# Research Papers — 2026-03 · bundle page 136 of 243 > Full-text markdown of papers #6751–6800 of 12123 published in 2026-03, newest first. AI-readable mirrors of the full 12123-paper 2026-03 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-03/page/136 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/135.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/137.md) ### Sat-JEPA-Diff: Bridging Self-Supervised Learning and Generative Diffusion for Remote Sensing Authors: Kursat Komurcu, Linas Petkevicius Published: 2026-03-14 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.13943v1 Predicting satellite imagery requires a balance between structural accuracy and textural detail. Standard deterministic methods like PredRNN or SimVP minimize pixel-based errors but suffer from the "regression to the mean" problem, producing blurry outputs that obscure subtle geographic-spatial features. Generative models provide realistic textures but often misleadingly reveal structural anomalies. To bridge this gap, we introduce Sat-JEPA-Diff, which combines Self-Supervised Learning (SSL) with Hidden Diffusion Models (LDM). An IJEPA module predicts stable semantic representations, which then route a frozen Stable Diffusion backbone via a lightweight cross-attention adapter. This ensures that the synthesized high-accuracy textures are based on absolutely accurate structural predictions. Evaluated on a global Sentinel-2 dataset, Sat-JEPA-Diff excels at resolving sharp boundaries. It achieves leading perceptual scores (GSSIM: 0.8984, FID: 0.1475) and significantly outperforms deterministic baselines, despite standard autoregressive stability limits. The code and dataset are publicly available on https://github.com/VU-AIML/SAT-JEPA-DIFF. --- ### Bidirectional Cross-Attention Fusion of High-Resolution RGB and Low-Resolution Hyperspectral Inputs for Multimodal Semantic Segmentation Authors: Jonas V. Funk, Lukas Roming, Andreas Michel, Paul Bäcker, Georg Maier, Thomas Längle, Markus Klute Published: 2026-03-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.13941v3 Multimodal semantic segmentation with heterogeneous sensors must reconcile complementary information across modalities that differ in spatial resolution and channel dimensionality. In particular, high-resolution RGB imaging provides detailed spatial structure but often fails to distinguish visually similar materials, whereas hyperspectral imaging (HSI) provides discriminative spectral signatures but at lower spatial resolution. We present Bidirectional Cross-Attention Fusion (BCAF), which aligns high-resolution RGB with low-resolution HSI at their native grids via localized, bidirectional cross-attention, avoiding pre-upsampling or early spectral collapse. BCAF uses two independent backbones: a standard Swin Transformer for RGB and an HSI-adapted Swin backbone that preserves spectral structure through 3D tokenization with spectral self-attention. Although our evaluation targets RGB-HSI fusion, BCAF is modality-agnostic and applies to co-registered RGB with lower-resolution, high-channel auxiliary sensors. On the benchmark SpectralWaste dataset, BCAF delivers strong performance, achieving 75.4% at 55 images/s. We further evaluate a novel industrial dataset: K3I-Cycling (first RGB subset already released on Fordatis). On this dataset, BCAF reaches 62.3% mIoU for material segmentation (paper, metal, plastic, etc.) and 66.2% mIoU for plastic-type segmentation (PET, PP, HDPE, LDPE, PS, etc.). These results show that preserving native-grid spatial detail and spectral structure improves multimodal segmentation under real-time constraints. Code and model checkpoints are publicly available at https://github.com/jonasvilhofunk/BCAF_2026. --- ### GroupGuard: A Framework for Modeling and Defending Collusive Attacks in Multi-Agent Systems Authors: Yiling Tao, Xinran Zheng, Shuo Yang, Meiling Tao, Xingjun Wang Published: 2026-03-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.13940v1 While large language model-based agents demonstrate great potential in collaborative tasks, their interactivity also introduces security vulnerabilities. In this paper, we propose and model group collusive attacks, a highly destructive threat in which multiple agents coordinate via sociological strategies to mislead the system. To address this challenge, we introduce GroupGuard, a training-free defense framework that employs a multi-layered defense strategy, including continuous graph-based monitoring, active honeypot inducement, and structural pruning, to identify and isolate collusive agents. Experimental results across five datasets and four topologies demonstrate that group collusive attacks increase the attack success rate by up to 15\% compared to individual attacks. GroupGuard consistently achieves high detection accuracy (up to 88\%) and effectively restores collaborative performance, providing a robust solution for securing multi-agent systems. --- ### Iterative Semantic Reasoning from Individual to Group Interests for Generative Recommendation with LLMs Authors: Xiaofei Zhu, Jinfei Chen, Feiyang Yuan, Zhou Yang Published: 2026-03-14 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2603.13934v1 Recommendation systems aim to learn user interests from historical behaviors and deliver relevant items. Recent methods leverage large language models (LLMs) to construct and integrate semantic representations of users and items for capturing user interests. However, user behavior theories suggest that truly understanding user interests requires not only semantic integration but also semantic reasoning from explicit individual interests to implicit group interests. To this end, we propose an Iterative Semantic Reasoning Framework (ISRF) for generative recommendation. ISRF leverages LLMs to bridge explicit individual interests and implicit group interests in three steps. First, we perform multi-step bidirectional reasoning over item attributes to infer semantic item features and build a semantic interaction graph capturing users' explicit interests. Second, we generate semantic user features based on the semantic item features and construct a similarity-based user graph to infer the implicit interests of similar user groups. Third, we adopt an iterative batch optimization strategy, where individual explicit interests directly guide the refinement of group implicit interests, while group implicit interests indirectly enhance individual modeling. This iterative process ensures consistent and progressive interest reasoning, enabling more accurate and comprehensive user interest learning. Extensive experiments on the Sports, Beauty, and Toys datasets demonstrate that ISRF outperforms state-of-the-art baselines. The code is available at https://github.com/htired/ISRF. --- ### OmniCompliance-100K: A Multi-Domain, Rule-Grounded, Real-World Safety Compliance Dataset Authors: Wenbin Hu, Huihao Jing, Haochen Shi, Changxuan Fan, Haoran Li, Yangqiu