Diffusion
-
WorldSonus: Bringing Sound to Worlds
2026-10-06 17:50:18Pengjun Fang, Jingyi Fa, Kam Man Wu, Jiaming Wang, Haoyuan Huang, Yaguang Wu, Xiangjun Huang, Ziyang Ma, Weijia Chen, Hongyu Liu, Zeyue Tian, Qifeng ChenAbstract
Recent advances in world models have enabled increasingly realistic visual synthesis. However, these generated environments remain largely silent. Bringing sound to world models poses three core challenges: real-time generation to keep pace with interactive video streams, interactive control to respond to mid-stream sound instructions, and spatially aligned stereo to reflect scene geometry and camera motion. To address these demands, we introduce WorldSonus, an interactive video-to-audio framework designed for real-time spatial sound synthesis in world models. For real-time generation, WorldSonus employs a streaming causal autoregressive diffusion architecture that synthesizes audio chunks at a low real-time factor (RTF) of 0.41. For interactive control, we incorporate an audio-centric captioning pipeline with chunk-indexed prompt scheduling, enabling dynamic manipulation of sound events during generation. For spatial alignment, we leverage high-quality stereo supervision curated from diverse stereo and ambisonic data. Extensive experiments demonstrate that while tailored for world models, WorldSonus generalizes effectively to open-domain video-to-audio benchmarks, matching or outperforming state-of-the-art bidirectional models in both acoustic quality and spatial alignment. Project page: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2610.08760
PDF
-
Denoising Hierarchical Representations: Joint Continuous Diffusion for Language Modeling
2026-10-06 17:38:19Mathias Ollu, Nikos KomodakisAbstract
Diffusion Language Models (DLMs) hold the promise of order-agnostic, parallel text generation. Recently, continuous diffusion and flow matching models have seen substantial gains, driven by carefully crafted token representations and diffusion/flow spaces. In this work, we introduce Hierarchical Continuous Diffusion Language Models (H-CDLMs), a simple framework that further improves continuous DLMs with minimal compute and parameter overhead. Drawing on the discrete DLM and continuous image diffusion literature on joint diffusion, we diffuse multiple modalities in parallel. These modalities represent tokens at different semantic granularities: in our instantiation, the tokens themselves and coarser clusters obtained by clustering pretrained token embeddings. We propose a general setup that allows per-modality samplers and schedules to enhance the interplay between modalities. Applied to CoBit, this yields H-CoBit, which delivers large empirical gains across benchmarks. At dataset entropy, H-CoBit improves MAUVE and reaches a generative perplexity (GenPPL) of 49.4 on LM1B and 50.4 on OWT, improving on the baseline by 24.2 and 20.7 points and surpassing even discrete DLMs of comparable size. On GSM8K, it reaches 27.4% accuracy, outperforming prior continuous diffusion and flow-based models. We further apply H-CDLM to the flow matching model FLM, obtaining consistent gains with H-FLM and demonstrating that the framework generalizes across continuous generative paradigms. Our code will be made publicly available at this https URL .
