Regularization
-
Perceptually Regularized Diffusion Model for Image Super-Resolution
2026-09-02 02:43:12Chuxiangbo Wang, Pavithra Venkatachalapathy, Ying Liang, Min Wang, Jing Qin, Yifei Lou, Weihong GuoAbstract
Image super-resolution, which aims to reconstruct high-resolution images from their low-resolution observations, is fundamental to medical imaging, remote sensing, surveillance, microscopy, and scientific visualization. Traditional model-based methods formulate super-resolution as an inverse problem with hand-crafted regularization priors. While interpretable and theoretically grounded, they rely on fixed assumptions and require computationally intensive iterative solvers. Deep learning methods offer data-driven flexibility by learning nonlinear mappings from low- to high-resolution images, among which diffusion models have achieved particularly impressive perceptual quality. However, the standard diffusion training objective is a pixel-domain noise-prediction loss that does not explicitly enforce perceptual fidelity, which can lead to oversmoothing and loss of fine image structure. To address these limitations, we propose a perceptually regularized diffusion framework that incorporates prior knowledge through perceptual-loss-based regularization, improving training convergence and encouraging the recovery of meaningful image features. Experiments on benchmark datasets demonstrate improved perceptual quality and competitive distortion metrics, highlighting the effectiveness of regularization for diffusion-based super resolution.
Abstract (translated)
URL
https://arxiv.org/abs/2609.02016
PDF
-
Consistency as Regularization for Unsupervised Shadow Removal
2026-09-01 19:26:25Anh-Kiet Duong, Petra Gomez-Kr\"amer, Jean-Michel CarozzaAbstract
Shadow removal is an important preprocessing step for many vision tasks, yet existing supervised methods require paired shadow and shadow-free images, while unsupervised approaches often still rely on shadow masks or shadow-free references. We propose ShadowCLR, an unsupervised framework that learns shadow removal directly from shadow images. Our key observation is that shadows vary across observations while the underlying scene content remains largely consistent. We therefore use consistency across shadow observations as regularization, encouraging the model to recover scene-consistent appearance while suppressing shadow-specific variations. Global and local consistency further enable us to explore visually related images, learn from imperfectly aligned observations, and focus the representation on shared scene information. Experiments on multiple benchmarks show that ShadowCLR achieves competitive and often superior performance over state-of-the-art unsupervised methods, demonstrating that consistency can provide regularization for shadow removal without shadow masks or shadow-free images.
Abstract (translated)
URL
https://arxiv.org/abs/2609.01806
PDF
-
Improved Automatic Target Recognition in Synthetic Aperture Sonar Imagery Using Large Deep Neural Networks
2026-09-01 19:09:21C. J. Moore, Alex Hurt, Jordan MalofAbstract
Automatic Target Recognition (ATR) in Synthetic Aperture Sonar (SAS) is a task largely dominated by deep neural networks (DNNs). Most SAS-ATR models use convolutional neural network (CNN) architectures whereas transformer-based architectures have had much less representation in the literature despite being state of the art in general computer vision (CV) research. Additionally, researchers have had mixed results in attempting to overcome challenges presented by a scarcity of labeled training data by using methods such as data augmentation and the use of pretrained weights from a variety of imaging modalities. In this work, we compare the performance of modern CNN and transformer-based DNNs to determine which architecture and training configurations elicit the highest performance in SAS-ATR. We investigate how network size, architecture, pretraining method, data augmentation and other forms of regularization affect SAS-ATR performance with a focus on producing the highest-performing model and providing a roadmap for training state-of-the-art SAS-ATR models.