Song Published: 2026-03-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.13933v2 Ensuring the safety and compliance of large language models (LLMs) is of paramount importance. However, existing LLM safety datasets often rely on ad-hoc taxonomies for data generation and suffer from a significant shortage of rule-grounded, real-world cases that are essential for robustly protecting LLMs. In this work, we address this critical gap by constructing a comprehensive safety dataset from a compliance perspective. Using a powerful web-searching agent, we collect a rule-grounded, real-world case dataset OmniCompliance-100K, sourced from multi-domain authoritative references. The dataset spans 74 regulations and policies across a wide range of domains, including security and privacy regulations, content safety and user data privacy policies from leading AI companies and social media platforms, financial security requirements, medical device risk management standards, educational integrity guidelines, and protections of fundamental human rights. In total, our dataset contains 12,985 distinct rules and 106,009 associated real-world compliance cases. Our analysis confirms a strong alignment between the rules and their corresponding cases. We further conduct extensive benchmarking experiments to evaluate the safety and compliance capabilities of advanced LLMs across different model scales. Our experiments reveal several interesting findings that have great potential to offer valuable insights for future LLM safety research. --- ### True 4-Bit Quantized Convolutional Neural Network Training on CPU: Achieving Full-Precision Parity Authors: Shivnath Tathe Published: 2026-03-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.13931v1 Low-precision neural network training has emerged as a promising direction for reducing computational costs and democratizing access to deep learning research. However, existing 4-bit quantization methods either rely on expensive GPU infrastructure or suffer from significant accuracy degradation. In this work, we present a practical method for training convolutional neural networks at true 4-bit precision using standard PyTorch operations on commodity CPUs. We introduce a novel tanh-based soft weight clipping technique that, combined with symmetric quantization, dynamic per-layer scaling, and straight-through estimators, achieves stable convergence and competitive accuracy. Training a VGG-style architecture with 3.25 million parameters from scratch on CIFAR-10, our method achieves 92.34% test accuracy on Google Colab's free CPU tier -- matching full-precision baseline performance (92.5%) with only a 0.16% gap. We further validate on CIFAR-100, achieving 70.94% test accuracy across 100 classes with the same architecture and training procedure, demonstrating that 4-bit training from scratch generalizes to harder classification tasks. Both experiments achieve 8x memory compression over FP32 while maintaining exactly 15 unique weight values per layer throughout training. We additionally validate hardware independence by demonstrating rapid convergence on a consumer mobile device (OnePlus 9R), achieving 83.16% accuracy in only 6 epochs. To the best of our knowledge, no prior work has demonstrated 4-bit quantization-aware training achieving full-precision parity on standard CPU hardware without specialized kernels or post-training quantization. --- ### Discriminative Flow Matching Via Local Generative Predictors Authors: Om Govind Jha, Manoj Bamniya, Ayon Borthakur Published: 2026-03-14 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.13928v1 Traditional discriminative computer vision relies predominantly on static projections, mapping input features to outputs in a single computational step. Although efficient, this paradigm lacks the iterative refinement and robustness inherent in biological vision and modern generative modelling. In this paper, we propose Discriminative Flow Matching, a framework that reformulates classification and object detection as a conditional transport process. By learning a vector field that continuously transports samples from a simple noise distribution toward a task-aligned target manifold -- such as class embeddings or bounding box coordinates -- we are at the interface between generative and discriminative learning. Our method attaches multiple independent flow predictors to a shared backbone. These predictors are trained using local flow matching objectives, where gradients are computed independently for each block. We formulate this approach for standard image classification and extend it to the complex task of object detection, where targets are high-dimensional and spatially distributed. This architecture provides the flexibility to update blocks either sequentially to minimise activation memory or in parallel to suit different hardware constraints. By aggregating the predictions from these independent flow predictors, our framework enables robust, generative-inspired inference across diverse architectures, including CNNs and vision transformers. --- ### Close to Reality: Interpretable and Feasible Data Augmentation for Imbalanced Learning Authors: Matheus Camilo da Silva, Gabriel Gustavo Costanzo, Andrea de Lorenzo, Sylvio Barbon Junior Published: 2026-03-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.13927v1 Many machine learning classification tasks involve imbalanced datasets, which are often subject to over-sampling techniques aimed at improving model performance. However, these techniques are prone to generating unrealistic or infeasible samples. Furthermore, they often function as black boxes, lacking interpretability in their procedures. This opacity makes it difficult to track their effectiveness and provide necessary adjustments, and they may ultimately fail to yield significant performance improvements. To bridge this gap, we introduce the Decision Predicate Graphs for Data Augmentation (DPG-da), a framework that extracts interpretable decision predicates from trained models to capture domain rules and enforce them during sample generation. This design ensures that over-sampled data remain diverse, constraint-satisfying, and interpretable. In experiments on synthetic and real-world benchmark datasets, DPG-da consistently improves classification performance over traditional over-sampling methods, while guaranteeing logical validity and offering clear, interpretable explanations of the over-sampled data. --- ### SmoothVLA: Aligning Vision-Language-Action Models with Physical Constraints via Intrinsic Smoothness Optimization Authors: Jiashun Li, Xiaoyu Shi, Hong Xie, Mingsheng Shang, Yun Lu Published: 2026-03-14 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2603.13925v1 Vision-Language-Action (VLA) models have emerged as a powerful paradigm for robotic manipulation. However, existing post-training methods face a dilemma between stability and exploration: Supervised Fine-Tuning (SFT) is constrained by demonstration quality and lacks generalization, whereas Reinforcement Learning (RL) improves exploration but often induces erratic, jittery trajectories that violate physical constraints. To bridge this gap, we propose SmoothVLA, a novel reinforcement learning fine-tuning framework that synergistically optimizes task performance and motion smoothness. The technical core is a physics-informed hybrid reward function that integrates binary sparse task rewards with a continuous dense term derived from trajectory jerk. Crucially, this reward is intrinsic, that computing directly from policy rollouts, without requiring extrinsic environment feedback or laborious reward engineering. Leveraging the Group Relative Policy Optimization (GRPO), SmoothVLA establishes trajectory smoothness as an explicit optimization prior, guiding the model toward physically feasible and stable control. Extensive experiments on the LIBERO benchmark demonstrate that SmoothVLA outperforms standard RL by 13.8\% in smoothness and significantly surpasses SFT in generalization across diverse tasks. Our work offers a scalable approach to aligning VLA models with physical-world constraints through intrinsic reward optimization. --- ### Generative Inverse Design of Cold Metals for Low-Power Electronics Authors: Kedeng Wu, Yucheng Zhu, Yan Chen, Bizhu Zhang, Shuyu Liu, Xiaobin Deng, Yabei Wu, Liangliang Zhu, Hang Xiao Published: 2026-03-14 Categories: cond-mat.mtrl-sci, cs.LG arXiv: https://arxiv.org/abs/2603.13920v1 Cold metals are a class of metals with an intrinsic energy gap located close to the Fermi level, which enables cold-carrier injection for steep-slope transistors and is therefore promising for low-power electronic applications. High-throughput screening has revealed 252 three-dimensional (3D) cold metals in the Materials Project database, but database searches are inherently limited to known compounds. Here we present an inverse-design workflow that generates 3D cold metals using MatterGPT, a conditional autoregressive Transformer trained on SLICES, an invertible and symmetry-invariant crystal string representation. We curate a training set of 26,309 metallic structures labeled with energy above hull and a unified band-edge distance descriptor that merges p-type and n-type cold-metal characteristics to address severe label imbalance. Property-conditioned generation targeting thermodynamic stability and 50-500 meV band-edge distances produces 148,506 unique candidates; 92.1% are successfully reconstructed to 3D structures and down-selected by symmetry, uniqueness and novelty filters, followed by high-throughput DFT validation. We identify 257 cold metals verified as novel with respect to the Materials Project database, with gaps around the Fermi level spanning 50-500 meV. First-principles phonon, electronic-structure, and work-function calculations for representative candidates confirm dynamical stability and contact-relevant work functions. Our results demonstrate that SLICES-enabled generative transformers can expand the chemical space of cold metals beyond high-throughput screening, providing a route to low-power electronic materials discovery. --- ### OpenCOOD-Air: Prompting Heterogeneous Ground-Air Collaborative Perception with Spatial Conversion and Offset Prediction Authors: Xianke Wu, Songlin Bai, Chengxiang Li, Zhiyao Luo, Yulin Tian, Fenghua Zhu, Yisheng Lv, Yonglin Tian Published: 2026-03-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.13919v1 While Vehicle-to-Vehicle (V2V) collaboration extends sensing ranges through multi-agent data sharing, its reliability remains severely constrained by ground-level occlusions and the limited perspective of chassis-mounted sensors, which often result in critical perception blind spots. We propose OpenCOOD-Air, a novel framework that integrates UAVs as extensible platforms into V2V collaborative perception to overcome these constraints. To mitigate gradient interference from ground-air domain gaps and data sparsity, we adopt a transfer learning strategy to fine-tune UAV weights from pre-trained V2V models. To prevent the spatial information loss inherent in this transition, we formulate ground-air collaborative perception as a heterogeneous integration task with explicit altitude supervision and introduce a Cross-Domain Spatial Converter (CDSC) and a Spatial Offset Prediction Transformer (SOPT). Furthermore, we present the OPV2V-Air benchmark to validate the transition from V2V to Vehicle-to-Vehicle-to-UAV. Compared to state-of-the-art methods, our approach improves 2D and 3D AP@0.7 by 4% and 7%, respectively. --- ### Evaluation of Visual Place Recognition Methods for Image Pair Retrieval in 3D Vision and Robotics Authors: Dennis Haitz, Athradi Shritish Shetty, Michael Weinmann, Markus Ulrich Published: 2026-03-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.13917v1 Visual Place Recognition (VPR) is a core component in computer vision, typically formulated as an image retrieval task for localization, mapping, and navigation. In this work, we instead study VPR as an image pair retrieval front-end for registration pipelines, where the goal is to find top-matching image pairs between two disjoint image sets for downstream tasks such as scene registration, SLAM, and Structure-from-Motion. We comparatively evaluate state-of-the-art VPR families - NetVLAD-style baselines, classification-based global descriptors (CosPlace, EigenPlaces), feature-mixing (MixVPR), and foundation-model-driven methods (AnyLoc, SALAD, MegaLoc) - on three challenging datasets: object-centric outdoor scenes (Tanks and Temples), indoor RGB-D scans (ScanNet-GS), and autonomous-driving sequences (KITTI). We show that modern global descriptor approaches are increasingly suitable as off-the-shelf image pair retrieval modules in challenging scenarios including perceptual aliasing and incomplete sequences, while exhibiting clear, domain-dependent strengths and weaknesses that are critical when choosing VPR components for robust mapping and registration. --- ### Towards Stable Self-Supervised Object Representations in Unconstrained Egocentric Video Authors: Yuting Tan, Xilong Cheng, Yunxiao Qin, Zhengnan Li, Jingjing Zhang Published: 2026-03-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.13912v1 Humans develop visual intelligence through perceiving and interacting with their environment - a self-supervised learning process grounded in egocentric experience. Inspired by this, we ask how can artificial systems learn stable object representations from continuous, uncurated first-person videos without relying on manual annotations. This setting poses challenges of separating, recognizing, and persistently tracking objects amid clutter, occlusion, and ego-motion. We propose EgoViT, a unified vision Transformer framework designed to learn stable object representations from unlabeled egocentric video. EgoViT bootstraps this learning process