Regularization
-
Localizing to Debias: A Patch-Level Benchmark and Baseline for Weakly Supervised Spatial Anomaly Detection
2026-08-12 13:27:20Sara Abdulaziz, Abdulrahman Al-Abri, Giacomo D'Amicantonio, Egor BondarevAbstract
Despite growing interest in weakly supervised video anomaly detection (WSVAD), current methods struggle to bridge the gap between coarse temporal supervision and fine-grained spatial reasoning. A key obstacle is the tendency of temporal detectors to latch onto background and scene-level cues rather than truly discriminative anomaly evidence. This background bias raises ethical concerns: models may inadvertently associate anomalies with societal or environmental context rather than authentic crime-related cues. Without spatial grounding, such biases remain hidden and unauditable. To address this, we propose SST-WSVADL, a sparse spatio-temporal framework that bridges temporal anomaly detection with fine-grained spatial localization. Rather than processing all spatial regions indiscriminately, SST-WSVADL progressively focuses on the most anomaly-relevant spatio-temporal regions through dynamic sparsification, naturally suppressing background dominant content while preserving discriminative evidence. The temporal and spatial branches are coupled end-to-end via motion-aware regularization that guides sparsification toward dynamically informative regions, without relying on external detectors or vision-language prompts. We publicly release frame-level spatial annotations and a method-agnostic evaluation protocol for three public datasets: UCF-Crime, XD-Violence, and MSAD. These resources enable the community to audit spatial biases in WSVAD predictions, supporting progress toward more ethical and accountable anomaly detection. Experiments demonstrate that SST-WSVADL is competitive with prior methods across benchmarks while enabling localization and patch-level auditability of scene bias, providing a reproducible foundation for interpretability-oriented evaluation of WSVAD models.
Abstract (translated)
URL
https://arxiv.org/abs/2608.12045
PDF
-
CoDiR: Confidence-Guided Diffusion Refinement for Semi-Supervised Histopathology Segmentation
2026-08-12 08:51:13Hoai Nhan Pham, Dang-Nguyen Bui, Le-Van Thai, Thanh-Hiep Vo, Lan Anh Dinh Thi, Tien Dat Nguyen, Duy-Dong Nguyen, Ngoc Lam Quang Bui, Tam Tran, Zhi HuangAbstract
Semi-supervised histopathology segmentation is challenging due to scarce annotations and unreliable pseudo-labels in ambiguous gland regions. To address this problem, we propose Confidence-Guided Diffusion Refinement (CoDiR), a semi-supervised framework that combines a Mean Teacher segmentation model with diffusion-based pseudo-label refinement. Given an unlabeled image, the teacher first produces a soft prediction, and only low-confidence regions are refined by a conditional diffusion model trained to capture plausible mask structures from labeled data. The refined mask is then fused with reliable teacher predictions and used to train the student with confidence weighting and consistency regularization. On the GlaS and CRAG datasets CoDiR reaches 88.09\% and 89.83\% mDice with 10\% labeled data, and 89.19\% and 90.29\% mDice with 20\%, matching or exceeding the strongest published method on seven of the eight benchmark metrics. Ablations attribute the largest single contribution to the refinement module, which adds +6.36\% mDice over the Mean Teacher baseline. The implementation code is publicly available at: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2608.11807
PDF
-
Dual Modality Prompted Diffusion Priors for Zero Shot Hyperspectral Pansharpening
2026-08-12 07:40:57Pengwei Xie, Fei Zhu, Jiajun Li, Xiangyuan Liu, Xiangyuan Liu, Kangqing Shen, Gemine VivoneAbstract
Hyperspectral pansharpening aims to reconstruct a high resolution hyperspectral (HRHS) image from a panchromatic (PAN) image and a low resolution hyperspectral (LRHS) image while preserving both spatial details and spectral fidelity. Recent diffusion based methods exploit pretrained image priors by generating a low dimensional representation and subsequently mapping it to the hyperspectral domain. However, the observed panchromatic and hyperspectral images are typically imposed only through external reconstruction objectives, limiting their direct interaction with the diffusion prior. To address this issue, we propose dual-modality image-prompted diffusion model (DIDM) for zero shot hyperspectral pansharpening. DIDM encodes the low resolution hyperspectral and panchromatic observations into spectral and spatial prompt tokens, respectively, and injects them into intermediate features of a frozen remote sensing diffusion model through cross attention, allowing complementary spectral and spatial information to directly guide diffusion feature evolution. In addition, we introduce a panchromatic guided weighted pixel aware total variation regularizer that combines low resolution hyperspectral degradation fidelity and panchromatic response fidelity with gradient adaptive structural regularization, thereby preserving structural discontinuities while suppressing spurious variations in homogeneous regions. Extensive experiments on Pavia, Chikusei, and Houston under reduced resolution protocols show that DIDM achieves the best performance across all evaluated metrics, while full resolution evaluation on FR1 yields the highest HQNR among the compared methods. These results demonstrate that internal dual modality prompting and panchromatic guided structural regularization provide an effective balance between spatial detail enhancement and spectral preservation.
