Denoising
-
EmoWorld: A Decoupled Affective Field for Controllable Emotional Video Generation
2026-08-06 16:20:23Bingyuan Wang, Baistan Zhyldyzbekov, Kunyu Feng, Zeyu WangAbstract
Emotion shapes how viewers interpret a scene, yet existing video generators entangle global atmosphere, affect-bearing semantic cues, and temporal progression within a single text condition. We present EmoWorld, a framework that decouples these factors within a frozen flow-matching video diffusion transformer (Video DiT). A one-time preparation stage extracts layer-specific affect directions and a reusable cue library from geometry-preserving neutral and emotion-edited panoramas. At inference, Visual Atmosphere Steering (VAS) injects atmosphere directions into hidden states, Semantic Affective Steering (SAS) isolates a separately scalable prompt residual for semantic cues, and Temporal Affective Steering (TAS) interpolates endpoint residual fields across denoising and video time. On Wan2.2, VAS improves target-emotion alignment by 19% while reducing a temporal-fluctuation proxy by 48%; SAS improves target-emotion alignment by 37% and increases detected affect-bearing cues by 36%; and TAS improves transition monotonicity by 15% over the strongest baseline. EmoWorld is evaluated across 27 emotion categories in text-to-video and image-to-video settings, demonstrates portability across multiple Video-DiT backbones, and supports camera-conditioned composition without updating generator parameters.
Abstract (translated)
URL
https://arxiv.org/abs/2608.06231
PDF
-
Sample-Adaptive Latent Rewards for Uncertainty-Guided Diffusion Post-Training
2026-08-06 14:55:42Rui Li, Yuanzhi Liang, Ke Hao, Ziqiao Weng, Haibin Huang, Chi Zhang, XueLong LiAbstract
Latent reward models can supervise visual diffusion models without decoding intermediate states into pixel space. This makes alignment with human preferences more efficient. However, existing latent reward models output only scalar scores. They do not estimate the uncertainty of each prediction. The generator therefore cannot determine which feedback is reliable. This can drive optimization in the wrong direction and lead to reward hacking. We propose \textsc{SURE}, a unified latent-space framework for image and video diffusion models. It learns reward distributions and directly uses their reliability to guide dense post-training. First, we propose sample-adaptive latent reward model (\textsc{SURE-LRM}). It predicts a Gaussian utility for each noisy latent. Its mean predicts the reward score. Its variance reflect the uncertainty of prediction without human annotation. The learned distribution then guides post-training through uncertainty-guided reward feedback learning (\textsc{SURE-REFL}). This method provides uncertainty-guided dense feedback along the denoising trajectory. At selected transitions, \textsc{SURE-REFL} queries the frozen \textsc{SURE-LRM}. It converts detached variance into reliability weights for samples at the same transition. Each weighted reward is backpropagated only through its local transition. The entire process remains in latent space and requires neither pixel-space decoding nor the full denoising graph. Experiments show that \textsc{SURE-LRM} improves preference prediction over strong baselines. \textsc{SURE-REFL} achieves the sota performance among various metrics and further improves optimization stability. It also achieves the highest VBench quality, semantic, and total scores among the evaluated methods.
Abstract (translated)
URL
https://arxiv.org/abs/2608.06125
PDF
-
Iterate or Widen? When Test-Time Refinement Helps LiDAR Scene Completion: A Controlled Study of Evidence Geometry, Training Coverage, and Compute
Abstract
Should a completion model spend extra test-time compute by iterating, or spend a similar parameter budget on a wider one-shot predictor? The answer is easily confounded by denoising curricula, corruption augmentation, capacity, and unpaired evaluation. We study this question in LiDAR semantic scene completion by comparing a one-shot predictor, a parameter-matched wider predictor, and a weight-tied multigrid refiner initialized from the same frozen predictor. The protocol separates coherent region removal, independent thinning, range-dependent attenuation, and additive clutter while preserving exact scene-condition pairing. Across five training seeds and 815 SemanticKITTI sequence-08 frames, the full iterative system improves mIoU over the wide control by 0.911 points under contiguous angular removal, with a 95% moving-block bootstrap interval of [0.804, 1.040] that clears a predeclared 0.5-point practical margin. Under independent 75% thinning, iteration adds only 0.300 points [0.166, 0.436], whereas observation-family augmentation adds 5.975 points [5.662, 6.140]. Neither intervention repairs additive clutter. The iterative system also costs 10.74 ms and 0.75 GiB per frame, versus 6.25 ms and 0.23 GiB for the wide control. These results establish a geometry-conditioned empirical boundary rather than a universal advantage: coherent gaps can justify fixed-depth refinement, broadly thinned evidence is addressed more effectively by training coverage, and spurious evidence requires a different robustness mechanism.