Abstract (translated)
URL
https://arxiv.org/abs/2609.01800
PDF
-
From Rollouts to Recipes: Self-Contained Post-Training for LLMs
2026-09-01 15:36:26Yifei Li, Lingling Zhang, Muye Huang, Zihan Ma, Jiashuai Liu, Jun LiuAbstract
Post-training large language models usually applies a single training recipe to all samples, even though the model's own rollouts reveal different sample-level learning states. We propose Self-Routing, a behavior-conditioned post-training framework that uses rollout correctness and confidence to decide how each sample should be optimized. Depending on its behavior state, a sample is routed to GRPO, on-policy self-distillation, regularization, or skipping, allowing training to adapt without external teachers, extra annotations, or additional sampling. Experiments on mathematical reasoning across Qwen3 and Qwen3.5 backbones show that Self-Routing consistently improves over uniform GRPO, uniform OPSD, fixed mixtures, and simpler routing baselines. Further analyses show that the routing distribution changes over training and reduces unnecessary updates on low-signal or already stable samples.
Abstract (translated)
URL
https://arxiv.org/abs/2609.01422
PDF
-
Prompt-Robust Language Models: Which Training Strategies Work?
2026-09-01 13:21:32Frederic Sadrieh, Michal \v{S}tef\'anikAbstract
Despite their strong performance, large language models remain highly sensitive to prompt formulation. Prior work addresses this through refined data construction or through dedicated robustness objectives. We reproduce and compare these strategies under controlled conditions, and measure how effective they are in addressing models' prompt sensitivity. We find the current robustness fine-tuning methods improve over standard fine-tuning and in-context learning, but the best-to-worst prompt gap remains as high as 40-57% of performance. Moreover, the recent robustness-enhancing methods we test - CoIN for contrastive alignment and PPCL for consistency regularization - often fail to outperform the simplest data construction strategy: training on one template per batch. Our diagnostics explain these results. The auxiliary objectives move the quantity they penalize, but do not generalize beyond it. Additionally, data construction strategies differ due to the conflicting signs of per-template gradients on 57-64% of parameters. Thus, batches that mix formulations force the optimizer to reconcile competing updates instead of finding a shared, prompt-agnostic one.
Abstract (translated)
URL
https://arxiv.org/abs/2609.01217
PDF
-
Behavior--Realization Separation for Constrained Physical Human--Robot Interaction
Abstract
Physical human--robot interaction software often couples desired-behavior specification with constrained realization; we treat these as separate layers. A \emph{behavior layer} supplies a desired contact-port acceleration $a_k^{\mathrm{id}}=f_\theta(e_k,\dot e_k,F_{h,k})$. A \emph{realization layer} converts it into constrained robot commands and reports total desired-versus-realized acceleration error instead of hiding it in saturation. A same-objective unconstrained counterfactual separates regularization from constraint intervention, while plant data expose model error. This paper implements a receding-horizon quadratic program realizing memoryless affine behaviors. Changing the behavior modifies objective coefficients through $(C_\theta,G_\theta)$ while the robot-command variable and feasible set remain unchanged. A planar study instantiates impedance and admittance; the same running layer accepts an impedance--admittance--impedance reassignment without reconstruction, under its existing rate limit. On a torque-controlled 7-DOF Franka FR3 in MuJoCo, the runtime freezes task-space dynamics per solve and enforces torque feasibility across its horizon. Under a sustained 20~N push, it holds a slack-relaxed workspace boundary to within approximately 0.1--0.2~mm, versus 4.4~cm (impedance) and 4.7~cm (admittance) overshoot from instantaneous clipping. A derated actuator budget then activates the torque constraint: horizon-wide enforcement keeps its frozen-model plan feasible to $2.1\times10^{-4}$~N$\cdot$m, whereas a first-step-only ablation plans up to 11.329~N$\cdot$m beyond budget; on the executed nonlinear plant, where both share the same local-model error, the gap is smaller but still favors horizon-wide enforcement (0.161 vs.\ 0.380~N$\cdot$m). These results are a focused proof of behavior--realization separation.