by jointly discovering and stabilizing "proto-objects" through three synergistic mechanisms: (1) Proto-object Learning, which uses intra-frame distillation to form discriminative representations; (2) Depth Regularization, which grounds these representations in geometric structure; and (3) Teacher-Filtered Temporal Consistency, which enforces identity over time. This creates a virtuous cycle where initial object hypotheses are progressively refined into stable, persistent representations. The framework is trained end-to-end on unlabeled first-person videos and exhibits robustness to geometric priors of varied origin and quality. On standard benchmarks, EgoViT achieves +8.0% CorLoc improvement in unsupervised object discovery and +4.8% mIoU improvement in semantic segmentation, demonstrating its potential to lay a foundation for robust visual abstraction in embodied intelligence. --- ### The Phenomenology of Hallucinations Authors: Valeria Ruscio, Keiran Thompson Published: 2026-03-14 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.13911v1 We show that language models hallucinate not because they fail to detect uncertainty, but because of a failure to integrate it into output generation. Across architectures, uncertain inputs are reliably identified, occupying high-dimensional regions with 2-3$\times$ the intrinsic dimensionality of factual inputs. However, this internal signal is weakly coupled to the output layer: uncertainty migrates into low-sensitivity subspaces, becoming geometrically amplified yet functionally silent. Topological analysis shows that uncertainty representations fragment rather than converging to a unified abstention state, while gradient and Fisher probes reveal collapsing sensitivity along the uncertainty direction. Because cross-entropy training provides no attractor for abstention and uniformly rewards confident prediction, associative mechanisms amplify these fractured activations until residual coupling forces a committed output despite internal detection. Causal interventions confirm this account by restoring refusal when uncertainty is directly connected to logits. --- ### Scene Generation at Absolute Scale: Utilizing Semantic and Geometric Guidance From Text for Accurate and Interpretable 3D Indoor Scene Generation Authors: Stefan Ainetter, Thomas Deixelberger, Edoardo A. Dominici, Philipp Drescher, Konstantinos Vardis, Markus Steinberger Published: 2026-03-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.13910v2 We present GuidedSceneGen, a text-to-3D generation framework that produces metrically accurate, globally consistent, and semantically interpretable indoor scenes. Unlike prior text-driven methods that often suffer from geometric drift or scale ambiguity, our approach maintains an absolute world coordinate frame throughout the entire generation process. Starting from a textual scene description, we predict a global 3D layout encoding both semantic and geometric structure, which serves as a guiding proxy for downstream stages. A semantics- and depth-conditioned panoramic diffusion model then synthesizes 360° imagery aligned with the global layout, substantially improving spatial coherence. To explore unobserved regions, we employ a video diffusion model guided by optimized camera trajectories that balances coverage and collision avoidance, achieving up to 10x faster sampling compared to exhaustive path exploration. The generated views are fused using 3D Gaussian Splatting, yielding a consistent and fully navigable 3D scene in absolute scale. GuidedSceneGen enables accurate transfer of object poses and semantic labels from layout to reconstruction, and supports progressive scene expansion without re-alignment. Quantitative results and a user study demonstrate greater 3D consistency and layout plausibility compared to recent panoramic text-to-3D baselines. --- ### FedPBS: Proximal-Balanced Scaling Federated Learning Model for Robust Personalized Training for Non-IID Data Authors: Eman M. AbouNassar, Amr Elshall, Sameh Abdulah Published: 2026-03-14 Categories: cs.LG, cs.AI, cs.DC arXiv: https://arxiv.org/abs/2603.13909v2 Federated learning (FL) enables a set of distributed clients to jointly train machine learning models while preserving their local data privacy, making it attractive for applications in healthcare, finance, mobility, and smart-city systems. However, FL faces several challenges, including statistical heterogeneity and uneven client participation, which can degrade convergence and model quality. In this work, we propose FedPBS, an FL algorithm that couples complementary ideas from FedBS and FedProx to address these challenges. FedPBS dynamically adapts batch sizes to client resources to support balanced and scalable participation, and selectively applies a proximal correction to small-batch clients to stabilize local updates and reduce divergence from the global model. Experiments on benchmarking datasets such as CIFAR-10 and UCI-HAR under highly non-IID settings demonstrate that FedPBS consistently outperforms state-of-the-art methods, including FedBS, FedGA, MOON, and FedProx. The results demonstrate robust performance gains under extreme data heterogeneity, with smooth loss curves indicating stable convergence across diverse federated environments. FedPBS consistently outperforms state-of-the-art federated learning baselines on UCI-HAR and CIFAR-10 under severe non-IID conditions while maintaining stable and reliable convergence. --- ### LineMaster Pro: A Low-Cost Intelligent Line Following Robot with PID Control and Ultrasonic Obstacle Avoidance for Educational Robotics Authors: Jeni Shahi, Abhishek Shah, A. S. M. Ahsanul Sarkar Akib Published: 2026-03-14 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2603.13907v1 Line following robots are fundamental platforms in robotics education, yet commercially available solutions remain prohibitively expensive ($150-300$) while lacking integrated obstacle detection capabilities essential for real-world applications. This paper presents LineMaster Pro, an intelligent low-cost line following robot implemented on an Arduino Nano platform that integrates dual TCRT5000 infrared sensors for precision line tracking, an HC-SR04 ultrasonic sensor for real-time obstacle detection, a digitally tuned PID controller with Ziegler-Nichols optimization, and a hierarchical finite state machine for robust obstacle avoidance. A systematic four-phase sensor calibration methodology ensures reliable operation across varying lighting and surface conditions. Experimental validation through 200 controlled trials and 72-hour continuous operation demonstrates mean tracking accuracy of 1.18 cm at 0.4 m/s (95\% CI (1.06, 1.30)), obstacle detection reliability of 96.7\% within 10-40 cm range with 0.7\% false positive rate, and 94\% successful recovery from path deviations. The PID implementation achieves 43\% improvement over conventional on-off control ($p<0.001$). At a