Abstract (translated)
URL
https://arxiv.org/abs/2608.06014
PDF
-
Adaptive-WAM: Quality-Guided Early-Exit Planning from Intermediate Video-Diffusion Features
2026-08-06 13:13:07Sining Ang, Yuguang Yang, Yan WangAbstract
Large video diffusion models provide rich spatiotemporal priors for autonomous driving, but existing world-action models often inherit the cost of iterative future-video generation even though deployment only requires an ego trajectory. We ask a more basic question: how much of a video diffusion model must be executed to make a reliable driving decision? Through a controlled study of video denoising timesteps and Diffusion Transformer (DiT) depth, we find that planning performance is largely insensitive to the tested video-noise levels, whereas strong trajectories can already be decoded from intermediate layers. Based on this observation, we introduce Adaptive-WAM, a quality-aware multi-exit planner built on a Wan2.2-5B backbone. Trajectory diffusion heads are attached to selected DiT blocks, and a lightweight trajectory-quality scorer terminates inference once the best trajectory decoded so far satisfies a quality threshold; otherwise, computation continues from the cached hidden state to a deeper exit. The deployed planner therefore avoids the iterative classifier-free denoising loop and VAE decoding required for future-video synthesis, while dynamically allocating backbone depth according to trajectory quality. On NAVSIM, the adaptive single-trajectory planner achieves 90.8 PDMS; a separate fixed-exit variant reaches 92.6 PDMS with 64 proposals. It further obtains 89.9 EPDMS on NAVSIM v2, yielding the best reported results among the compared front-view video world-model planners. Without target-domain fine-tuning, Adaptive-WAM transfers to nuScenes with 0.88 m average L2 error and a 0.08\% collision rate. On an A100, adaptive routing improves PDMS from 90.62 to 90.79 while averaging 170 ms end-to-end planning latency, approximately 10\% below the 190 ms fixed block-15 planner and 47\% below the 320 ms fixed full-depth planner. Code will be released.
Abstract (translated)
URL
https://arxiv.org/abs/2608.06008
PDF
-
Vorch-Director: Interactive World Story Model via Noise-Aware Error Rectification
2026-08-06 09:09:49Lisai Zhang, Yidi Wu, Qi Liu, Xin Ma, Yang Ding, Gang Yue, Siqian Yang, Jingyuan Chen, Lin Ma, Yaohui WangAbstract
Autoregressive continuation provides a natural path toward minute-scale audio-visual generation by repeatedly extending a short-window generator conditioned on previously generated video and audio. However, models are trained on clean ground-truth histories, while inference relies on their own generated histories, where accumulated errors cause identity drift, over-smoothing, and audio-visual desynchronization. Recent methods reduce this mismatch by reusing prediction residuals as synthetic corruption, but we observe that the effectiveness of residual correction critically depends on the flow-matching noise level at which residuals are produced. We propose Vorch-Director, a noise-level-aware residual correction strategy that associates each residual with its originating noise level and injects residuals from matched noise regimes during training. By aligning injected errors with the denoising process, Vorch-Director produces more realistic autoregressive histories while retaining efficient teacher-forcing training. Built on the audio-visual LTX-2 diffusion transformer, Vorch-Director further introduces task embeddings to distinguish historical video, reference images, and target video, enabling unified conditioning for long-horizon generation. Together with a clean conditioning sink and mixed-task training, Vorch-Director supports multi-shot, multi-subject, reference-guided audio-visual long-video generation. We evaluate Vorch-Director on ST-Bench and introduce a new long-horizon audio-visual benchmark with metrics for quality drift and long-range consistency. Extensive experiments demonstrate improved stability and audio-visual fidelity over strong baselines.