Abstract (translated)
URL
https://arxiv.org/abs/2608.11748
PDF
-
CAM-Guided Saliency Cutout and Image-Based Malware Classification
2026-08-12 04:32:00Yasaman Ebrahimi, Martin Jurecek, Mark StampAbstract
Dropout regularization is commonly used to reduce overfitting by removing parts of a neural network during training. For Convolutional Neural Networks (CNN), cutouts serve a somewhat analogous purpose. Cutouts can be implemented as data augmentation: the original training image is retained, and additional copies are created with regions removed. In this chapter, we test whether cutout placement can be improved by using High-Resolution Class Activation Mapping (HiResCAM). We compare four controlled training conditions: no cutout, standard random cutout, low-saliency cutout, and high-saliency cutout. We experiment using grayscale malware images from the RawMal-TF dataset (17 families with~1,000 samples per family), and for comparison to natural images, we experiment with the well-known CIFAR-100 dataset. All experiments are based on ResNet18 with~100 training epochs. For the cutout experiments, we test cutout areas of~5\%, 10\%, 20\%, and~30\%, and we consider~$M\in\{4,8}$ augmented copies per original training image. The RawMal-TF results are slightly worse for all three cutout cases (random, high and low saliency) as compared to no cutouts. In contrast, our CIFAR-100 experimental results improve slightly under low-saliency cutout. These results suggest that the value of saliency-guided cutout is domain dependent, and that malware images should not be treated as equivalent to natural images.
Abstract (translated)
URL
https://arxiv.org/abs/2608.11634
PDF
-
DeCo-MIL: Debiased Counterfactual Reasoning for Long-Tailed Whole Slide Image Analysis
2026-08-12 03:52:31Xiaoxiao Li, Xitong Ling, Jiawen Li, Weiming Chen, Zhenyang Cai, Xidong Wang, Tian Guan, Benyou Wang, Yonghong HeAbstract
Multiple instance learning (MIL) is widely used for weakly supervised whole slide image (WSI) analysis. However, under long-tailed distributions, MIL-based WSI analysis faces a nested dual long-tail: an inter-slide class long tail and an intra-slide long tail of instance-level discriminative evidence. The two long tails are coupled: tail classes have few training slides, while their limited diagnostic evidence is concentrated in a few patches and obscured by abundant within-bag redundancy. This coupling biases models toward head classes and degrades rare-class recognition. To address this, we propose DeCo-MIL for long-tailed WSI analysis, which jointly alleviates the nested dual long-tail through frequency-debiased counterfactual reasoning. For the inner long tail, DeCo-MIL clusters patches into tissue-morphology anchors, replaces each anchor with its matched normal prototype to perform a counterfactual intervention, and estimates its counterfactual contribution to the ground-truth class using class-frequency-corrected predictions. These contributions guide redundancy masking to preserve scarce discriminative instances. For the outer long tail, DeCo-MIL constructs anchor-stratified pseudo-bags from redundancy-reduced bags and combines tail-aware oversampling with consistency regularization, increasing effective supervision for tail classes while preserving tissue-morphology composition. Extensive experiments on three long-tailed WSI benchmarks demonstrate that DeCo-MIL achieves state-of-the-art performance in both tail-class recognition and overall classification.