Abstract (translated)
URL
https://arxiv.org/abs/2610.08738
PDF
-
Disentangling Paradigm, Identifier, and Decoding in Generative Retrieval
2026-10-06 17:23:47Hicham Randrianarivo, Logan Renaud, Alexia AllalAbstract
Generative retrieval trains a language model to generate the identifier of a relevant document. Recent work replaces the autoregressive decoder with diffusion, but changes identifiers, training recipe and decoding at once, so differences cannot be credited to the paradigm. On NQ320K and MS300K, we train autoregressive, masked-diffusion and block-diffusion models with residual-quantised, product-quantised and random identifiers. With identifier length and training budget fixed, we decode each model in several ways. Decoding alone moves a diffusion model's Hit@1 by 6.6 to 13.7 points. Our reference diffusion decoding, generate-and-match, generates an identifier, then retrieves the closest corpus identifiers. The generated identifier is right for 14-21% of NQ320K queries. We test one-pass scoring to decode diffusion retrievers: the model reads a fully masked identifier once, and each document is scored by its codes' probabilities. It matches or beats generate-and-match in 11 of 12 settings. Autoregressive models still lead in Hit@1; on NQ320K, the lead comes from the model, not beam search. Starting from one sampled identifier, one-pass scoring removes 46-83% of masked diffusion's deficit to beam search; from generate-and-match, at most a quarter. On NQ320K, every paradigm largely memorises which identifier answers which query: random identifiers keep 83-90% of the Hit@1 of residual-quantised ones. There, product-quantised identifiers lead residual-quantised ones by 3.4 points in the autoregressive model and by -0.7 to +3.6 in diffusion models; across decodings, AR's gap exceeds diffusion's by 1.5-2.3 points, around our 2-point threshold. Paradigm comparisons must report each paradigm at its own recipe and best decoding.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08716
PDF
-
Local Content-Style Control for Diffusion-based Image Stylization
Abstract
Image stylization with latent-diffusion models entangles two independently refined axes: what a region depicts and how it is depicted. Such pipelines expose only global controls, yet professional retouching demands deliberate, region-specific control. We lift two conditioning weights already present in a ControlNet + IP-Adapter stylization pipeline from global scalars to per-location spatial maps, yielding local, per-axis control of content and style in a single generative pass. Because the two weights act on disjoint pathways, adjusting them independently spans a 2x2 retouching vocabulary, from free regeneration to identity preservation. We validate that edits stay confined to the retouched region and that each weight predominantly steers its own axis. Our approach requires no retraining and drops unchanged into any such pipeline.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08704
PDF
-
Feature Information Dynamics in Diffusion
2026-10-06 16:24:07Jia-Shu Pan, Tao Zhang, Yufei Huang, Yanjun Sheng, Tailin WuAbstract
Diffusion models generate data through a continuum of denoising problems, and are widely observed to reveal coarse structure before fine detail. Yet, this intuition is mostly empirical and qualitative. We introduce feature information dynamics, an information-theoretic framework for localizing when a feature is generated during diffusion. Using the I-MMSE identity, we connect the rate of feature mutual information change to a gap between optimal unconditional and feature-conditional denoising losses, yielding practical estimators for feature information density. We further develop a chained decomposition that separates shared from incremental information in a feature hierarchy. We use this framework first to quantitatively confirm spectral autoregression in pixel diffusion, and then to extend the analysis beyond frequency: under a class $\to$ mask $\to$ Canny conditioning chain, the per-feature information densities differ across pixel, SDVAE, VAVAE, and RAE, exposing fundamental differences between these representations and suggesting that ordered generation could be beneficial for training diffusion models. Our code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08626
PDF
-
LiDAR Resolution Recovery via Foundation-Model-Guided Diffusion
2026-10-06 16:20:20Samed Do\u{g}an, Nico Leuze, Alfred Sch\"ottlAbstract
High-beam-count LiDAR sensors are costly, yet many perception pipelines require dense angular sampling. Using a pretrained Stable Diffusion model as the backbone, we fine-tune a LiDAR-conditioned depth model with pseudo-depth targets from a 2D foundation model. During training, the LiDAR conditioning is randomly decimated at different beam budgets. We then investigate how much of a LiDAR scan can be recovered from heavily decimated input and characterize performance across the input beam budget. We evaluate against physically held-out real beams on nuScenes and report recovery separately from fit accuracy. Our model yields its largest advantage in very sparse regimes, achieving a $\delta_{1.25}$ accuracy of $66.8$% from $4$-beam input where scattered interpolation reaches only $45.1$%. A class-stratified error breakdown further reveals that planar surfaces recover first while objects introducing depth discontinuities degrade earliest. Together, these results quantify the recovery/resolution trade-off for foundation-model-guided LiDAR enhancement.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08620
