrm{stable}}=0.1$. These results demonstrate that compact pretrained rectified-flow transformers can be adapted for contrast-enhanced MRI synthesis using parameter-efficient fine-tuning and task-aware regional losses.
Modern video games combine first-person perception, rapid visual changes, persistent world state, and heterogeneous native controls. Existing game agents map visual and task context directly to actions but lack explicit world dynamics modeling, whereas interactive game world models predict visual futures from supplied actions but do not serve as task policies. World-Action Models (WAMs) unify these objectives, but remain largely unexplored under the dynamics and open-ended interaction of video games. We introduce GameWAM, to our knowledge the first WAM for native closed-loop gameplay and GUI control. GameWAM jointly generates future visual observations and executable keyboard-mouse trajectories through parallel visual and action generative processes with block-causal conditioning and flow matching. To support joint world-action learning, we construct synchronized gameplay and GUI trajectories. To handle heterogeneous native control, GameWAM predicts a gameplay/GUI mode at each action step and generates actions with mode-specific prediction distributions and continuous-action normalization. For long-horizon interaction, block-cycle control predicts beyond the committed horizon, executes only a short action prefix, and replans from new observations, while fine-grained within-cycle context and hierarchical cross-cycle history preserve temporal continuity. Experiments demonstrate competitive task success with fewer executed native actions than the compared agents. We further uncover Low-Frequency Action Source Imprinting (LASI), in which low-frequency components of the sampled action source systematically steer coarse generated camera motion under fixed conditioning, revealing a source-sensitivity failure mode in generative control. Project page is available at https://yunncheng.github.io/GameWAM/.
Tianchi Liu, Zeyang Song, Tianrui Wang +3eess.AS cs.AI
Psychological research on emotion dynamics has established that human affect is a continuous, evolving process: emotions rise, decay, and transition within seconds. Current emotional text-to-speech (TTS) systems, however, condition on a single discrete label or static embedding per utterance, fundamentally misaligning with the temporal nature of affect. While recent LLM-based TTS systems may implicitly vary prosody through text understanding, such variation is neither explicitly controllable nor precise enough for targeted intra-utterance transitions. We address three challenges: (1) a multi-pass flow blending pipeline synthesizes frame-aligned transition audio, circumventing the scarcity of natural intra-utterance transitions; (2) dual-stage Valence-Arousal-Dominance (VAD) conditioning guides prosodic planning in the LLM and acoustic realization in the flow decoder via frame-level VAD embeddings; (3) direction-magnitude decoupled injection structurally separates emotion direction from injection magnitude, preventing content degradation. EmoTra-TTS adds only +0.43% parameters with no latency overhead, achieves 30%-87% relative improvement on emotion transition quality, corroborated by 64.4%-79.5% overall win rates in pairwise preference tests against four SOTA baselines and two commercial systems.
Ziying Song, Shengkai Zhang, Lin Liu +8cs.CV cs.RO
Long-horizon planning is critical for safe autonomous driving in complex scenarios. Existing methods improve planning continuity with temporal memory, but such memory may become invalid and mislead decisions when the driving command changes. Thus, selectively leveraging useful history while suppressing command-inconsistent memory remains a key challenge. To address this issue, we propose MomADv2, a reliable state-space memory framework for long-horizon end-to-end autonomous driving. At its core, MomADv2 introduces a Selective State-Space Planning Memory Query Module, which filters historical planning queries based on temporal continuity and command consistency, selects planning modes relevant to the current command, and models the evolution of planning intentions through a selective state-space mechanism. To further alleviate local trajectory deviations and error accumulation in long-horizon planning, we design a Flow-Matching Trajectory Residual Refiner. It learns a continuous residual correction field from the refined planning output to the expert trajectory, enabling fine-grained trajectory refinement while preserving the stability of anchor-based planning. Extensive experiments on closed-loop NAVSIM and Bench2Drive, as well as open-loop nuScenes, demonstrate that MomADv2 improves long-horizon planning consistency and reduces the average collision rate by 15.6% over MomAD under 6-second planning.