Abstract (translated)
URL
https://arxiv.org/abs/2608.14719
PDF
-
Boundary-Continuous Cross-Camera RGB Mapping via Hue-Split Model Trees
2026-08-12 01:34:05Yuma Kinoshita, Hitoshi KiyaAbstract
We propose a hue-split model-tree method for boundary-continuous cross-camera RGB mapping. Cross-camera RGB mapping aims to produce consistent color representations across cameras whose recorded RGB values differ due to sensor spectral sensitivities and image-signal processing pipelines. A common chart-based remedy is to estimate a single global affine color correction matrix (CCM), but such a global model cannot capture hue-specific discrepancies between cameras. To capture that behavior, we recursively partitions the source-camera color space along a scalar hue coordinate and builds an model tree that stores an affine CCM at every node. For fitting the node CCMs, we utilize a log-domain error objective. To prevent false contours that arise from hard hue splits, we further introduce a boundary-continuous formulation in which the prediction is obtained by blending the log-domain outputs of all node CCMs along the root-to-leaf path. The path-wise blending weights are optimized under a simplex constraint using both a chart-pair fitting loss and an explicit continuity regularizer defined on deterministic boundary prototype pairs placed just on either side of each learned hue threshold. We conducted an experiment on a Canon EOS-1Ds Mark II to Canon EOS 20D mapping using the Middlebury Registered Color Checker dataset. The results show that hue splitting substantially reduces log-RMSE over a single global affine CCM and that the proposed path blending with boundary prototype regularization simultaneously improves accuracy and suppresses chromaticity gaps at the learned hue thresholds across two illuminants and multiple exposure conditions.
Abstract (translated)
URL
https://arxiv.org/abs/2608.11548
PDF
-
VIScore: Diagnosing Planning-Relevant Quality in Latent World Models
2026-08-11 17:34:10Haiyu Wu, Randall Balestriero, Morgan LevineAbstract
Regulating the latent space to an isotropic Gaussian distribution provides a stable and information-maximized landscape for world model planning. However, the latent space property and successful planning remain disconnected. We first study this by comparing SIGReg and VISReg, two regularization loss functions with the same distribution target but different properties. Compared with SIGReg, VISReg has more flexibility in controlling the weights of center, scale, and shape regularization, and a larger batch size brings a finer distribution approximation. We find that the former, despite being beneficial in self-supervised learning (SSL), does not help the planning, whereas the latter improves the planning success on out-of-domain (OOD) datasets. This motivates a deep understanding of the factors that correlate with the success rate. Unlike the previous metrics focusing on the encoded latent only, we propose the Veracity-Influence-Sobriety score (VIScore), a metric that quantifies the reachability and capacity of a predictor given the encoded feature, and the hallucination of the searching-based planner. Compared with straightness, physical-state probing, and empowerment, we show that, with the measurement covering encoder, predictor, and planner, VIScore explains the success rate better than the others, as reflected by a strong Spearman correlation. Specifically, VIScore consistently achieves a Spearman correlation over 0.75 on both seen and unseen models and datasets on the cross-task success rate pool. Moreover, VIScore is the only metric that has a calibration error below the constant fit across all testing scenarios, showcasing the importance of these three aspects in planning success. We hope this metric can help future studies on world model design and diagnosis.