PDF
-
One for All, All for One: Coordinated Multi-Agent Diffusion Steering via Stochastic Optimal Control
2026-10-06 16:02:49Riccardo Barbano, Vincent Pauline, Runchang Li, George Webber, Alexander Denker, \v{Z}eljko Kereta, Stefan Bauer, Francisco Vargas, Esmeralda S. WhitammerAbstract
Deep generative models often produce structured outputs composed of interacting components. Modelling these outputs with a single model requires learning both the component distributions and their interactions. We pursue a modular alternative: reuse independently trained component generators and learn only how to coordinate them to produce coherent structured outputs. Our framework, Coordinated Multi-Agent Diffusion Steering (CMDS), treats frozen pretrained diffusion models as reusable generative primitives and coordinates their reverse processes through a learned control. We formulate coordination as a stochastic optimal control problem, balancing an assembly-level reward that specifies the desired properties of the combined output against deviations from the pretrained dynamics. The learned control amortises this optimisation, allowing reuse across new task instances. Experiments show that CMDS can recover a known target distribution, satisfy different spatial constraints with the same trained control, and recover individual sources from degraded mixtures. Across multi-agent maze navigation, articulated robot planning, and text-conditioned human motion, CMDS turns frozen models into coordinated multi-agent generators.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08595
PDF
-
Digital Twin-Driven Real2Sim2Real: Simulator-Conditioned Generation via Paired Driving-Scene Reconstruction
2026-10-06 13:36:50Hojun Lim, Hyeongseok Jeon, Donghyun Kim, Soonyoung Jung, Heecheol YooAbstract
Camera-based 3D perception for autonomous driving relies heavily on large annotated datasets, and deploying such a system to a new target region typically requires data collection and annotation. Generative augmentation has been proposed to reduce this cost, but existing approaches face a fundamental trade-off: label-conditioned methods consume the very annotations they aim to replace, while simulator-conditioned methods offer free annotations but lack visual grounding to specific real environments. This work investigates the extent to which a digital-twin-driven Real2Sim2Real pipeline (DT-R2S2R) can substitute for target-region real data. By reconstructing recorded driving clips inside a georeferenced digital twin (DT-R2S), we condition a diffusion model on geometrically aligned simulator renderings, establishing a digital twin-grounded Sim2Real model (DT-S2R). As a result, DT-S2R synthesizes photorealistic driving images given low-cost yet georeferenced simulator data across both reconstructed and novel simulator scenes within digital-twin coverage. The efficacy of generated data is verified on diverse 3D detectors. DETR3D, especially, reports 93.18% of mAP obtained by a target-region real-data oracle, without employing target images for detector training. Furthermore, simple co-training with existing out-of-target real data outperforms the oracle. Thus, DT-R2S2R can substantially reduce the cost of manual on-site data collection and annotation in digital twin-available districts, providing a practical foundation for scaling 3D perception.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08339
PDF
-
MARCO: The Radioactive Watermark for Protein Generative Models
2026-10-06 13:18:22Huajie Chen, Xin Guo, Yuchen Shi, Yuchen Zhong, Minhui Xue, Chi Liu, Congcong Zhu, Kun Gao, Minfeng Qi, Tianqing ZhuAbstract
Protein Generative Models (PGMs) have revolutionized structural biology by enabling the design of complex 3D protein structures from sequence data. However, this breakthrough introduces a dual-use challenge, exposing high-value PGMs to economic risks like unauthorized model extraction and biosecurity threats such as biohazard synthesis. To mitigate these threats, we propose \textbf{MARCO} (\textsc{COnformation waterMARk}), the first radioactive watermarking framework specifically tailored for PGMs. MARCO establishes a Dual-Layer defense that simultaneously protects intellectual property and ensures the forensic traceability of potential biosecurity misuses. (i) To preserve efficiency, MARCO iteratively embeds watermarks during diffusion reverse denoising via an auxiliary encoder-decoder, allowing the original PGM parameters to remain frozen for broad compatibility. (ii) To preserve biophysical fidelity and maximize robustness, we employ specialized loss functions targeting $C_\alpha$-atom pairwise distances and torsion angles ($\psi, \phi$) within an adversarial training framework integrated with stochastic attack simulations. (iii) Crucially, MARCO exhibits ``radioactivity'' where the watermark automatically transfers to the outputs of any pirate models trained on the watermarked data, effectively countering model extraction attacks. Comprehensive experiments demonstrate that MARCO achieves superior fidelity and robustness while successfully validating watermark transferability.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08316