Abstract (translated)
URL
https://arxiv.org/abs/2608.05776
PDF
-
Flow-Map Distillation on Relation Manifolds for Image Restoration
2026-08-06 08:59:28Zihao He, Songhua LiuAbstract
Knowledge distillation for image restoration typically aligns intermediate features or relation matrices between teacher and student networks as static targets, ignoring the dynamic structure of the knowledge transfer process. In this paper, we propose Flow-Map Distillation on Relation Manifolds (FoRM), which reformulates relation-based knowledge transfer as a continuous flow mapping problem on the relation manifold. Rather than regressing a constant velocity field between student and teacher relation states, FoRM learns a flow map operator $\mathcal{F}_\theta(\mathbf{z}, t, s)$ that directly predicts the relation state at any target time $s$ given the current state at time $t$, enabling richer trajectory-level supervision. To ensure global self-consistency of the learned flow map, we introduce a safe semigroup consistency constraint that enforces compositional agreement using ground-truth bridge states, eliminating phantom-state error accumulation. An endpoint anchoring loss further prevents the operator from drifting away from the teacher target. Extensive experiments on five image restoration tasks, including super-resolution, deraining, denoising, deblurring, and low-light enhancement, demonstrate consistent gains over state-of-the-art distillation baselines across multiple backbone architectures, reducing training variance by approximately 50\% compared to naive flow matching distillation while achieving superior restoration quality.
Abstract (translated)
URL
https://arxiv.org/abs/2608.05769
PDF
-
LiteKD-Net: Lightweight Knowledge-Distilled Network for Mobile Image Denoising
Abstract
Mobile image denoising requires both good restoration quality and low computational cost. In addition, it's annoying to collect large-scale LQ-GT clean pairs. As a result, we propose LiteKD-Net, a lightweight knowledge-distilled network for mobile image denoising. First, a physics-guided noise simulation pipeline generates paired training data by adding pixel crosstalk compared with pipelines applied to cameras. Next, we adapt the Real-ESRGAN to identity-resolution denoising and construct a lightweight Student using Lite-RRDB blocks based on depthwise separable convolutions. Third, feature-level knowledge distillation is applied to transfer the Teacher's restoration capability to the Student without introducing additional inference cost. Experiments on real-world datasets show that our model reaches great reduction in runtime and increase in the inference rate with good restoration quality. Our model also reaches the best in all metrics compared with SwinIR. These results indicate that LiteKD-Net provides a great trade-off between restoration quality and computational efficiency.
Abstract (translated)
URL
https://arxiv.org/abs/2608.05739
PDF
-
PhyLatent: Learning Dynamics-Relevant Representations for JEPA World Models
2026-08-06 08:02:15Xi Zeng, Haojie Ren, Ziying SongAbstract
We propose PhyLatent, a dynamics-relevant training objective for JointEmbedding Predictive Architecture (JEPA) world models. Our key observation is that preventing global latent collapse does not ensure that a representation preserves physical states and action consequences. We identify three failure modes in JEPA world models: physical invariance collapse, physical identifiability collapse, and counterfactual dynamics collapse. PhyLatent addresses them through three training pathways: physical invariance, physical identifiability, and counterfactual dynamics, implemented with physical state grounding, future representation alignment, static visual invariance, counterfactual branch separation, and latent denoising. On OGBench-Cube, PhyLatent reduces the three failure rates from 15.60%, 6.71%, and 8.41% to 7.53%, 0.95%, and 4.62%, respectively, and improves model predictive control (MPC) success from 70.0% to 78.1%. With the same architecture and planner, it further improves success from 81.0% to 98.0% on TwoRooms and remains competitive on Reacher and PushT. These results show that global non-collapse alone is insufficient for learning a reliable JEPA worldmodel state space.