Abstract (translated)
URL
https://arxiv.org/abs/2608.11174
PDF
-
SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense
2026-08-11 14:01:24Siyuan Liang, Yupeng Qiu, Junfeng Fang, Rong-Cheng Tu, Jiaxing Huang, Dacheng TaoAbstract
Text-to-Video (T2V) generative models are vulnerable to jailbreak attacks in real-world deployment, leading them to produce harmful or inappropriate content. Existing defense approaches mainly rely on input filtering or reconstruction, which not only incur high computational latency but also tend to distort semantics. To address these issues, we experimentally and systematically analyze the differences between clean and jailbreak samples in the cross-attention feature space, revealing for the first time a cumulative separation effect and a progressively increasing trend of linear separability between the two during the diffusion process. Based on this insight, we propose SafeCA, a feature-level defense mechanism for safe cross-attention localization and regularization. Firstly, we identify key defensive regions and values through attention stability analysis using cross-attention features collected from clean prompts within a single inference. Secondly, SafeCA mitigates anomalous activations via attention masking with energy normalization and introduces a lightweight semantic-space adapter to redirect abnormal semantic flows. Furthermore, we detect and suppress potentially malicious tokens by back-propagating feature anomaly signals to the input cue words, thereby enhancing the deployability of the defense in commercial models. Experimental results show that SafeCA reduces the jailbreak success rate by about 20% on mainstream T2V models, adds almost no inference overhead (+0.1s), and maintains good text-video semantic consistency. Overall, SafeCA provides an architecture-level, deployable protection paradigm for T2V generation models.
Abstract (translated)
URL
https://arxiv.org/abs/2608.10933
PDF
-
DSAR: Dual-Stream Autoregressive Modeling of Temporal Cloth Dynamics for Photorealistic Animatable Avatars
2026-08-11 05:19:21Haozhong Xiong, Yao Yu, Yu Zhou, Sidan DuAbstract
Creating photorealistic and temporally coherent animatable human avatars from RGB videos remains challenging. Current methods struggle to capture realistic cloth dynamics, producing over-smoothed appearance or severe artifacts on out-of-distribution poses. This limitation stems from a fundamental oversight: existing approaches neglect the temporal causality inherent in cloth physics, where current states emerge from previous states through temporal evolution rather than instantaneous skeletal configurations alone. Without explicit modeling of this causal structure, networks learn pose-appearance correlations instead of motion evolution, leading to poor generalization. We introduce a dual-stream autoregressive framework that explicitly models both observable geometric information and implicit internal state. The geometric stream propagates surface displacement from the previous frame, while the state stream fuses current features with historical states retrieved from a memory bank. Motion-adaptive aggregation handles spatially-varying dynamics, and adaptive regularization balances smoothness with flexibility. Experiments on challenging datasets demonstrate significant improvements in rendering quality, temporal consistency, and generalization to motion patterns beyond training distributions, validating that dual-stream temporal modeling enables realistic cloth dynamics.
Abstract (translated)
URL
https://arxiv.org/abs/2608.10500
PDF
-
ELVAE: Evidential Learning-Based Variational Autoencoder for Uncertainty-Aware Generation
Abstract
Variational autoencoders generate samples from probabilistic latent representations but do not distinguish uncertainty about the latent location from variability around it. We formulate ELVAE, an evidential learning-based VAE in which each latent coordinate is governed by an input-dependent normal-inverse-gamma posterior. This hierarchy yields an explicit latent-location uncertainty that can be used during generation, not merely reported after inference: low-uncertainty anchors support more reliable synthetic samples, while high-uncertainty anchors can be deliberately exploited for stress testing. The objective is an exact evidence lower bound, and we show that direct regularization of the full hierarchy is required, since the marginalized latent law alone cannot identify the uncertainty decomposition. In an MNIST generation pilot with a frozen external classifier, this uncertainty clearly stratified the semantic reliability of generated digits. A zero-displacement control revealed that most of the effect reflects how reliably an anchor can be re-generated, while a smaller but distinct component is attributable to uncertainty-scaled perturbation itself. The effect holds only under within-class uncertainty ranking, and its magnitude varies across seeds. These findings support the learned latent-location uncertainty as a practical control variable for uncertainty-aware generation, separating anchor reliability from perturbation-induced failure.