PDF
-
AutodidactWAM: Cross-Modal Self-Distillation from Generated Video to Robot Actions
2026-10-06 10:39:42Sergei Kurchev, Iaroslav Kolomiets, Miguel Altamirano Cabrera, Artem Lykov, Dzmitry TsetserukouAbstract
World-action models (WAMs) such as Cosmos 3 jointly generate future video and robot actions from an observation and instruction. Adapting one such model with a lightweight LoRA fine-tune to a previously unseen robot, a Unitree G1 humanoid with five-fingered BrainCo hands, exposes a video-action asymmetry: the video renders plausible task executions, while the co-generated action is systematically mis-targeted. We evaluate closed-loop real-robot trials at three cumulative stages: pre-grasp, grasp, and pick-and-place. The native action succeeds only approximately 17%, 10%, and 7% of the time, respectively, and performs worse on held-out objects. We propose AutodidactWAM, a hand-pose estimator trained without teleoperation, followed by inverse kinematics, that runs on the model's generated video to recover action estimates. Paired with the native prediction, these recovered actions provide preferred targets for fine-tuning only the action-related layers, while the generated video is teacher-forced. We compare supervised relabeling with a rectified-flow adaptation of Diffusion-DPO. After one-time embodiment adaptation, self-distillation requires no additional task-specific teleoperation. The recovered-action gate reaches approximately 75%, 47%, and 42% pre-grasp, grasp, and pick-and-place success, compared with 17%, 10%, and 7% for the native action. A hybrid objective combining preference supervision, supervised target fitting, and Cartesian trajectory anchoring (DPO+SFT+DTW) performs best: on Oreo, the training object, it reaches 90% pre-grasp and 20% full-task success; on a held-out object, it reaches 80% and 30%. Plain Flow-DPO reaches 0% success despite 1.000 validation preference accuracy, indicating that the combination of training objectives, rather than the contrastive objective alone, drives the observed gains.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08119
PDF
-
Two Halves are More than One: Phase-wise Velocity Distillation for Fast and High-Quality Image Generation
2026-10-06 10:03:30Zhen Guo, Rongyuan Wu, Qiaosi Yi, Chenxi Xie, Xinyu Wei, Lei ZhangAbstract
Recent diffusion-based image generation backbones have grown substantially in scale, making the network inference cost increase rapidly. While diffusion distillation techniques can reduce the number of inference steps, high-quality image generation within a single full-backbone-forward compute budget remains challenging. Existing one-step methods typically allocate this budget to a single evaluation of a monolithic student. However, approximating the heterogeneous coarse-to-fine transport with a single monolithic mapping is difficult and often leads to over-smoothed outputs. To address this issue, we propose Phase-wise Velocity Distillation (PVD), which partitions the generation timeline into a coarse and a fine phase, and models the transition within each phase via the average velocity. A dedicated half-sized expert is assigned to each phase, decoupling structural composition from detail refinement while keeping the cumulative computation equivalent to one full-backbone forward pass. We show that the use of two half-sized phase-specific experts outperforms a single full-size monolithic student. On class-conditional image generation, PVD achieves an FID of 1.48 on ImageNet 256 x 256. On more complex text-to-image (T2I) tasks, PVD-distilled models (Stable Diffusion 3.5-Medium, FLUX.1-dev, Qwen-Image) produce results competitive with their multi-step teachers, significantly outperforming prior distillation methods. Moreover, across the evaluated T2I backbones, PVD reduces active parameters by 49.10-50.89% and peak VRAM by 45.76-48.36% compared to the corresponding teachers. Source code and distilled models are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08070
PDF
-
PACE: Stage-Consistent Long-Horizon Robot Manipulation via Progress-Aligned Context for Execution
2026-10-06 07:58:47Yenan Chen, Junjie Shi, Lu Chen, Zhongxiang Zhou, Rong XiongAbstract