Abstract (translated)
URL
https://arxiv.org/abs/2609.00669
PDF
-
BLARM: Animating 3D Objects from Video via Blending Latent Rigid Motion Primitives
2026-08-31 17:21:54Pradyumn Goyal, Yizhak Ben-Shabat, Hsueh-Ti Derek Liu, Haomiao Jiang, Snehasish Mukherjee, Kyle Spence, Mark Stauber, Evangelos Kalogerakis, Yunze ZengAbstract
We introduce BLARM, a feed-forward method for video-driven 3D mesh animation. Given a monocular video and a static object mesh, BLARM predicts a temporally coherent animated mesh whose motion follows the video. Rather than relying on explicit rigs or directly regressing high-dimensional vertex motion, we represent animation using a compact set of learned, time-varying rigid motion components and time-invariant vertex-to-component skinning weights. This yields a low-dimensional deformation space without requiring skeletons, cages, skinning weights, or rig annotations. Our architecture conditions geometry-derived deformation latents on video features through factorized spatial-temporal attention, then decodes rigid transformations blended by predicted skinning weights. Trained with trajectory reconstruction, entropy regularization, and motion-aware contrastive learning, BLARM produces accurate and temporally stable animations while recovering compact, interpretable motion structure from monocular video.
Abstract (translated)
URL
https://arxiv.org/abs/2608.31113
PDF
-
SMG: Semantic Motion Graph for Monocular Dynamic Gaussian Splatting
2026-08-31 16:06:18Haozheng Yu, Xinyu Yang, Rundong Luo, Jennifer J. Sun, Bharath HariharanAbstract
We study dynamic Gaussian Splatting from monocular videos. While recent advancements in dynamic Gaussian splatting offer a promising foundation for modeling dynamic scenes, they often overfit to the training views and fail under occlusion or complex scene motion due to the lack of reliable regularization signals in under-constrained regions. We propose Semantic Motion Graph (SMG), a novel approach models the Gaussian motion as the low-rank semantic motion. Our key insight is that the real-world scene motion is often structured by semantic coherence: regions that are spatially close and semantically related tend to exhibit consistent dynamics. To leverage this prior, we construct SMG to model structured motion of the scene. The Gaussian motion is driven by the motion of SMG nodes. We further observe that the uncertainty of Gaussian motion arises from both unreliable off-the-shelf priors and weakly constrained regions during optimization. SMG addresses this by using reliable graph nodes to guide the motion of nearby unreliable nodes. To evaluate dynamic Gaussian splatting under challenging real-world scenarios, we introduce a new multiview dataset collected under an ego-exo setup. Extensive experiments demonstrate that SMG achieves state-of-the-art performance on monocular dynamic Gaussian splatting across challenging real-world benchmarks. Project page: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.31023
PDF
-
GarmentWeaver: Schema-Aware Structured Synthesis for Multimodal Sewing Patterns
2026-08-31 10:25:00Yinwen Lu, Weihao Luo, Yueqi ZhongAbstract
Multimodal Sewing pattern generation aims to infer executable sewing patterns from design cues such as sketches and textual descriptions. As an interpretable and simulation-compatible representation, sewing patterns are particularly valuable for digital garment creation. However, existing methods often model garment specifications as flat long sequences, which entangles garment structure with detailed parameters and leads to redundant components, inaccurate local details, and poor simulation compatibility. In this paper, we present GarmentWeaver, a schema-aware framework for multimodal Sewing pattern generation. GarmentWeaver constructs compact hierarchical targets by activating garment-relevant structural branches and predicts executable Sewing patterns in a structured manner. Specifically, we introduce a schema-aware target construction strategy, build the generator on top of a pretrained vision-language model for multimodal garment understanding, and impose feasibility-aware regularization to encourage structurally valid and simulation-compatible outputs. Extensive experiments show that GarmentWeaver produces more accurate and more executable sewing patterns than strong baselines, while also yielding better simulation results. These findings demonstrate the effectiveness of schema-aware structured generation for reliable multimodal Sewing pattern prediction.