Abstract (translated)
URL
https://arxiv.org/abs/2608.10398
PDF
-
Deep Analog: Open-Set Film Emulation with Reference-Conditioned 3D LUTs
2026-08-10 20:46:54Yitong MuAbstract
Film emulation reproduces the look of an analog film stock on a new digital photograph. We target its open-set form -- matching any reference film frame from a single example -- with a 3D lookup table (LUT) predicted from that reference. Real-time image enhancement predicts per-image weights over a fixed bank of 3D LUTs and blends them. We show this is a gated mixture of experts and inherits its failure: trained end-to-end against reconstruction, the gate collapses onto a single expert, so a bank of K LUTs delivers the capacity of one. An entropy term, the enhancement-setting analogue of mixture-of-experts load balancing, restores utilization and recovers about 1 dB PSNR. The deeper constraint survives: a fixed LUT basis is closed-set, freezing the achievable looks at training time. We therefore discard the basis and predict a single 3D LUT as a residual from a reference image (StyleLUTNet), trained by self-supervision on procedurally generated color transforms. The conditional design removes the gate and generalizes open-set to unseen film stocks without paired data or retraining. Around this color backbone we build Deep Analog, a film-emulation pipeline that adds histogram-based tone matching and a physics-informed optical renderer -- multi-scale grain and per-channel halation driven by parameters an inverse network regresses from the reference. On 350 self-supervised pairs the color stage reaches 22.05 dB PSNR / 0.925 SSIM and the full pipeline 21.72 dB / 0.923; the color path runs in 5.2 ms at 1080p (192 FPS) and exports a portable .cube LUT for standard editing tools. A second degeneracy in conditional LUT training -- residual-scale collapse -- shares the root cause and yields a general principle: auxiliary regularization must stay subordinate to reconstruction.
Abstract (translated)
URL
https://arxiv.org/abs/2608.14702
PDF
-
DistMoE: Private-data Rehearsal-free Routing in Mixture-of-Experts for Distributed Instruction Tuning
2026-08-10 17:52:14Mainak Singha, Niccol\`o Biondi, Elisa Ricci, Subhankar RoyAbstract
Multimodal Large Language Models (MLLMs) have shown strong multimodal instruction-following ability, but adapting them to diverse visual-language domains typically assumes centralized data access and costly joint training. This is restrictive when data is distributed across private, domain-specific, or permission-limited clients. To this end, we propose DistMoE, a mixture-of-experts (MoE) approach for distributed visual instruction tuning. In each layer of the language decoder it augments the public feedforward network (FFN) with a client-specific private FFN expert, with the goal to acquire domain-specific knowledge. However, independent expert training causes the private FFNs to learn representation of different scale and magnitudes, making merging the experts difficult. To reduce client-specific drift, we introduce a public-anchored expert composition stage that updates only routers and lightweight private projection adapters on a mix of local client data and public data, via an isotropic regularization loss, therefore making it cross-client rehearsal-free composition. During inference, DistMoE performs modular routing over public and private experts, enabling token-wise domain composition without explicit domain labels. Experiments across diverse visual-language benchmarks show that DistMoE enables flexible expert reuse, effective domain adaptation, and competitive performance while preserving modular control over client-specific knowledge. Codes are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.09907
PDF
-
Se-DPO: Self-Evolving Token Credit for Direct Preference Optimization
2026-08-10 13:05:38Wenxiao Zhao, Shu Wang, Ying Nian WuAbstract
Direct Preference Optimization (DPO) aggregates token-level log-probability ratios via uniform summation, implicitly treating all tokens as contributing equally to the preference signal. However, the contribution of individual tokens to the preference signal varies. We introduce token credit, which modulates each token's KL regularization based on its contribution to the preference outcome. We derive that effective token credit is proportional to the magnitude of each token's implicit reward, and observe that this quantity evolves substantially during training. This implies that static token credit becomes increasingly misaligned as training progresses. In this work, we propose Se-DPO (Self-Evolving Token Credit for DPO), a live mechanism that derives token credit from the model's own evolving internal signals during DPO training. Since the reward signal varies in reliability across positions, Se-DPO calibrates token credit based on both the strength and the confidence of each token's contribution. Se-DPO requires no external models, adding only a lightweight calibration network with minimal computational overhead. Experiments show that Se-DPO improves over DPO by up to 9.8 points on AlpacaEval~2 and 12.2 points on Arena-Hard.