Abstract (translated)
URL
https://arxiv.org/abs/2608.05720
PDF
-
Vorch-Streamer: Extending Human Audio-Visual Generation to Real-Time Long-Form Streaming
2026-08-06 07:00:37Menglin Han, Yang Ding, Yulei Lu, Haoran Yu, Xin Ma, Junyi Chen, Zhangkai Ni, Lin Ma, Yaohui WangAbstract
Real-time long-form avatar audio--video generation requires causal, continuous synthesis while maintaining audiovisual synchronization and visual consistency. Adapting a pretrained bidirectional model to this setting presents two key dilemmas. First, autoregressively reusing generated blocks as context creates exposure bias, causing errors and visual drift to accumulate over long rollouts. Second, a global speech utterance does not indicates a causal generator which portion should be spoken next when only limited local audio--video context is available. We present \textbf{Vorch-Streamer}, a post-training framework that addresses these challenges and enables real-time long-form Text-to-Audio-Video (T2AV) streaming. We construct a synthetic corpus of 80K avatar clips spanning 12--21 seconds and first train a causal generator with mixed Teacher Forcing and Diffusion Forcing. We then apply long-horizon Self Forcing with DMD distillation, exposing the model to its own rollout distribution while preserving the quality of the pretrained bidirectional teacher. To explicitly control speech progression, an external language model predicts discrete 25-Hz speech-planning tokens, whose continuous features condition the audio diffusion branch and align each causal block with the content it should speak. With bounded causal context and four-step denoising, Vorch-Streamer jointly generates audio and video from text at 27.12 FPS, exceeding the 24-FPS real-time playback rate while maintaining competitive audio--lip synchronization and strong identity preservation over long-form generation.
Abstract (translated)
URL
https://arxiv.org/abs/2608.05663
PDF
-
Hierarchical Flow Matching for 3D Point Cloud Generation
2026-08-06 03:23:49Linhao Wang, Qichang Zhang, Ye Su, Hao WangAbstract
Generating high-quality 3D point clouds requires capturing both global shape topology and local geometric details. Existing flow-based methods rely on continuous normalizing flows (CNFs) that demand expensive ODE solving and trace estimation during training, while diffusion models require hundreds of iterative denoising steps. Moreover, most approaches adopt single-level generation directly in point space, disregarding the hierarchical structure natural to 3D shapes. We propose Hierarchical Flow Matching (HFM) that extends flow matching to bilevel structure for unconditional 3D point cloud generation. HFM decomposes the task into two levels via optimal-transport flow matching: a \textit{Latent Flow Matching} models the global shape manifold in a compact latent space, and a \textit{Conditional Point Flow Matching} reconstructs detailed point clouds conditioned on the latent code. Both flows are trained with simple MSE regression losses. The resulting straight OT paths enable efficient sampling with as few as 15 Euler steps per flow, while the structured latent space supports downstream tasks including classification. Extensive experiments on ShapeNet and ModelNet benchmarks demonstrate that HFM achieves competitive or even best performance compared with prior state-of-the-art methods.
Abstract (translated)
URL
https://arxiv.org/abs/2608.05557
PDF
-
MOSAIK: Multi-Patch Content-Aware Spatial Allocation of Image Tokens for Efficient Generation
2026-08-05 22:52:41Mohammadreza Hami, Mohammadreza Samadi, Chao Gao, Negar HassanpourAbstract
Pixel-space diffusion models avoid the reconstruction ceiling of latent diffusion models by generating directly in image space. However, their substantially higher token count makes generation expensive due to the quadratic complexity of self-attention. Several existing efficiency methods reduce this cost by using larger patches at selected denoising steps, thereby representing the image with fewer tokens. Yet, each step still uses a single patch size uniformly across the entire image, overlooking that different regions suffer different fidelity losses when coarsened. We introduce MOSAIK, a damage-guided framework that varies patch size across regions and denoising steps. MOSAIK adapts the PixelDiT backbone to generate arbitrary heterogeneous patch layouts, and a lightweight predictor uses intermediate denoising features to estimate the fidelity loss caused by coarsening each region. Given a token budget, our damage-guided layout predictor assigns fine patches to sensitive regions and coarse patches elsewhere. Remarkably, while reducing FLOPs by 70% and token count by 83%, MOSAIK matches the full-compute PixelDiT on GenEval and its DPG-Bench score drops by only 1.0 point. Compared to diverse efficiency paradigms, including temporal patch scheduling and feature caching, our approach delivers highly competitive performance at moderate budgets and consistently outperforms these baselines in highly constrained compute regimes.