Abstract (translated)
URL
https://arxiv.org/abs/2608.30550
PDF
-
OPAL: Orthonormal Prototype Alignment Learning for Interpretable Image Classification
2026-08-30 19:54:58Il\'an Carretero, Gustavo Jes\'us Angulo, Roc\'io del Amor, Valery NaranjoAbstract
Prototypical part-based models provide explainable predictions by comparing input regions to learned prototypes. However, current approaches are burdened by complex, multi-stage training pipelines and heavily rely on auxiliary regularization to prevent prototype collapse. To overcome these limitations, we introduce Orthonormal Prototype Alignment Learning (OPAL), a single-stage, end-to-end framework that simplifies interpretable classification. Our approach anchors the latent space using predefined orthonormal bases, embedding each class within a dedicated subspace spanned by fixed part-prototypes. To achieve precise part localization, OPAL enforces spatial competition across feature maps. This mechanism isolates sparse, discriminative regions, directing each prototype to consistently attend to the same semantic concept across different images. By framing classification as a direct representation alignment task, our method eliminates the need for auxiliary losses. Extensive experiments on fine-grained benchmarks demonstrate that OPAL outperforms both its non-interpretable counterparts and state-of-the-art part-prototype methods, delivering granular visual explanations by explicitly revealing the specific image regions driving every prediction. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.30003
PDF
-
ReCalMatch:Reliability-Calibrated Semantic Guidance for Semi-Supervised Fine-Grained Recognition
2026-08-30 16:49:31Yundi Hong, Hongyang He, Zheng Fang, Xuanyu Liu, Victor SanchezAbstract
Semi-supervised fine-grained visual recognition is highly vulnerable to overconfident pseudo-label errors: visually similar categories frequently produce high-confidence yet incorrect predictions, and consistency regularization then reinforces these errors throughout training. Existing semi-supervised learning (SSL) methods estimate pseudo-label reliability almost entirely from the visual classifier itself---maximum probability, adaptive thresholds, or entropy---signals that remain blind to whether a predicted class is \emph{semantically} compatible with the visual representation. We propose \textbf{ReCalMatch}, a reliability-calibrated semantic framework for semi-supervised fine-grained recognition. Rather than treating textual semantics as auxiliary supervision, ReCalMatch uses multi-aspect semantic prototypes as \emph{calibration evidence} for pseudo-label learning. We construct class-conditioned semantic prototypes from class names and domain-specific semantic aspects, and measure a \emph{visual--semantic agreement} score between each unlabeled embedding and its pseudo-label prototype. This agreement is combined with prediction confidence and entropy into a single reliability weight that down-weights pseudo-labels that are visually confident but semantically inconsistent. A semantic consistency term and a semantic margin regularizer further sharpen prototype separability under limited labels. Extensive experiments on CUB-200-2011, Stanford Dogs, NABirds, and iNaturalist18 show that ReCalMatch consistently improves strong SSL baselines, with the largest gains in low-label regimes where pseudo-label noise is most severe.
Abstract (translated)
URL
https://arxiv.org/abs/2609.29678
PDF
-
The Sequential Price of Continual Learning
Abstract
Sequential task updates are fundamental to continual learning, but their recency bias can impose a lasting performance cost. We study this cost in an overparameterized linear-regression model with i.i.d. task sampling. We prove that distribution-level forgetting and population loss converge to the same stationary limit. This common limit separates exactly into the intrinsic loss asymptotically attained by joint training and an additional sequential price, and in more homogeneous task geometries the two terms coincide, making the total loss twice that of joint training. We further analyze fixed-strength elastic weight consolidation (EWC) under general task curvatures and characterize its stationary sequential price at every regularization strength. Under strong regularization, the price decays inversely with EWC strength while convergence to stationarity slows at the same scale. On the Jester joke-rating dataset, the theory exactly quantifies both the sequential price generated by naturally conflicting user preferences and its reduction by EWC.