Vector sketches remain one of the most concise and immediate mediums for abstract human expression. However, generating high-quality vector strokes that exhibit human-like drawing styles remains an open challenge due to the severe scarcity of fine-grained, high-quality text-to-sketch paired data. Existing text-conditioned generation methods often rely on unstable, time-consuming optimization or struggle to generalize to unseen categories in a zero-shot manner. To address these limitations, we present SketchFlow, a novel generative framework rooted in Optimal Transport (OT) theory and flow matching. By leveraging pre-trained CLIP models to bypass labor-intensive image-level text annotations, we formulate cross-modal alignment as a continuous mapping problem directly within the CLIP latent space. To bridge the inevitable modality gap between discrete text concepts and continuous sketch features, we first inject noise into discrete category embeddings to construct a continuous Gaussian Mixture Model (GMM) prior. We then utilize an Optimal Transport Conditional Flow Matching (OT-CFM) model to learn a deterministic vector field mapping from this continuous GMM prior to the target sketch feature distribution. Finally, a Hybrid Diffusion Decoder, fusing 1D U-Net and Transformer architectures, is designed to decode these features into fast and high-fidelity stroke trajectories. Extensive experiments demonstrate that SketchFlow substantially outperforms existing baselines in visual quality and adherence to natural human drawing styles. Furthermore, our geometry-preserving framework demonstrates promising local zero-shot synthesis for prompts beyond the QuickDraw training vocabulary, including unseen concept labels and semantic modifiers, while enabling smooth, continuous semantic interpolation between distinct concepts. Source code is available at: https://github.com/doudin404/SketchFlow.
Video Joint Embedding Predictive Architecture (V-JEPA) learns powerful spatiotemporal representations from video through self-supervised latent feature prediction. However, V-JEPA is built around random-mask completion and deterministic regression, making it fundamentally ill-suited for autonomous driving planning that demands future-directed prediction tightly coupled with action. To address this, we rethink the V-JEPA paradigm and present WA-JEPA, a V-JEPA-native world-action model designed for autonomous driving planning. Instead of random spatiotemporal masking, WA-JEPA employs hybrid future-masked pre-training, where the model infers future latents from observed context. Departing from deterministic regression, we recast future prediction as conditional flow matching over latent futures, which substantially improves the model's ability to generate plausible future latents for downstream planning. Finally, a joint future-action predictor is proposed to denoise future scene tokens and ego trajectories together in a unified spatiotemporal latent space, allowing action supervision to directly shape planning-relevant world representations. Pre-trained on nuPlan videos and fine-tuned on NAVSIM, WA-JEPA reaches 91.7 EPDMS on NAVSIM-v2, surpassing the strongest end-to-end and world-action baselines by 1.6 and 1.3 EPDMS, and, without HUGSIM-specific fine-tuning, attains the best HD-Score of 0.4462 on the closed-loop HUGSIM benchmark under the same evaluation protocol. These results validate V-JEPA-native world-action modeling as a powerful and scalable paradigm for autonomous driving planning. Code is available at https://github.com/AFARI-Research/WA-JEPA.
Preference optimization is a standard alignment method for generative models, yet extending it to continuous-time dynamics remains non-trivial. In flow matching, reward-driven updates modify transport trajectories without an inherent constraint to the pretrained data manifold and can move terminal samples off the pretrained support. We formalize this failure mode as manifold drift. Theoretically, we show that optimal flow matching recovers the terminal data distribution, whereas a preference update leaves the pretrained manifold whenever its induced terminal displacement has a nonzero normal component. As a remedy, we propose ThermoDPO, a temperature-controlled objective that anchors pairwise preference optimization on preferred samples. Across temperature regimes, this objective connects rejection sampling fine-tuning and FlowDPO and controls a pointwise reconstruction-based surrogate for manifold distance. To counteract diminished signals at low temperatures, we further introduce a weighted variant, ThermoDPO-weighted. On the main toy benchmark, ThermoDPO-weighted attains a StrictScore of 0.899, compared with 0.629 for FlowDPO and 0.857 for FlowDPO+RFT. On SD3.5-M at CFG = 4.5, it improves OCR by 47.5% and the average of four metrics by 16.0%.
This paper introduces Tensor Field Models (TFMs), realization-level Mathematical Structures in which a learned Operator maps a product of admissible component-section families to a prescribed family of time-dependent tangent sections on a Generative State Manifold. Analytic and dynamical restrictions are encoded through the choice of admissible families rather than imposed by the root definition. Constructed, component-separable, and Tensor Bundle TFMs provide structured refinements of this common object. In the conditional realizations considered here, a structured condition $c=(c_1,\ldots,c_n)$ is mapped componentwise to a reusable collection $\mathbf H_c=(H_{c_1}^{(1)},\ldots,H_{c_n}^{(n)})$. In the architectures evaluated here, the component representations remain distinct and are combined only by the Field Operator to produce the generated Vector Field. All learned models are trained using Flow Matching. Experiments show that TFMs can improve performance and that amortized sampling enabled by reusable condition representations can accelerate generation.