Abstract (translated)
URL
https://arxiv.org/abs/2608.05450
PDF
-
Learning When to Stop: Prefix-Optimal Dynamic Diffusion Policies for Continuous Control
2026-08-05 17:24:55Rohit Kumar Salla, Manoj Saravanan, Simon StepputtisAbstract
Diffusion policies are a powerful policy class for continuous control, but their iterative denoising process creates a substantial computational bottleneck. Reducing this cost requires adapting the number of denoising steps to the difficulty of each action while preserving task performance. We introduce Prefix-Optimal Generative Policies (POGP), a framework that learns a prefix value function at every intermediate denoising step through a Bellman-style recursion over the denoising chain. The prefix value function serves two purposes: it provides an auxiliary training objective that encourages intermediate outputs to become high-quality actions, and it enables a test-time stopping rule that terminates denoising when additional steps are unlikely to produce meaningful improvement. Across four MuJoCo environments and comparisons with 12 baselines, POGP reduces the required number of denoising iterations by approximately 2.7-fold while retaining near-full task performance. Compared with state-of-the-art dynamic diffusion baselines, prefix training also improves final task performance by approximately 3.5%. These results indicate that supervising intermediate denoising steps is useful not only for adaptive early stopping, but also as an auxiliary objective that improves the learned policy.
Abstract (translated)
URL
https://arxiv.org/abs/2608.05084
PDF
-
DreamWAM: Beyond RGB Future Prediction for World Action Models
2026-08-05 16:04:23Shanglin Yuan, Weiheng Zhao, Xin Shi, Haoyi Jiang, Xianda Guo, Liu Liu, Wenyu Liu, Wei Sui, Xinggang WangAbstract
World Action Models (WAMs) learn action-relevant representations by predicting how the observed world will evolve. Most existing WAMs define this future in RGB space, where task-relevant state transitions are entangled with nuisance variations in texture, illumination, background, and viewpoint. We argue that WAMs should explicitly predict action-relevant future state rather than relying on RGB prediction alone. We introduce DreamWAM, which reformulates future prediction as structured world modeling beyond RGB, representing future states through complementary views of appearance, motion, geometry, and semantics. During training, DreamWAM combines joint latent denoising of RGB and motion with lightweight gated residual branches for geometry and semantics. Shared attention between VideoDiT and ActionDiT allows the action branch to learn from these future-state predictions, while all beyond-RGB supervision branches are disabled at inference and deployment remains RGB-only. Across both no-rollout and joint video-action inference, DreamWAM consistently improves the matched RGB-only baselines on LIBERO, from 97.30\% to 98.40\% and from 98.00\% to 98.90\%, respectively. The gains become larger under unseen LIBERO-Plus perturbations, from 51.36\% to 63.44\% and from 69.16\% to 75.47\%. The same robustness extends to real-world manipulation, where DreamWAM attains an average success rate of 74.4\% across unseen changes in lighting, background, and object layout, compared with 55.6\% for Fast-WAM-Joint. These results show that robust world-action learning depends not only on predicting the future, but on representing it in a form that matters for action. The code and models are publicly released at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.04996
PDF
-
ContextMaster: Interactive Multi-Shot Video Creation via Fixed-Budget Sparse Context Routing
2026-08-05 15:27:26Xu Guo, Zhengxuan Wei, Xinghui Li, Hanzhuo Huang, Xinyu Liu, Xiangyang Luo, Min Wei, Yiran Zhu, Qiulin Wang, Yulong Xu, Xintao Wang, Pengfei Wan, Qi Fan, Xiangwang HouAbstract
Recent video models increasingly support generation, reference conditioning, and editing within a single model, yet typically expose them as separate operations over fixed inputs. Practical creation unfolds across multiple shots, requiring one model to generate from text, follow a reference, or edit source footage while maintaining shared history. We formalize this setting as interactive multi-shot video creation (IMVC) and introduce ContextMaster, a unified model with a role-aware context representation for these operations. An interactive model must retain access to an expanding history without allowing the context read cost at each denoising step to grow. ContextMaster combines reusable clean context states with fixed budget sparse context routing and uses ConstraintSink to keep task constraints visible. To address the dual challenges of sparse context access and inference with few denoising steps, we propose a two-stage privileged context distillation framework, which transfers full context behavior from a dense teacher through consistency distillation and then refines deployment rollouts with distribution matching. Experiments on the three primitive tasks demonstrate improved task fulfillment and consistency across shots over specialized baselines. User studies further validate flexibly composed workflows, while the model reaches 16 FPS on a single GPU.