Abstract (translated)
URL
https://arxiv.org/abs/2609.29674
PDF
-
ReNFT: Repairing Mode Collapse in Reward Post-Training via Internal Probability-Mass Recalibration
2026-08-30 14:13:50Yuchen Bao, Chao Wen, Haowei Wang, Ruoxin Chen, Donghao Luo, Jiahui Zhan, Wenjian Huang, Shen Chen, Yiting Wang, Taiping Yao, Chengjie Wang, Shouhong Ding, Jianguo ZhangAbstract
Reward post-training of diffusion generators inevitably concentrates probability mass on a few reward-favored modes, a mode collapse that erases within-prompt diversity. Existing methods for mitigating collapse rely on external signals or interfaces, augmenting the reward with perceptual objectives, adjusting reference regularization, or modifying the text encoder, but none repairs an adapter that has already collapsed while preserving the acquired reward. We observe that online post-training primarily reallocates probability mass over capabilities inherited from pretraining rather than learning new visual content. Collapse is therefore suppression, not deletion, and can be reversed from within the generator. We propose ReNFT, which repairs a high-reward, low-diversity adapter through internal probability-mass recalibration. Unconditional probes first prioritize "anti-hub" prompts where the prompt-independent bias is easiest to expose. Two policy-dominated mixed routes then generate matched counterfactual proposals from the same prompt and initial noise, one probing the frozen base direction for suppressed alternatives and the other exposing the post-trained unconditional tendency. Reward ranking with an adaptive flipping guard assigns pull and push roles, and a joint-and-paired NFT update realizes the repair. On PickScore and GenEval, ReNFT retains 98.9% and 99.0% of NFT's reward while improving DreamSim-Div by 58.8% and 55.0%, respectively, offering a complementary alternative to external interventions.
Abstract (translated)
URL
https://arxiv.org/abs/2609.00061
PDF
-
ACTD: Anchor-Based Cross-Tokenizer Distillation with Residual Regularization
2026-08-30 08:54:48Huiyi Zhang, Zijian Li, Xiaocheng Feng, Weitao Ma, Xiaoliang Yang, Yichong Huang, Bing QinAbstract
Knowledge distillation effectively transfers reasoning capabilities from large language models to lightweight student models. To enable knowledge transfer across disparate model families, researchers increasingly explore cross-tokenizer distillation. However, cross-tokenizer distillation remains challenging due to vocabulary and sequence misalignment, while approximate vocabulary alignment can introduce additional noise into distillation. To address these challenges, we propose Anchor-Based Cross-Tokenizer Distillation with Residual Regularization (ACTD). ACTD bridges structural heterogeneity through vocabulary and sequence alignment, while mitigating alignment noise via a novel anchor loss with residual regularization. We further extend this framework to a multi-teacher setting. Evaluated across five reasoning benchmarks with three distinct teacher models, ACTD achieves state-of-the-art performance. Moreover, its multi-teacher extension outperforms the strongest single-teacher and multi-teacher baselines, further demonstrating the robustness of our method.
Abstract (translated)
URL
https://arxiv.org/abs/2608.29662
PDF
-
See the Change, Keep the Flow: Unsupervised Action Segmentation via Spectral-Temporal Representation Learning
2026-08-30 07:04:28Yun Li, Jun Xiao, Cong Zhang, Kin-Man LamAbstract
Unsupervised action segmentation aims to discover latent action categories and their temporal organization without action annotations. Optimal transport-based methods provide structured frame-to-action assignments, however, their pseudo-label quality is fundamentally conditioned on the representation space used to construct the transport cost. We argue that reliable OT pseudo-labeling requires a representation geometry that is simultaneously sensitive to discriminative action changes and coherent along local temporal progressions. Based on this insight, we propose SpecT-OT, a spectral-temporal representation learning framework built upon an unbalanced optimal transport pseudo-labeling concept. SpecT-OT introduces a Spectral Reparameterization Projector (SRP), which parameterizes projector weights with fixed Fourier bases and learnable coefficients to improve the modeling of rapidly varying discriminative features, and Temporal Affinity Regularization (TAR), which imposes distance-aware, label-free constraints on pairwise frame affinities to stabilize local temporal structure. The two components jointly produce more discriminative and temporally stable transport costs, yielding more reliable pseudo-labels for iterative representation learning. Experiments on four benchmarks demonstrate strong performance compared with state-of-the-art methods. SpecT-OT achieves the best results on 13 of 15 metrics, including 4.1-point MoF and 7.4-point F1 gains over the baseline on Breakfast and Desktop Assembly, respectively.