Abstract (translated)
URL
https://arxiv.org/abs/2608.09568
PDF
-
DocPure: Prompt-Free Unified Document Restoration via Degradation-Aware Structure-Guided Wavelet Modulation
2026-08-10 12:35:39Lingming Su (College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou, China), Wanglong Lu (College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou, China, AI Analytics Team, Nasdaq, St. John's, Canada), Tao Wang (vivo Mobile Communication Co., Ltd, Shanghai, China), Kaihao Zhang (College of Engineering and Computer Science, The Australian National University, Canberra, Australia), Nan Zhang (College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou, China), Liyan An (College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou, China), Hanli Zhao (College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou, China)Abstract
High-quality document images are pivotal for information archiving and downstream automatic processing. However, they are frequently compromised by diverse degradations during uncontrolled acquisition and transmission. While unified document restoration techniques have been proposed to restore images from multiple degradations, they often struggle with training multiple degradation-specific models, reliance on manual task-specific prompts, or cross-task data pairing. To address these limitations, we propose DocPure, a prompt-free unified framework that achieves degradation-aware document restoration. We design a degradation-aware structure auto-encoder with degradation-informed routing regularization to predict clean structural priors from degraded inputs. The model is prompt-free at inference, and degradation labels are only used as auxiliary supervision for the routing regularization during training. Furthermore, we introduce a structure-guided wavelet interaction mechanism to bridge frequency-domain features and spatial semantics. Within the structure-guided wavelet interaction mechanism, a cross-frequency adaptive modulation utilizes low-frequency sub-bands to modulate high-frequency recovery, ensuring structural consistency. Extensive experiments demonstrate that DocPure achieves strong performance compared with state-of-the-art methods across various tasks, including deblurring, denoising, compression artifact reduction, and deshadowing.
Abstract (translated)
URL
https://arxiv.org/abs/2608.09536
PDF
-
RecoverFly: A Failure-Aware Reinforcement Learning Post-Training Framework for Aerial Vision-Language Navigation
2026-08-10 11:37:46Boxiong Wang, Hui Kang, Geng Sun, Jiahui Li, Chao Yu, Daxin TianAbstract
Unmanned aerial vehicle vision-language navigation (UAV-VLN) requires agents to translate visual observations and language instructions into reliable flight actions in complex environments. Although recent end-to-end UAV vision-language-action (UAV-VLA) policies reduce reliance on separately designed perception, planning, and control modules, their behavior-cloning objectives provide limited corrective supervision for interactive closed-loop execution. Reinforcement learning (RL) offers a promising solution, while its effectiveness is constrained by inefficient use of samples, long-tailed scene distributions, and policy distribution shift during optimization. To this end, we propose RecoverFly, a failure-aware RL post-training framework for end-to-end UAV-VLA policies. Specifically, RecoverFly adapts token-level RL for stable optimization of grammar-constrained autoregressive UAV actions, revisits unresolved failure cases to strengthen corrective learning and sample utilization, and combines a two-stage long-tail scene curriculum with reference-policy regularization to improve scene adaptation while preserving acquired capabilities. Experiments on the TravelUAV benchmark demonstrate that RecoverFly achieves the best performance on the seen, unseen-map, and unseen-object splits. Moreover, compared to the AerialVLA initialization, RecoverFly improves success rate by 3.12 to 8.37 percentage points under a total rollout budget of about 30\% of the training-set size, validating its effectiveness, robustness, and generalization capabilities.