Abstract (translated)
URL
https://arxiv.org/abs/2608.04956
PDF
-
In-Context Forcing: Uncovering Context Effects in Autoregressive Video Diffusion
2026-08-05 13:54:31Lingxiao Yang, Liu Liu, Moran Li, Han Feng, Wenjian Cao, Jiangning Zhang, Ye ShiAbstract
Current few-step autoregressive video diffusion models depend on previous fully denoised clean frames as context for all denoising steps of the current frame. However, these clean frames leak excessive local details, which causes the model to take shortcuts, resulting in compromised temporal semantics and dynamics. Inspired by the perspective of diffusion as masking, we explore the impact of noisy contexts on few-step autoregressive generation. Yet, simply applying contexts with the same noise levels provides insufficient guidance, leading to poor temporal consistency. To resolve this dilemma, we introduce In-Context Forcing, a progressive autoregressive paradigm that utilizes contexts with decreasing noise levels. By applying less masking to distant frames and more masking to adjacent ones, this approach provides adaptive guidance, effectively ensuring both robust temporal consistency and high inter-frame dynamics. Furthermore, by decoupling the strict dependence on previous clean frames, our paradigm enables cross-frame parallel denoising, achieving substantial inference acceleration without sacrificing performance. Extensive experiments on VBench demonstrate that our method significantly outperforms state-of-the-art approaches in both visual fidelity and inference speed.
Abstract (translated)
URL
https://arxiv.org/abs/2608.05237
PDF
-
MobileWAM: Bridging World Action Models to Mobile Manipulation with Chain-of-Foresight
2026-08-05 10:12:37Zehua Fan, Junjie He, Wenxuan Song, Xi Wang, Wenqi Lyu, Linge Zhao, Fuhao Li, Zihan You, Yifei Yang, Kaiming Xu, Qi Jiang, Yue Jiang, Haoang Li, Cheng Chi, Bailin Li, Yan WangAbstract
World action models (WAMs) built on video generation backbones are a rising recipe for robot learning, yet remain confined to tabletop manipulation. Mobile manipulation demands simultaneous locomotion and whole-body manipulation amid scene-scale dynamics, yet is still dominated by dynamics-blind visual encoders with hand-crafted coordination. We bridge this gap with MobileWAM, a mixture-of-transformers architecture that fuses a pretrained video diffusion transformer with a lightweight action expert through layerwise joint attention, translating internet-scale motion priors into whole-body control. To reconcile the heterogeneous dynamics of moving and manipulating, each feed-forward layer of the action expert becomes a three-expert mixture of shared, locomotion, and manipulation experts, softly routed by the motion intent in the action tokens. To densify supervision, we further propose Chain-of-Foresight (CoF): intermediate representations sequentially predict a chain of future latent chunks, each step conditioned on its predecessor. CoF pairs naturally with our decoupled video--action denoising scheme. At deployment, the WAM serves as a pure current-frame encoder; foresight acts only through gradients, so at inference the foresight chain and video generation are discarded, leaving only policy-level cost. MobileWAM surpasses state-of-the-art mobile manipulation policies on ManiSkill-HAB and fine-tunes to a real ARX Lift2 mobile manipulator across diverse tasks with strong generalization. Code will be released soon.
Abstract (translated)
URL
https://arxiv.org/abs/2608.04657
PDF
-
Visual Anchoring in Diffusion: Multimodal Zero-Shot Skeleton Action Recognition
2026-08-05 09:28:00Zehao Bao, Shujun Guo, Bruce X. B. YuAbstract
Zero-shot Skeleton Action Recognition (ZSAR) remains ambiguous when unseen actions share similar skeleton joint dynamics but differ in objects or scene context. RGB provides these missing cues, yet existing multimodal methods typically maintain independent skeleton and RGB scoring branches and fuse their outputs. Without using unlabeled test data for adaptation or fusion calibration, a fixed fusion weight cannot capture class-pair-dependent modality reliability, while an adaptive rule lacks target-side feedback for deciding which branch should dominate. We bypass this weight-selection problem via the classify-by-generation paradigm, where each class is scored by how accurately a text-conditioned denoiser predicts the noise added to the skeleton feature. This formulation separates the progressively corrupted skeleton from fixed conditioning, allowing RGB and text to jointly condition a single class-scoring function rather than produce independent scores. We instantiate this idea as Multimodal Triplet Diffusion for Skeleton-Text Matching (TDSM-MM), augmenting a text-conditioned denoising Transformer with a non-diffused RGB condition token that serves as a stable visual anchor during skeleton data reconstruction. Our proposed TDSM-MM has been ablated via extensive experiments and achieved the best inductive accuracy on three of four NTU-60/120 splits and surpasses the transductive state-of-the-art on NTU-120 96/24 (i.e., 71.3% vs. 69.1%), without test-time adaptation, suggesting that diffusion-based methods can be a promising direction for zero-shot learning.