Abstract (translated)
URL
https://arxiv.org/abs/2608.29611
PDF
-
TACS: Trajectory-Aware Candidate Selection for LLM Jailbreak Suffix Optimization
Abstract
Gradient-based jailbreak suffix optimization methods typically update the suffix by retaining the candidate with the lowest current loss. We show that this seemingly natural design is fundamentally myopic: candidates that look better under the current-step proxy often fail to produce better jailbreak outcomes later in the search, revealing a form of selection-stage reward hacking. This suggests that candidate selection, rather than candidate generation alone, is a hidden bottleneck in suffix optimization. To address this issue, we propose \OURS{}, a trajectory-aware candidate selection framework for jailbreak suffix optimization. Instead of selecting candidates solely by their immediate loss, \OURS{} augments per-step evaluation with a trajectory-aware proxy and stabilizes selection with reference-policy regularization and a discriminator-estimated chi-squared correction, encouraging choices that remain effective beyond the current step. Experiments on HarmBench show that \OURS{} consistently outperforms strong baselines under the same search budget, substantially improving attack success rates while exhibiting more stable optimization behavior throughout the search. Our findings highlight that mitigating selection-stage reward hacking caused by myopic candidate selection is critical for improving jailbreak suffix optimization.
Abstract (translated)
URL
https://arxiv.org/abs/2608.29564
PDF
-
CoCoA: Context-Conditional Cultural Alignment for Large Language Models
2026-08-30 01:04:36Kyungdon Lee, Wei Xu, Alan Ritter, Dong-Ho Lee, JinYeong BakAbstract
Large Language Models (LLMs) often favor Western-associated entities across cultural contexts. Conventional debiasing methods aim for uniform neutrality, but cultural bias mitigation demands context-conditional behavior, preferring culturally appropriate entities when cultural cues are present and remaining neutral when they are absent. We propose CoCoA (Context-Conditional Cultural Alignment), a framework that learns this behavior through dual-context training on the same entity pairs under contexts with and without cultural cues. CoCoA combines a contrastive alignment objective with calibration and drift regularization, optimized through goal-aware gradient reconciliation. We evaluate CoCoA on CAMeL and Camellia, two entity-centric cultural bias benchmarks, across ten language settings and four LLMs. CoCoA reduces the Cultural Bias Score from 43 to 24 on average while maintaining near-neutral preferences at 50.2, with minimal impact on general performance across five standard benchmarks. These findings highlight that effective cultural alignment requires context-conditional modeling rather than uniform debiasing, and establish a new direction for mitigating entity-centric cultural bias in LLMs.
Abstract (translated)
URL
https://arxiv.org/abs/2608.29492
PDF
-
Polis: 3D Self-Supervision at City Scale
2026-08-29 20:07:51Alexander Rusnak, Sophia Kovalenko, Jingru Wang, Ismail Moudden, Xiru Wang, Fr\'ed\'eric KaplanAbstract
Reliable semantic representations derived from city-scale 3D models are increasingly important for urban analysis, infrastructure monitoring, autonomous systems, and heritage conservation. However, urban scenes of large spatial extent captured through aerial surveying differ substantially from the indoor, object-level, and self-driving LiDAR data used to pretrain most 3D self-supervised models. We introduce Polis, to our knowledge the first application of Sketched Isotropic Gaussian Regularization (SIGReg) as an objective for a native point cloud encoder, and evaluate it through a frozen-feature benchmark spanning fourteen city- and building-scale corpora. Polis combines geometrically matched cosine invariance, SIGReg, and VICReg-style anti-collapse terms with a 12.8k-scene outdoor pretraining mixture and gravity-preserving spatial view sampling. Controlled ablations show that this objective outperforms student--teacher architecture alternatives, as well as Polis versions without anti-collapse terms, on the same representative outdoor corpus. On three pretraining-disjoint city datasets, Polis reaches $23.8\%$ mean mIoU versus $16.3\%$ for the next-best encoder under high-capacity frozen probing, and $17.3\%$ versus $16.1\%$ at a matched point and voxel budget. The same city-scale lead holds on datasets whose training sets were seen in pretraining. On localized terrestrial captures with fine-grained facade and streetscape labels, the ranking reverses. Our results show that distributionally-regularized joint embedding architectures can be successful on challenging city-scale 3D scenes, and that transfer improves when self-supervision is designed for the capture geometry and spatial context of this domain while also revealing the limits of this specialization.