total hardware cost of \$28.50 based on verified Bangladesh market prices, LineMaster Pro achieves a 94\% cost reduction compared to commercial alternatives, establishing a practical benchmark for accessible robotics education in resource-constrained environments. --- ### Pixel-level Scene Understanding in One Token: Visual States Need What-is-Where Composition Authors: Seokmin Lee, Yunghee Lee, Byeonghyun Pak, Byeongju Woo Published: 2026-03-14 Categories: cs.CV, cs.AI, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2603.13904v2 For robotic agents operating in dynamic environments, learning visual state representations from streaming video observations is essential for sequential decision making. Recent self-supervised learning methods have shown strong transferability across vision tasks, but they do not explicitly address what a good visual state should encode. We argue that effective visual states must capture what-is-where by jointly encoding the semantic identities of scene elements and their spatial locations, enabling reliable detection of subtle dynamics across observations. To this end, we propose CroBo, a visual state representation learning framework based on a global-to-local reconstruction objective. Given a reference observation compressed into a compact bottleneck token, CroBo learns to reconstruct heavily masked patches in a local target crop from sparse visible cues, using the global bottleneck token as context. This learning objective encourages the bottleneck token to encode a fine-grained representation of scene-wide semantic entities, including their identities, spatial locations, and configurations. As a result, the learned visual states reveal how scene elements move and interact over time, supporting sequential decision making. We evaluate CroBo on diverse vision-based robot policy learning benchmarks, where it achieves state-of-the-art performance. Reconstruction analyses and perceptual straightness experiments further show that the learned representations preserve pixel-level scene composition and encode what-moves-where across observations. Project page available at: https://seokminlee-chris.github.io/CroBo-ProjectPage. --- ### Distributed Acoustic Sensing for Urban Traffic Monitoring: Spatio-Temporal Attention in Recurrent Neural Networks Authors: Izhan Fakhruzi, Manuel Titos, Carmen Benítez, Luz García Published: 2026-03-14 Categories: cs.LG, cs.SD arXiv: https://arxiv.org/abs/2603.13903v1 Effective urban traffic monitoring is essential for improving mobility, enhancing safety, and supporting sustainable cities. Distributed Acoustic Sensing (DAS) enables large-scale traffic observation by transforming existing fiber-optic infrastructure into dense arrays of vibration sensors. However, modeling the high-resolution spatio-temporal structure of DAS data for reliable traffic event recognition remains challenging. This study presents a real-world DAS-based traffic monitoring experiment conducted in Granada, Spain, where vehicles cross a fiber deployed perpendicular to the roadway. Recurrent neural networks (RNNs) are employed to model intra- and inter-event temporal dependencies. Spatial and temporal attention mechanisms are systematically integrated within the RNN architecture to analyze their impact on recognition performance, parameter efficiency, and interpretability. Results show that an appropriate and complementary placement of attention modules improves the balance between accuracy and model complexity. Attention heatmaps provide physically meaningful interpretations of classification decisions by highlighting informative spatial locations and temporal segments. Furthermore, the proposed SA-bi-TA configuration demonstrates spatial transferability, successfully recognizing traffic events at sensing locations different from those used during training, with only moderate performance degradation. These findings support the development of scalable and interpretable DAS-based traffic monitoring systems capable of operating under heterogeneous urban sensing conditions. --- ### CT-Conditioned Diffusion Prior with Physics-Constrained Sampling for PET Super-Resolution Authors: Liutao Yang, Zi Wang, Peiyuan Jing, Xiaowen Wang, Javier A. Montoya-Zegarra, Kuangyu Shi, Daoqiang Zhang, Guang Yang Published: 2026-03-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.13901v1 PET super-resolution is highly under-constrained because paired multi-resolution scans from the same subject are rarely available, and effective resolution is determined by scanner-specific physics (e.g., PSF, detector geometry, and acquisition settings). This limits supervised end-to-end training and makes purely image-domain generative restoration prone to hallucinated structures when anatomical and physical constraints are weak. We formulate PET super-resolution as posterior inference under heterogeneous system configurations and propose a CT-conditioned diffusion framework with physics-constrained sampling. During training, a conditional diffusion prior is learned from high-quality PET/CT pairs using cross-attention for anatomical guidance, without requiring paired LR--HR PET data. During inference, measurement consistency is enforced through a scanner-aware forward model with explicit PSF effects and gradient-based data-consistency refinement. Under both standard and OOD settings, the proposed method consistently improves experimental metrics and lesion-level clinical relevance indicators over strong baselines, while reducing hallucination artifacts and improving structural fidelity. --- ### MO-SAE:Multi-Objective Stacked Autoencoders Optimization for Edge Anomaly Detection Authors: Lizhao Zhang, Shengsong Kong, Tao Guo, Shaobo Li, Zhenzhou Ji Published: 2026-03-14 Categories: cs.NE, cs.LG arXiv: https://arxiv.org/abs/2603.13895v1 Stacked AutoEncoders (SAE) have been widely adopted in edge anomaly detection scenarios. However, the resource-intensive nature of SAE can pose significant challenges for edge devices, which are typically resource-constrained and must adapt rapidly to dynamic and changing conditions. Optimizing SAE to meet the heterogeneous demands of real-world deployment scenarios, including high performance under constrained storage, low power consumption, fast inference, and efficient model updates, remains a substantial challenge. To address this, we propose an integrated optimization framework that jointly considers these critical factors to achieve balanced and adaptive system-level optimization. Specifically, we formulate SAE optimization for edge anomaly detection as a multi-objective optimization problem and propose MO-SAE (Multi-Objective Stacked AutoEncoders). The multiple objectives are addressed by integrating model clipping, multi-branch exit design, and a matrix approximation technique. In addition, a multi-objective heuristic algorithm is employed to effectively balance the competing objectives in SAE optimization. Our results