Abstract (translated)
URL
https://arxiv.org/abs/2608.09467
PDF
-
Flow-based conditional cardiac anatomy generation for virtual cohorts
2026-08-10 11:30:02Konstantinos Kevopoulos, Beatrice Moscoloni, Benjamin Alheit, Cameron Beeche, Julio A. Chirinos, Alexander Heinlein, Mathias PeirlinckAbstract
Cardiac digital twin research is moving from subject-specific anatomical replicas toward virtual cohorts that represent clinically relevant population subgroups. Yet access to representative imaging-derived anatomy datasets remains limited by cohort size, subgroup sparsity, and data-sharing constraints. Conditional generative models could help address this gap, but virtual cohorts are useful only if they preserve realistic, metadata-dependent anatomical variability. Existing cardiac anatomy generators largely rely on conditional variational autoencoders (cVAEs), which couple representation learning and metadata conditioning through a shared regularized latent prior. We introduce CAN-FLOW, a two-step Conditional ANatomy generation framework based on normalizing FLOWs that first learns geometry-only latent representations of diffeomorphic cardiac shape momenta and then models their sex-, age-, and body-mass-index-dependent distribution with a conditional normalizing flow. We trained CAN-FLOW on 2,208 healthy UK Biobank subjects and compared it with cVAEs across regularization strengths. CAN-FLOW generated plausible stochastic biventricular anatomies that better reproduced clinical phenotype distributions, metadata-dependent trends, subgroup variability, point-cloud coverage, and high-dimensional shape variability. Together, these results establish CAN-FLOW as a shareable framework for generating realistic, stochastically varying, metadata-conditioned biventricular anatomies for virtual cohort construction and in silico clinical trial workflows.
Abstract (translated)
URL
https://arxiv.org/abs/2608.09460
PDF
-
Imaginative Generative AI: Crossing the Entropy Wall into Worlds Beyond Imitation
2026-08-10 10:05:46Hossein Goli, Farzan Farnia, Amin GohariAbstract
Generative AI models are primarily designed to imitate the data distribution, an objective that neither corrects diversity lost by a learned generator nor defines how generation should extend beyond the diversity of the data itself. We introduce Imaginative Generative AI (IGA), a framework that makes diversity part of the target-distribution design problem: among distributions close to a reference, IGA selects one whose spectral diversity reaches a prescribed level. Diversity is measured by the von Neumann entropy of the generated distribution's kernel covariance operator in a fixed representation space, providing a reference-free representation-guided measure of how broadly probability mass occupies embedding directions. The spectral entropy of the population data distribution defines an Entropy Wall. Below the wall, IGA performs diversity repair, recovering variation that a learned generator has lost while remaining within the diversity level of the data. Beyond the wall, the data distribution itself becomes infeasible, and IGA deliberately departs from it to produce distributions with greater representation-relative spectral diversity, an operational notion of imaginative generation. These regimes form a single regularization path from imitation to imagination and define an i.i.d. target distribution at each prescribed diversity level. We develop the theory of this entropy-constrained projection and show that, under a KL anchor to a pretrained generator, the optimum satisfies a self-consistent exponential-tilt relation. This characterization leads to IGA Guidance, a retraining-free inference-time method for score-based and diffusion models, including DDPM and DDIM samplers. Experiments on synthetic and vision benchmarks demonstrate diversity repair below the Entropy Wall and controlled spectral extrapolation beyond it.