Abstract (translated)
URL
https://arxiv.org/abs/2608.29426
PDF
-
RAGDiffusion++: From Macro-Retrieval to Micro-Fidelity Alignment for Garment Generation
2026-08-29 14:06:09Yuhan Li, Xianfeng Tan, Fangao Zeng, Wenxiang Shang, Pipei Huang, Hao Zhou, Zhiyu Jin, Wenjun Zhang, Bingbing NiAbstract
Standard clothing asset generation---restoring forward-facing flat-lay garment images from diverse real-world contexts---holds immense commercial value yet demands both macroscopic topological accuracy and microscopic physical fidelity. Although our previous work RAGDiffusion effectively eradicated large-scale structural hallucinations via retrieval-augmented macro-constraints, achieving industrial-grade micro-texture realism remains an unsolved bottleneck. We formally identify this limitation as High-Frequency Trajectory Collapse: supervised fine-tuning (SFT) converges to the conditional mean of the training distribution, which is dominated by smooth, low-frequency textures, causing high-frequency patterns (e.g., fabric weaves, intricate logos) to become nearly un-sampleable. Naively applying Reinforcement Learning (RL) post-training further triggers Artifact Hacking, where models exploit semantic biases in generic reward models by generating deceptive checkerboard noise. Our key insight is that RL can fundamentally reshape the sampling distribution of flow models---elevating the probability of high-fidelity trajectories under accurate reward guidance---while adversarial regularization prevents exploitation of reward blind spots. Realizing this principle requires three prerequisites: (i)inherent capacity, established through a 27,725-pair high-complexity garment dataset (STGarment-Plus) and a Dual-Image-Stream FLUX architecture upgrade; (ii)perceptive reward, provided by a novel attribute-aware reward model (Garment-RM) trained on 500K images via fine-grained contrastive learning, achieving 84.67% human preference accuracy; and (iii)hacking prevention, enforced by our Adversarial-Regularized GRPO (AR-GRPO) strategy that integrates a dynamic discriminator into the RL sampling trajectory to penalize artifacts while enriching authentic high-frequency details.
Abstract (translated)
URL
https://arxiv.org/abs/2608.29280
PDF
-
Using Channel Representations in Regularization Terms: A Case Study on Image Diffusion
2026-08-29 12:33:24Christian Heinemann, Freddie {\AA}str\"om, George Baravdish, Kai Krajsek, Michael Felsberg, Hanno ScharrAbstract
In this work we propose a novel non-linear diffusion filtering approach for images based on their channel representation. To derive the diffusion update scheme we formulate a novel energy functional using a soft-histogram representation of image pixel neighborhoods obtained from the channel encoding. The resulting Euler-Lagrange equation yields a non-linear robust diffusion scheme with additional weighting terms stemming from the channel representation which steer the diffusion process. We apply this novel energy formulation to image reconstruction problems, showing good performance in the presence of mixtures of Gaussian and impulse-like noise, e.g. missing data. In denoising experiments of common scalar-valued images our approach performs competitive compared to other diffusion schemes as well as state-of-the-art denoising methods for the considered noise types.
Abstract (translated)
URL
https://arxiv.org/abs/2608.29227
PDF