Generative novel view synthesis from sparse input images is rarely all reconstruction or all generation: pixels visible in some source view have a unique correct value modulated only by view-dependent shading, while pixels in disocclusions or beyond the captured volume admit a distribution of plausible completions. Existing generative novel-view-synthesis methods conflate these regimes under a single uniform loss, blurring the line between geometric fidelity and creative hallucinations even when scene geometry is injected through warped point clouds or projected depth. We introduce GenRec, a multi-view flow matching model that builds the reconstruction--generation split directly into its architecture, supervision, and gradient flow. Guided by an observation mask derived from the source cameras and a monocular depth estimator, a flow matching backbone jointly denoises RGB and scene-coordinate maps across all target views, while a pixel-space refinement stage restores high-frequency detail on observed pixels; the same mask gates supervision so regression signals do not contaminate the generative prior. Across RealEstate10K, DL3DV-10K, and Mip-NeRF~360, in both single-view extrapolation and two-view interpolation, GenRec attains the best reconstruction fidelity in observed regions while also surpassing purely generative baselines on perceptual quality in unobserved ones, showing the effectiveness of our approach.
Unified image restoration (UIR) aims to recover high-quality (HQ) content from low-quality (LQ) images with different degradations using a single model. Most recent methods adapt large pretrained text-to-image (T2I) latent diffusion models for their strong capacity and generative priors. However, the variational autoencoder (VAE) in latent T2I models may discard restoration-sensitive details, while the open-ended synthesis prior can introduce content-inconsistent artifacts. We present PixRestore, a VAE-free pixel-space Diffusion Transformer (DiT) for UIR, where the diffusion backbone is trained entirely from scratch, without relying on T2I pretraining. PixRestore performs flow matching directly on patchified pixels, preserving fine-grained details while keeping the token sequence tractable. To adapt to different degradations, PixRestore learns to predict the reliability of layer features using LQ--HQ DINO feature similarity. Features from more reliable layers are fused as dense conditioning, while less reliable layers receive stronger HQ-feature supervision to encourage degradation removal. We train PixRestore on a large-scale corpus of diverse scenes and degradations, and further finetune it into a one-step generator using DINO-based adversarial objectives for efficient inference. Experiments on public benchmarks and real-world test sets show that, with only about 50M parameters and single-step inference, PixRestore achieves the best overall fidelity, perceptual quality, and robustness to degradations among competing UIR models while being far more efficient. Larger PixRestore variants can further boost performance, demonstrating the scalability of our pixel-space design. Code and the curated benchmark can be found at https://github.com/csslc/PixRestore.
Current flow matching models learn to transport the source i.i.d. Gaussian noise into the target distribution of natural images, yet this source distribution carries no notion of spatial structure. Images however are fundamentally local since nearby pixels are strongly correlated. By sampling the noise independently, we hypothesize that models are implicitly encouraged to exploit less noisy neighbors as context during training, partially bypassing the need to properly learn the true local structure of images. The source distribution, in other words, works against the inductive bias of the image domain. To ameliorate this design discrepancy, we propose StructFlow which encodes spatial locality directly into the source by having the pixels within a small region share a common noise component. This structured source produces transport paths that are geometrically aligned with image regions - enabling properties that generic flow matching struggles to provide: fine-grained local editing that naturally respects boundaries, robust structure preservation, and smooth semantic interpolation between images. We show that these benefits also extend to large pre-trained models, demonstrating that StructFlow can even be incorporated through a lightweight post-training phase. Comprehensive experiments on multiple datasets, in unconditional, class and text-conditioned regimes, using different diffusion transformer architectures confirm that StructFlow not only offers competitive image generation quality, but also significantly improves localized controllable re-synthesis.
Limit order book (LOB) simulators are most useful to practitioners when they combine realistic market dynamics, computationally efficient sampling, controllable scenario generation, and the ability to generalize beyond the instruments seen during training---properties that existing agent-based and deep generative simulators provide only partially. We present \textbf{FlowLOB}, a conditional \textbf{flow}-matching generator of \textbf{LOB} trajectories, trained on multiple Hong Kong Exchange (HKEX) symbols at three sampling frequencies ($0.1$s, $1$s, $10$s) in tick-relative representation that transfers to unseen instruments. Because flow and diffusion models admit a common formulation, we train both with identical data, architecture, and budget, and sample both through the same fixed-step ODE solvers, yielding a controlled comparison of sampling efficiency and fidelity. Flow matching attains its best quality with only $10$ ODE-solver steps, whereas diffusion needs many more function evaluations to approach the same fidelity. At this efficient operating point, FlowLOB improves realism over baselines, two learned and two agent-based models, in most distributional metrics at the two finer sampling frequencies. We evaluate counterfactual controllability with a distributional test that asks whether changing a scenario condition moves the generated statistic toward the corresponding real tail regime; FlowLOB satisfies this criterion in most tested settings. Both realism and control effects transfer zero-shot on a held-out symbol. We additionally conduct ablation studies on the network architecture and the learning rate.