Demonstration-conditioned policies provide a natural interface for specifying robot behavior, yet long-horizon manipulation remains difficult when visually similar states recur across different stages or when demonstrations and executions proceed at different speeds. We identify the resulting failure mode as stage confusion and introduce Progress-Aligned Context for Execution (PACE), a stateful method that continually reinterprets a complete demonstration according to realized execution progress. PACE compresses the demonstration into ordered multimodal prompt tokens and uses training-only dual-edge attention supervision to expose its latent stage structure. During execution, an episode-local fast-weight memory causally encodes realized action-observation transitions and modulates prompt cross-attention, producing a progress-aligned context for a unified diffusion action expert without test-time stage labels or stage-specific policies. PACE improves success from 88.9% to 94.0% on LIBERO-Gen Goal Chain, from 79.1% to 83.3% on Spatial Combination, and from 33.3% to 73.3% on the two-step Block Routing tasks. Failure analysis further indicates that structured demonstration alignment and causal execution memory jointly mitigate stage confusion.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07917
PDF
-
Best-of-$N$ Guidance for Test-time Diffusion Alignment
2026-10-06 07:19:42Richard Lee Kim, Yeongmin Kim, Gyuwon Sim, Taekyu Kim, Minsang Park, Il-chul MoonAbstract
Diffusion models achieve strong generative performance but often struggle to align generated samples with human preferences measured by a reward model. A simple yet effective algorithm for test-time alignment is Best-of-$N$ (BoN) sampling, which draws $N$ i.i.d. samples from a pre-trained diffusion model and outputs the single highest-reward sample. Despite its empirical success, BoN makes limited use of reward information, as it is incorporated only at the final selection stage without influencing the reverse diffusion trajectory during sampling. Consequently, BoN sampling does not improve the average alignment of generated samples and is primarily suited to single-output settings. We propose Best-of-$N$ Guidance (BoNG), a novel method that integrates the principle of BoN sampling directly into the reverse diffusion process. BoNG performs online BoN selection over denoising particles and adjusts the reverse diffusion process to steer the particle population toward higher-reward regions during generation. Specifically, by introducing an asymmetric guidance interaction among denoising particles, BoNG uses the current BoN particle as a guidance signal to the rest of the particle population. This particle-level interaction reshapes the sampling process toward higher-reward regions, enabling BoNG to improve not only the final best sample beyond Vanilla BoN sampling, but also the average quality of generated samples. Over 36 empirical comparisons, BoNG achieves the best performance in 29 cases, ranking first in 80.56% of the comparisons against SMC and Vanilla BoN sampling. BoNG also supports multi-output capability, achieving 1.3$\times$ ImageReward score of the latest sample-based guidance method with a 1.6$\times$ speedup. We release the code at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.05108
PDF
-
Model-Based Geometry-Aware Generative Optimization for Constrained Locomotion Planning
2026-10-06 05:07:24Zhilin He, Xinyuan Wang, Changliu LiuAbstract
Constrained Locomotion Planning (CLP) for quadrupeds and humanoids, where robots must satisfy collision avoidance, contact consistency, kinematic feasibility, and support constraints, is challenging under high-dimensional dynamics and highly non-convex environments. Recent Model-Based Diffusion (MBD) approaches recast trajectory optimization as posterior sampling over trajectories, using known dynamics and Monte Carlo rollouts to analytically estimate the denoising score function without demonstration learning. While constrained variants further incorporate feasibility into model-based score rollouts and show promising performance, they are still limited by (1) lacking a task-modulated active constraint geometry that shapes the score direction and reverse stochasticity, and (2) using deterministic DDPM-style reverse transport without adaptive scheduling across different generative transports. Therefore, we introduce Model-Based Geometry-Aware Generative Optimization (2GO) for constrained locomotion, which turns active constraint geometry into executable denoising operators through normal- induced metric shaping, tangent-space stochastic filtering, and CFS-based retraction. 2GO further decouples generative transport from reverse stochasticity through an adaptive diffusion and flow-like schedule. Experiments on constrained quadruped and humanoid locomotion demonstrate strong performance in discrete foothold selection and continuous posture planning, with higher success rates, fewer violations, and improved execution compatibility.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07772
PDF
-
StairVLA: Stage-Aware Hierarchical Action Generation for Vision-Language-Action Models
2026-10-06 04:53:15Shangyuan Yuan, Xinda Qi, Yujiang Pu, Wenliang Guo, Xiaobo TanAbstract