demonstrate that the proposed MO-SAE delivers substantial improvements over the original approach. On the x86 architecture, it reduces storage space and power consumption by at least 50%, improves runtime efficiency by no less than 28%, and achieves an 11.8% compression rate, all while maintaining application performance. Furthermore, MO-SAE runs efficiently on edge devices with ARM architecture. Experimental results show a 15% improvement in inference speed, facilitating efficient deployment in cloud-edge collaborative anomaly detection systems. --- ### Robust Self-Training with Closed-loop Label Correction for Learning from Noisy Labels Authors: Zhanhui Lin, Yanlin Liu, Sanping Zhou Published: 2026-03-14 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2603.13894v1 Training deep neural networks with noisy labels remains a significant challenge, often leading to degraded performance. Existing methods for handling label noise typically rely on either transition matrix, noise detection, or meta-learning techniques, but they often exhibit low utilization efficiency of noisy samples and incur high computational costs. In this paper, we propose a self-training label correction framework using decoupled bilevel optimization, where a classifier and neural correction function co-evolve. Leveraging a small clean dataset, our method employs noisy posterior simulation and intermediate features to transfer ground-truth knowledge, forming a closed-loop feedback system that prevents error amplification. Theoretical guarantees underpin the stability of our approach, and extensive experiments on benchmark datasets like CIFAR and Clothing1M confirm state-of-the-art performance with reduced training time, highlighting its practical applicability for learning from noisy labels. --- ### UVLM: A Universal Vision-Language Model Loader for Reproducible Multimodal Benchmarking Authors: Joan Perez, Giovanni Fusco Published: 2026-03-14 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2603.13893v1 Vision-Language Models (VLMs) have emerged as powerful tools for image understanding tasks, yet their practical deployment remains hindered by significant architectural heterogeneity across model families. This paper introduces UVLM (Universal Vision-Language Model Loader), a Google Colab-based framework that provides a unified interface for loading, configuring, and benchmarking multiple VLM architectures on custom image analysis tasks. UVLM currently supports two major model families -- LLaVA-NeXT and Qwen2.5-VL -- which differ fundamentally in their vision encoding, tokenization, and decoding strategies. The framework abstracts these differences behind a single inference function, enabling researchers to compare models using identical prompts and evaluation protocols. Key features include a multi-task prompt builder with support for four response types (numeric, category, boolean, text), a consensus validation mechanism based on majority voting across repeated inferences, a flexible token budget (up to 1,500 tokens) enabling users to design custom reasoning strategies through prompt engineering, and a built-in chain-of-thought reference mode for benchmarking. UVLM is designed for reproducibility, accessibility, and extensibility and as such is freely deployable on Google Colab using consumer-grade GPU resources. The paper also presents the first benchmarking of different VLMs on tasks of increasing reasoning complexity using a corpus of 120 street-view images. --- ### Large Language Models Reproduce Racial Stereotypes When Used for Text Annotation Authors: Petter Törnberg Published: 2026-03-14 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.13891v2 Large language models (LLMs) are increasingly used for automated text annotation in tasks ranging from academic research to content moderation and hiring. Across 19 LLMs and two experiments totaling more than 4 million annotation judgments, we show that subtle identity cues embedded in text systematically bias annotation outcomes in ways that mirror racial stereotypes. In a names-based experiment spanning 39 annotation tasks, texts containing names associated with Black individuals are rated as more aggressive by 18 of 19 models and more gossipy by 18 of 19. Asian names produce a bamboo-ceiling profile: 17 of 19 models rate individuals as more intelligent, while 18 of 19 rate them as less confident and less sociable. Arab names elicit cognitive elevation alongside interpersonal devaluation, and all four minority groups are consistently rated as less self-disciplined. In a matched dialect experiment, the same sentence is judged significantly less professional (all 19 models, mean gap $-0.774$), less indicative of an educated speaker ($-0.688$), more toxic (18/19), and more angry (19/19) when written in African American Vernacular English rather than Standard American English. A notable exception occurs for name-based hireability, where fine-tuning appears to overcorrect, systematically favoring minority-named applicants. These findings suggest that using LLMs as automated annotators can embed socially patterned biases directly into the datasets and measurements that increasingly underpin research, governance, and decision-making. --- ### Large Language Models Reproduce Racial Stereotypes When Used for Text Annotation Authors: Petter Törnberg Published: 2026-03-14 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.13891v1 Large language models (LLMs) are increasingly used for automated text annotation in tasks ranging from academic research to content moderation and hiring. Across 19 LLMs and two experiments totaling more than 4 million annotation judgments, we show that subtle identity cues embedded in text systematically bias annotation outcomes in ways that mirror racial stereotypes. In a names-based experiment spanning 39 annotation tasks, texts containing names associated with Black individuals are rated as more aggressive by 18 of 19 models and more gossipy by 18 of 19. Asian names produce a bamboo-ceiling profile: 17 of 19 models rate individuals as more intelligent, while 18 of 19 rate them as less confident and less sociable. Arab names elicit cognitive elevation alongside interpersonal devaluation, and all four minority groups are consistently rated as less self-disciplined. In a matched dialect experiment, the same sentence is judged significantly less professional (all 19 models, mean gap $-0.774$), less indicative of an educated speaker ($-0.688$), more toxic (18/19), and more angry (19/19) when written in African American Vernacular English rather than Standard American English. A notable exception occurs for name-based hireability, where fine-tuning appears to overcorrect, systematically favoring minority-named applicants. These findings suggest that using LLMs as automated annotators can embed socially patterned biases directly into the datasets and measurements that increasingly underpin research, governance, and