High-fidelity image generation faces a trade-off between speed and quality. Diffusion models produce strong visuals but require costly iterative sampling. Existing efficient methods mainly distill pretrained models into few-step samplers, a challenging process that depends heavily on teacher-model quality. In this paper, we introduce XYZFlow, a framework that rethinks efficient generation through multidimensional scaling of flow matching. Unlike single-step mappings, XYZFlow enhances expressivity by making probability paths more identifiable and learnable through structured multidimensional conditioning. We view autoregressive modeling as implicit flow straightening, where richer context reduces trajectory ambiguity. XYZFlow realizes this idea through two orthogonal dimensions: temporal scaling, which uses non-Markovian conditioning on the full denoising history; and spatial scaling, enabled by Next Shortcut Prediction, which sequentially generates patches using preceding patches' denoising trajectories as priors. Experiments show that XYZFlow achieves state-of-the-art performance, with 7.2-8.5X teacher speedups and competitive FID, while Next Shortcut Prediction delivers superior quality-latency trade-offs over model scaling or step reduction.
Recent advances in zero-shot text-to-speech (TTS) have substantially improved speech quality and voice cloning fidelity. However, many zero-shot TTS systems still depend on audio prompt transcripts at inference time. This dependency limits cross-lingual voice cloning, since in-the-wild reference audio is often untranscribed. In this technical report, we present Confucius4-TTS, a multilingual zero-shot TTS system that supports 14 languages and performs both intra-lingual and cross-lingual reference cloning without requiring transcripts of audio prompts. Confucius4-TTS follows a two-stage architecture, consisting of text-to-semantic (T2S) and semantic-to-acoustic (S2A) modules. The LLM-based T2S module uses a learnable speaker encoder to extract timbre features from self-supervised speech representations, and the conditional flow-matching S2A module converts the predicted semantic tokens into mel-spectrograms. The same model also supports continuation cloning when a reference transcript is available. Confucius4-TTS is trained on large-scale multilingual speech data. It achieves high intelligibility and speaker similarity on public benchmarks. On the CV3-Eval cross-lingual benchmark, Confucius4-TTS obtains an average WER of 3.73% across six directions. On our internal cross-lingual set, it achieves the best average overall rank in human evaluation among recent open-source and commercial systems. We release code, model checkpoints, and demos at https://github.com/netease-youdao/Confucius4-TTS.
Sangwoo Jo, Donggeun Ko, Jayeon Kang +3cs.CV cs.AI cs.LG
Image restoration is fundamentally constrained by the tradeoff between distortion and perception: minimizing pixel-wise error yields over-smoothed results, whereas optimizing for perceptual realism often introduces structural deviations. Recent approaches attempt to balance this tradeoff via posterior sampling or multi-stage generative pipelines, yet remain computationally expensive and architecturally complex. To overcome these limitations, we propose PCFlow (Perceptually Consistent Flow Matching), a unified framework that directly parameterizes a continuous transport from degraded observations to clean targets, jointly optimizing distortion and perceptual quality. While its latent consistency flow objective drives stable and efficient few-step inference, a Latent Consistency Perceptual Loss (LCPL) imposes semantic constraints directly on the guiding velocity field, steering the dynamics toward visually sharp data manifolds. Furthermore, recognizing the inherent conflict between structural and perceptual consistencies, we integrate a conflict-free gradient projection strategy to stabilize the multi-objective optimization landscape. Combined with lightweight, convolution-only backbone, PCFlow achieves competitive performance across diverse restoration tasks at a fraction of traditional computational costs.