Vision-language-action (VLA) models increasingly rely on diffusion- or flow-matching-based action heads to generate continuous robot actions. These action heads typically process the denoising trajectory in a largely uniform manner. However, we observe that the conditioning focus naturally shifts across denoising stages: early stages combine language instructions and visual observations to establish a coarse action trajectory, whereas later stages place greater emphasis on current visual observations for action alignment. Based on this insight, we introduce StairVLA, a stage-aware hierarchical action generation framework that uses partially denoised actions as a natural interface between coarse long-horizon action generation and local refinement. A high-level VLA performs early denoising to produce a reusable long-horizon partially denoised action trajectory, while a lightweight refiner operates at a higher frequency to refine local action chunks using the latest observations. This design amortizes expensive high-level VLA computation while preserving frequent closed-loop correction. On LIBERO, our GR00T-style instantiation improves average success from 96.5% to 97.8% while reducing amortized inference latency from 115.0 ms to 44.2 ms per action chunk. More broadly, across two VLA backbones, simulation benchmarks, and real-robot tasks, StairVLA consistently reduces inference cost while maintaining strong task performance.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07756
PDF
-
RefRoute: Decoupling Conditioning Cost from References via Compact Residual Conditioning and Spatial Routing
2026-10-06 04:16:27Wanning He, Yuyao Zhang, Yu-Wing TaiAbstract
Multi-reference image generation requires preserving the appearance of multiple subjects while composing them into a coherent scene. However, existing diffusion transformers commonly encode references as dense visual token grids and jointly process them with global attention, making conditioning increasingly expensive as the number and resolution of references grow. We present RefRoute, a framework that addresses both reference representation cost and attention overhead through two complementary mechanisms. Compact residual conditioning combines low-resolution latent tokens with lightweight residual features extracted from full-resolution pixels, reducing reference token counts while retaining fine-grained appearance cues. Condition routing and attention routing align reference tokens with their assigned target regions and restrict cross-reference interactions, while allowing selective reference access beyond region boundaries for scene integration. We further introduce RefRoute-Data for training many-reference generation models and ManyRef100, a benchmark spanning human, object, and mixed compositions with 10-17 references. After many-reference fine-tuning, RefRoute achieves an overall Weighted-Ref-VIEScore of 36.06 on ManyRef100, compared with 8.88 for FLUX.2-Klein-9B. Separate inference-cost evaluations show substantially slower latency growth as the reference count increases: at 16 references, our 50-step and 4-step configurations achieve $18.3\times$ and $14.2\times$ speedups over their corresponding FLUX baselines, respectively. These results establish compact reference representations and spatially routed attention as an effective approach to scalable many-reference image generation.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07720
PDF
-
SpecFold: Folding Multi-Branch Redundancy for Faster Speculative Decoding in Diffusion Language Models
2026-10-06 03:42:24Chung-En Ho, Weiyu Sun, Cheng-Jhih Shih, He Li, Yong Liu, Yingyan Celine LinAbstract
Diffusion large language models (DLLMs) generate text through iterative block denoising, and multi-branch speculative decoding accelerates this process by verifying a main branch together with multiple draft branches in a single forward pass. While prior DLLM acceleration methods primarily exploit temporal redundancy across denoising steps, we identify a complementary redundancy axis within each speculative verification step: multi-branch computational redundancy. During speculative verification, draft branches inherit most tokens from their parents while unmasking a small set of additional positions, causing large portions of hidden states to remain highly similar across branches. We propose SpecFold, an algorithm-system co-design that exploits this multi-branch redundancy to reduce the cost of multi-branch speculative verification. Algorithmically, SpecFold performs token-level residual gating and selectively reuses parent computation through folded attention and FFN while preserving residual hidden states. Systemically, a Triton kernel implementation translates this fine-grained reuse into end-to-end throughput gains through efficient sparse multi-branch execution. SpecFold is orthogonal to temporal caching and compatible with existing DLLM speculation strategies. Across two DLLM families, five models, and five standard benchmarks, SpecFold achieves up to 1.64x throughput over Spiffy and up to 1.99x over vanilla decoding, while maintaining comparable task performance.