decision-making. --- ### Multi-Modal Character Localization and Extraction for Chinese Text Recognition Authors: Qilong Li, Chongsheng Zhang Published: 2026-03-14 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.13886v1 Scene text recognition (STR) methods have demonstrated their excellent capability in English text images. However, due to the complex inner structures of Chinese and the extensive character categories, it poses challenges for recognizing Chinese text in images. Recently, studies have shown that the methods designed for English text recognition encounter an accuracy bottleneck when recognizing Chinese text images. This raises the question: Is it appropriate to apply the model developed for English to the Chinese STR task? To explore this issue, we propose a novel method named LER, which explicitly decouples each character and independently recognizes characters while taking into account the complex inner structures of Chinese. LER consists of three modules: Localization, Extraction, and Recognition. Firstly, the localization module utilizes multimodal information to determine the character's position precisely. Then, the extraction module dissociates all characters in parallel. Finally, the recognition module considers the unique inner structures of Chinese to provide the text prediction results. Extensive experiments conducted on large-scale Chinese benchmarks indicate that our method significantly outperforms existing methods. Furthermore, extensive experiments conducted on six English benchmarks and the Union14M benchmark show impressive results in English text recognition by LER. Code is available at https://github.com/Pandarenlql/LER. --- ### SCoCCA: Multi-modal Sparse Concept Decomposition via Canonical Correlation Analysis Authors: Ehud Gordon, Meir Yossef Levi, Guy Gilboa Published: 2026-03-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.13884v1 Interpreting the internal reasoning of vision-language models is essential for deploying AI in safety-critical domains. Concept-based explainability provides a human-aligned lens by representing a model's behavior through semantically meaningful components. However, existing methods are largely restricted to images and overlook the cross-modal interactions. Text-image embeddings, such as those produced by CLIP, suffer from a modality gap, where visual and textual features follow distinct distributions, limiting interpretability. Canonical Correlation Analysis (CCA) offers a principled way to align features from different distributions, but has not been leveraged for multi-modal concept-level analysis. We show that the objectives of CCA and InfoNCE are closely related, such that optimizing CCA implicitly optimizes InfoNCE, providing a simple, training-free mechanism to enhance cross-modal alignment without affecting the pre-trained InfoNCE objective. Motivated by this observation, we couple concept-based explainability with CCA, introducing Concept CCA (CoCCA), a framework that aligns cross-modal embeddings while enabling interpretable concept decomposition. We further extend it and propose Sparse Concept CCA (SCoCCA), which enforces sparsity to produce more disentangled and discriminative concepts, facilitating improved activation, ablation, and semantic manipulation. Our approach generalizes concept-based explanations to multi-modal embeddings and achieves state-of-the-art performance in concept discovery, evidenced by reconstruction and manipulation tasks such as concept ablation. --- ### Benchmarking the Energy Cost of Assurance in Neuromorphic Edge Robotics Authors: Sylvester Kaczmarek Published: 2026-03-14 Categories: cs.NE, cs.AR, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2603.13880v1 Deploying trustworthy artificial intelligence on edge robotics imposes a difficult trade-off between high-assurance robustness and energy sustainability. Traditional defense mechanisms against adversarial attacks typically incur significant computational overhead, threatening the viability of power-constrained platforms in environments such as cislunar space. This paper quantifies the energy cost of assurance in event-driven neuromorphic systems. We benchmark the Hierarchical Temporal Defense (HTD) framework on the BrainChip Akida AKD1000 processor against a suite of adversarial temporal attacks. We demonstrate that unlike traditional deep learning defenses which often degrade efficiency significantly with increased robustness, the event-driven nature of the proposed architecture achieves a superior trade-off. The system reduces gradient-based adversarial success rates from 82.1% to 18.7% and temporal jitter success rates from 75.8% to 25.1%, while maintaining an energy consumption of approximately 45 microjoules per inference. We report a counter-intuitive reduction in dynamic power consumption in the fully defended configuration, attributed to volatility-gated plasticity mechanisms that induce higher network sparsity. These results provide empirical evidence that neuromorphic sparsity enables sustainable and high-assurance edge autonomy. --- ### Dual-Strategy Improvement of YOLOv11n for Multi-Scale Object Detection in Remote Sensing Images Authors: Shuaiyu Zhu, Sergey Ablameyko Published: 2026-03-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.13879v1 Satellite remote sensing images pose significant challenges for object detection due to their high resolution, complex scenes, and large variations in target scales. To address the insufficient detection accuracy of the YOLOv11n model in remote sensing imagery, this paper proposes two improvement strategies. Method 1: (a) a Large Separable Kernel Attention (LSKA) mechanism is introduced into the backbone network to enhance feature extraction for small objects; (b) a Gold-YOLO structure is incorporated into the neck network to achieve multi-scale feature fusion, thereby improving the detection performance of objects at different scales. Method 2: (a) the Gold-YOLO structure is also integrated into the neck network; (b) a MultiSEAMHead detection head is combined to further strengthen the representation and detection capability for small and multi-scale objects. To verify the effectiveness of the proposed improvements, experiments are conducted on the DOTAv1 dataset. The results show that, while maintaining the lightweight advantage of the model, the proposed methods improve detection accuracy (mAP@0.5) by 1.3% and 1.8%, respectively, compared with the baseline YOLOv11n, demonstrating the effectiveness and practical value of the proposed approaches for object detection in remote sensing images. --- ### Step-CoT: Stepwise Visual Chain-of-Thought for Medical Visual Question Answering Authors: Lin Fan, Yafei Ou, Zhipeng Deng, Pengyu Dai, Hou Chongxian, Jiale Yan, Yaqian Li, Kaiwen Long, Xun Gong, Masayuki Ikebe, Yefeng Zheng Published: 2026-03-14 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.13878v1 Chain-of-thought (CoT) reasoning