Abstract (translated)
URL
https://arxiv.org/abs/2608.04623
PDF
-
StyleComposer: Training-Free Multi-Reference Style Composition
2026-08-05 09:17:50Sanghyeok Lee, Jihye Kang, Namhyuk AhnAbstract
The style of a painting is not monolithic: color, texture, and structure may come from different sources. Existing reference-guided methods transfer them as one style signal, leaving each attribute's source and strength outside the user's control. We ask where in a diffusion model one attribute can change while the others hold, and find that no single representation isolates all three. The proposed StyleComposer therefore routes each style attribute through the representation where it separates best and coordinates the routes over denoising time. Without training or inversion, it satisfies three references and the prompt jointly more closely than prior methods, and exposes one strength slider per attribute. Project page: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2608.05213
PDF
-
Just Repair: A Minimal Denoising Network for Time Series Anomaly Detection
2026-08-05 08:11:07Kadir-Kaan \"Ozer, Ren\'e Ebeling, Markus EnzweilerAbstract
Time series anomaly detectors have grown steadily more complex, incorporating attention mechanisms, adversarial training, and stochastic latent variables. Yet, it is unclear how much of this machinery detection actually requires. We test this question with JuRe (Just Repair), a deliberately minimal detector: a single depthwise-separable convolutional residual block trained to repair Gaussian-corrupted, channel-masked windows, scored at inference by a fixed structural discrepancy function with no learned parameters. JuRe ranks second on the TSB-AD multivariate benchmark (AUC-PR 0.404 over 180 series) and second on the UCR univariate archive (AUC-PR 0.201 over 250 series), where it leads all neural baselines. On TSB-AD, JuRe runs roughly $20\times$ faster than AxonAD, one of the top-ranked methods on that benchmark. Full-benchmark ablations show that removing Gaussian corruption reduces AUC-PR by 0.046, whereas AUC-PR across the evaluated architecture variants spans at most 0.017. A synthetic linear-manifold experiment provides partial evidence for this geometric interpretation: anomaly scores correlate with true off-manifold distance (Pearson $r=0.725$), and repair directions align increasingly with the true projection as anomaly magnitude grows. Wilcoxon signed-rank tests with Holm correction find significant differences against 20 of 25 baselines, although dependence among series limits dataset-level interpretation. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2604.17388
PDF
-
GUARD: Grounding Uncertainty and Ablation-Based Risk Detection for Diffusion-Based VLAs
2026-08-05 06:48:15Suhas Hegde, Jitendra Yasaswi Bharadwaj KattaAbstract
Diffusion-based vision-language-action (VLA) policies can generate plausible actions even when their predictions are weakly grounded in the visual and language evidence defining the task. We introduce GUARD, a test-time failure detection method that measures this grounding without modifying the pretrained policy. GUARD estimates the influence of token-indexed entries in the final vision-language model key-value (KV) cache, constructs counterfactual caches by ablating salient KV entries, and compares their denoising responses with the original conditioning. Based on the comparison, we derive GUARD diagnostic stream including sensitivity, attention entropy, modality bias, and grounding efficiency, which are calibrated online and processed by a lightweight temporal classifier. We evaluate GUARD under task-held-out splits across five policy-benchmark settings, using Pi0, SmolVLA, and Alpamayo-1.5 on LIBERO, SimplerEnv, MetaWorld, and PhysicalAI-AV. GUARD achieves the best ROC-AUC on four of five unseen-task settings and ranks second on the remaining setting, improving the average unseen-task ROC-AUC by 5.73 percentage points over the strongest competing runtime monitor while remaining within 0.19 points of the best seen-task average. These results show that directly probing action-head dependence on multimodal evidence provides a transferable failure signal across policies, tasks, embodiments, and domains.
Abstract (translated)
URL
https://arxiv.org/abs/2608.04510
PDF