Abstract (translated)
URL
https://arxiv.org/abs/2610.04875
PDF
-
ESP: Energy-Score Policy for One-Step Multimodal Action Generation
2026-10-06 03:34:46Lilika Makabe, Heecheol Kim, Yasuyuki MatsushitaAbstract
Generative action models based on diffusion and flow matching have been increasingly adopted in vision-language-action (VLA) policies for their ability to capture diverse behaviors, including multiple valid action sequences under the same observation and instruction. Their iterative sampling procedures, however, require repeated network evaluations to generate each action chunk, increasing inference latency in closed-loop control. We propose ESP (Energy-Score Policy), a teacher-free approach that maps policy context and noise directly to an action chunk in a single network evaluation. ESP trains the action head with the energy score rather than mean squared error. Whereas squared-error regression targets the conditional mean, the energy score is strictly proper: its expected value is uniquely minimized by the target distribution. This provides a principled objective for learning multimodal action distributions without iterative sampling, with exact recovery at the population optimum when the model can represent the target distribution. Experiments on both simulation and real-world manipulation tasks demonstrate competitive task success with substantially lower action-generation latency than the flow matching baseline. These results support direct distributional learning as an efficient alternative to iterative generative robot policies.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07696
PDF
-
Disentangling Dual Image References in Frequency Aware Diffusion Models for Personalized Generation
2026-10-06 03:18:07Haipeng Liu, Yang Wang, Meng WangAbstract
Personalized image generation aims to synthesize text-driven images conditioned on reference images, while mainly casting the generation as image customization for foreground and style transfer for background. Previous arts of diffusion models suffers from the text misalignment with background for image customization and foreground for style transfer during the denoising process. Such facts, as we observed, rooted from the entanglement among hybrid frequency bands during the denoising process. To address such salient limitation, in this paper, we study personalized generation based on dual references - customization and color and style reference - and propose a paradigm to disentangle these Dual image references within Frequency-aware Diffusion Models, dubbed Dual-FDM, to simultaneously tackle two crucial personalized image generation tasks: customization style transfer and color style transfer, by disentangling different frequency bands via mask strategy within frequency domain. For customization style transfer, we replace the mid-frequency band of the background in the style reference with that from the foreground of the customized reference. For color style transfer, we substitute the low-frequency band of the background in the style reference with that from both the foreground and background of the color reference. Both the substituted frequency bands are used as the key and value to reconstruct the query foreground and background of the denoised personalized this http URL experiments validate the superiority of Dual-FDM over the state-of-the-art diffusion models for personalized image generation. Our code can be accessed from this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07684
PDF
-
Enhanced Video Text Editing with Trajectory-Aligned Glyph Rendering
2026-10-06 03:00:00Shulian Zhang, Xiangyu Shu, Wenbo Li, Jian Chen, Yong GuoAbstract
Video text editing aims to replace or add text in a video while keeping the rest of the video unchanged, which requires the edited text to be correct in every frame and to move coherently with the scene. Despite the remarkable progress of video diffusion models, they struggle to reproduce exact stroke structures and often produce garbled or wrong characters, especially for characters with complex strokes. To address this, we propose a trajectory-aligned glyph rendering reference that provides explicit per-frame glyph guidance following the position and perspective of the text, and a depth-normalized recognizer feature supervision that supervises the generated text on multi-depth features of a frozen text recognizer with per-depth normalized errors, targeting stroke errors overlooked by the diffusion loss. We further build VTEdit, a benchmark of 288 real-scene clips with 440 annotated text trajectories covering text replacement and text addition, which will be publicly released to facilitate future research. Experiments on VTEdit show that our method outperforms image text editing methods, video editing methods, and commercial models in text accuracy and background preservation, achieving a sentence accuracy of 0.9408, and receives the highest preference in a user study.
Abstract (translated)
URL
https://arxiv.org/abs/2609.34178
PDF