Abstract (translated)
URL
https://arxiv.org/abs/2608.09385
PDF
-
In-Loop Model Adaptation with Coupled Latent-Noise Guidance for High-Fidelity Subject-Driven Text-to-Image Generation
2026-08-10 08:07:28Yushun Tang, Weiming Chen, Siyi Liu, Yi Zhang, Feng Wu, Zhihai HeAbstract
Text-to-image diffusion models have achieved remarkable success in generating high-quality images from a given text prompt. Subject-driven generation aims to synthesize customized images to mimic the appearance of subjects in given reference images within different visual contexts specified by the text prompts. The central challenge here is that, when the reference image changes, the diffusion model cannot efficiently adapt to different visual contexts while consistently maintaining the subject identity. Existing methods either train the model with a large domain-specific dataset or fine-tune the model using the reference image for hundreds of iterations before actual image generation. In this work, we explore a new approach, called \textit{In-Loop Model Adaptation} (IMA), which adapts the core diffusion model at each generation step during the actual process of image generation, without being trained on the reference image before the generation process. To this end, we establish a DDIM inversion chain that maps the reference image to a sequence of latent, as well as a text-to-image generation chain which generates the image from the text prompt only. We then introduce a masked latent consistency loss and a noise regularization loss to characterize the latent-noise difference between the diffusion model and these two chains at each generation step. This coupled latent-noise loss is used to guide the in-loop model adaptation to preserve the subject identity specified by the reference image while maintaining accurate alignment with the text prompt, resulting in high-fidelity text-to-image generation. Our extensive experiments demonstrate that our proposed IMA method significantly improves the performance of subject-driven text-to-image generation.
Abstract (translated)
URL
https://arxiv.org/abs/2608.09244
PDF
-
Rethinking Medical Landmark Localization with Prototype Learning-based Progressive Offset Correction
2026-08-10 06:49:16Jingxian Xu, Yuhao Huang, Rusi Chen, Yanfeng Zhou, Dong NiAbstract
Accurate landmark localization in medical images is a fundamental step for quantitative clinical measurement and downstream analysis. Existing localization methods have advanced, among which multi-stage refinement is a superior solution. Although this strategy mitigates the anatomical ambiguity inherent in single-stage global predictions, its high computational cost limits practical applicability. In this work, we propose a parameter-economic model, PPOC-LL, which leverages Prototype learning-based Progressive Offset Correction for Landmark Localization. Our contribution is three-fold. First, to drive coarse-to-fine landmark optimization, we introduce a multi-scale dynamic perception strategy for patch-level feature pyramid modeling. Second, to effectively handle anatomically similar patterns, we design a similarity-driven prototype learning mechanism that captures informative local semantics for robust offset prediction. Last, to stabilize the model learning and improve the overall performance, we incorporate a novel error-aware reliability regularization via tolerance-based balancing. We collected a large validation cohort, including two public and one private datasets spanning X-ray and ultrasound modalities, covering cephalometric, symphysis-fetal head, and fetal heart landmarks. Extensive experiments demonstrate that PPOC-LL achieves satisfactory performance with a favorable trade-off between accuracy and model complexity.
Abstract (translated)
URL
https://arxiv.org/abs/2608.09182
PDF
-
View-Adaptive Renderer for View-Consistent 2D-to-3D Generation
2026-08-10 04:28:08U-Chae Jun, Jaeeun Ko, Jiwoo KangAbstract
Reconstructing 3D shapes from a single image remains a fundamental yet challenging problem in computer vision. Traditional monocular 3D generation pipelines typically synthesize multiple views from a single input image before applying Neural Radiance Field (NeRF)-based reconstruction. However, inherent projective ambiguities often produce visual discontinuities across generated viewpoints, leading to inaccuracies in reconstructed 3D models. Current solutions either incur significant additional computational burdens or fail to adequately resolve practical inconsistencies between synthesized views. To address these limitations, we propose a novel viewpoint-adaptive neural rendering framework that enables robust 3D reconstruction even when given partially inconsistent multi-view inputs. Our approach introduces view-adaptive neural renderers that independently correct viewpoint-dependent errors while simultaneously sharing a global feature backbone to preserve structural coherence. Furthermore, we propose a self-attention fusion module that adaptively integrates multi-view information, ensuring geometric consistency without relying heavily on indirect regularizations or computationally intensive methods. Through extensive experiments, we demonstrate that our method consistently improves 3D reconstruction fidelity. Importantly, our approach achieves near state-of-the-art performance without diffusion-based SDS supervision, relying primarily on photometric rendering loss with lightweight attention regularizers. This balance between accuracy and efficiency makes the proposed framework highly practical for real-world applications.
Abstract (translated)
URL
https://arxiv.org/abs/2608.09110
PDF