Hansen Jin Lillemark, Alex Rojas, Zachary Novack +5cs.CV cs.AI cs.LG
Standard autoregressive video generation algorithms based on Diffusion and Flow Matching rely on rigid training objectives and static sampling schedules, limiting inference procedures from adapting to the data. We introduce Equilibrium Forcing (EqF), a simplified framework for video denoising generative models without noise level conditioning. EqF pioneers modular training- and inference-time designs for noise-unconditional generation that decouple learning the denoising field from sampling. This flexibility allows for inference-time algorithms that operate in a closed loop by adapting to feedback from the sample, improving video quality and consistency on challenging autoregressive video generation benchmarks. Extensive analysis elucidates exactly how removing the noise level conditioning enables EqF's data-dependent inference properties to surpass the performance of standard noise level-conditional denoising video methods.
Lisa K. Fischer, Mykhailo Riabets, Daniel Rueckert +3cs.CV cs.AI cs.LG
Large-scale multi-modal MRI datasets impose substantial storage and I/O costs, limiting the training of 3D generative models on commodity infrastructure. While lossy compression is known to preserve accuracy for discriminative segmentation networks, its effect on generative models, which must learn the full data distribution rather than a decision boundary, is unexplored. We study whether standard image codecs can effectively compress semantically rich brain tumor MRI while preserving the fidelity required to train and deploy a 3D MRI generative model. Each 3D volume is compressed with JPEG2000 or a near-lossless JPEG-LS pipeline. Next, a Wavelet Flow Matching model, conditioned on BraTS image sequences (T1n, T1c, T2, T2f), is trained on compressed data, and the resulting models are evaluated on the validation set. At a 20:1 compression ratio, synthesis quality is statistically equivalent to a model trained on uncompressed data within a pre-specified margin ($Δ$PSNR $<1$,dB, $Δ$SSIM $<0.02$; paired TOST $p=[[p]]$): mean PSNR is 27.3,dB vs. 27.0,dB and mean SSIM is 0.95 vs. 0.96 across modalities. Our results indicate that JPEG2000 compression is a practical step toward scalable 3D MRI generative modeling without degrading synthesis quality. The codebase is available at https://github.com/lisafis/MRIComp4Flow .
Existing unified 4D reconstruction and point tracking approaches typically rely on heuristic interpolations or just predict at integer timestamps, lacking kinematic coherence and failing to model dynamics at any arbitrary timestamp. In this paper, we propose Uni4R, a framework that unifies these tasks by learning continuous velocity fields through the synergy of Optimal Transport (OT) and Ordinary Differential Equation (ODE). Importantly, this continuous velocity field acts as a kinematic prior that mutually benefits both 4D reconstruction and point tracking. Specifically, we propose the Flow Matching Guided Decoder (FMGD). A global velocity branch first extracts anchor features that capture the global dynamic state of the sequence. Then, FMGD leverages Flow Matching (FM) theory to formulate a probability path defined by OT on the anchor feature manifold, instantiating it as FM-guided velocity features for velocity prediction. This establishes a robust kinematic inductive bias. Meanwhile, a point reconstruction branch provides geometric features. The local velocity prediction module then joint above features and time embeddings, to decode velocities at arbitrary timestamps. To overcome the absence of high-quality ground-truth velocities in fractional frames, we propose an integral-consistency training strategy. This strategy uses an ODE solver to integrate velocities to recover target pointmaps, enabling the model to be supervised end-to-end directly from integer timestamps. Experimental results demonstrate that Uni4R achieves SOTA performance in both 4D reconstruction and point tracking, and achieves SOTA in our new kinematics-aware benchmark at continuous time.
Yuqian Zhang, Yao Shi, Kexin Huang +7cs.SD cs.AI cs.CL
Zero-shot text-to-speech (TTS) now supports interactive assistants, personalized media, and accessibility tools. All TTS systems require faithful linguistic rendering, consistent speaker identity, and low-latency response. Yet compact streaming systems must preserve sufficient acoustic detail in a predictable low-rate latent sequence, while iterative diffusion sampling and classifier-free guidance multiply inference cost at every autoregressive step. To strike a balance between high-fidelity synthesis and low-latency inference, we present CuteTTS, a compact continuous-autoregressive TTS system. It combines semantically aligned causal VAE latents with patch-level autoregression, explicit speaker conditioning, and a bidirectional flow-matching head. We further introduce guidance-step distillation, which absorbs classifier-free guidance and multiple solver steps into a single interval-conditioned student. Evaluations on LibriSpeech and Seed-TTS-Eval demonstrate competitive intelligibility and speaker similarity in zero-shot voice cloning, while distillation lowers first-audio latency by 23.3% and real-time factor by 40.8% relative to the base model with comparable objective and subjective quality. These results provide a practical path toward continuous-autoregressive TTS that reconciles high-fidelity generation with the latency demands of real-time interaction.