has advanced medical visual question answering (VQA), yet most existing CoT rationales are free-form and fail to capture the structured reasoning process clinicians actually follow. This work asks: Can traceable, multi-step reasoning supervision improve reasoning accuracy and the interpretability of Medical VQA? To this end, we introduce Step-CoT, a large-scale medical reasoning dataset with expert-curated, structured multi-step CoT aligned to clinical diagnostic workflows, implicitly grounding the model's reasoning in radiographic evidence. Step-CoT comprises more than 10K real clinical cases and 70K VQA pairs organized around diagnostic workflows, providing supervised intermediate steps that guide models to follow valid reasoning trajectories. To effectively learn from Step-CoT, we further introduce a teacher-student framework with a dynamic graph-structured focusing mechanism that prioritizes diagnostically informative steps while filtering out less relevant contexts. Our experiments show that using Step-CoT can improve reasoning accuracy and interpretability. Benchmark: github.com/hahaha111111/Step-CoT. Dataset Card: huggingface.co/datasets/fl-15o/Step-CoT --- ### Scribe Verification in Chinese manuscripts using Siamese, Triplet, and Vision Transformer Neural Networks Authors: Dimitrios-Chrysovalantis Liakopoulos, Yanbo Zhang, Chongsheng Zhang, Constantine Kotropoulos Published: 2026-03-14 Categories: cs.LG, eess.IV arXiv: https://arxiv.org/abs/2603.13877v1 The paper examines deep learning models for scribe verification in Chinese manuscripts. That is, to automatically determine whether two manuscript fragments were written by the same scribe using deep metric learning methods. Two datasets were used: the Tsinghua Bamboo Slips Dataset and a selected subset of the Multi-Attribute Chinese Calligraphy Dataset, focusing on the calligraphers with a large number of samples. Siamese and Triplet neural network architectures are implemented, including convolutional and Transformer-based models. The experimental results show that the MobileNetV3+ Custom Siamese model trained with contrastive loss achieves either the best or the second-best overall accuracy and area under the Receiver Operating Characteristic Curve on both datasets. --- ### GradMem: Learning to Write Context into Memory with Test-Time Gradient Descent Authors: Yuri Kuratov, Matvey Kairov, Aydar Bulatov, Ivan Rodkin, Mikhail Burtsev Published: 2026-03-14 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.13875v2 Many large language model applications require conditioning on long contexts. Transformers typically support this by storing a large per-layer KV-cache of past activations, which incurs substantial memory overhead. A desirable alternative is compressive memory: read a context once, store it in a compact state, and answer many queries from that state. We study this in a context removal setting, where the model must generate an answer without access to the original context at inference time. We introduce GradMem, which writes context into memory via per-sample test-time optimization. Given a context, GradMem performs a few steps of gradient descent on a small set of prefix memory tokens while keeping model weights frozen. GradMem explicitly optimizes a model-level self-supervised context reconstruction loss, resulting in a loss-driven write operation with iterative error correction, unlike forward-only methods. On associative key--value retrieval, GradMem outperforms forward-only memory writers with the same memory size, and additional gradient steps scale capacity much more effectively than repeated forward writes. We further show that GradMem transfers beyond synthetic benchmarks: with pretrained language models, it attains competitive results on natural language tasks including bAbI and SQuAD variants, relying only on information encoded in memory. --- ### Zero-Forgetting CISS via Dual-Phase Cognitive Cascades Authors: Yuquan Lu, Yifu Guo, Zishan Xu, Siyu Zhang, Yu Huo, Siyue Chen, Siyan Wu, Chenghua Zhu, Ruixuan Wang Published: 2026-03-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.13874v1 Continual semantic segmentation (CSS) is a cornerstone task in computer vision that enables a large number of downstream applications, but faces the catastrophic forgetting challenge. In conventional class-incremental semantic segmentation (CISS) frameworks using Softmax-based classification heads, catastrophic forgetting originates from Catastrophic forgetting and task affiliation probability. We formulate these problems and provide a theoretical analysis to more deeply understand the limitations in existing CISS methods, particularly Strict Parameter Isolation (SPI). To address these challenges, we follow a dual-phase intuition from human annotators, and introduce Cognitive Cascade Segmentation (CogCaS), a novel dual-phase cascade formulation for CSS tasks in the CISS setting. By decoupling the task into class-existence detection and class-specific segmentation, CogCaS enables more effective continual learning, preserving previously learned knowledge while incorporating new classes. Using two benchmark datasets PASCAL VOC 2012 and ADE20K, we have shown significant improvements in a variety of challenging scenarios, particularly those with long sequence of incremental tasks, when compared to exsiting state-of-the-art methods. Our code will be made publicly available upon paper acceptance. --- ### On Interpolation Formulas Describing Neural Network Generalization Authors: Jin Guo, Roy Y. He, Jean-Michel Morel Published: 2026-03-14 Categories: cs.LG, math.DS arXiv: https://arxiv.org/abs/2603.13872v1 In 2020 Domingos introduced an interpolation formula valid for "every model trained by gradient descent". He concluded that such models behave approximately as kernel machines. In this work, we extend the Domingos formula to stochastic training. We introduce a stochastic gradient kernel that extends the deterministic version via a continuous-time diffusion approximation. We prove stochastic Domingos theorems and show that the expected network output admits a kernel-machine representation with optimizer-specific weighting. It reveals that training samples contribute through loss-dependent weights and gradient alignment along the training trajectory. We then link the generalization error to the null space of the integral operator induced by the stochastic gradient kernel. The same path-kernel viewpoint provides a unified interpretation of diffusion models and GANs: diffusion induces stage-wise, noise-localized corrections, whereas GANs induce distribution-guided corrections shaped by discriminator geometry. We visualize the evolution of implicit kernels during optimization and quantify out-of-distribution behaviors through a series of numerical experiments. Our results support a feature-space memory view of learning: training stores data-dependent information in an evolving tangent feature geometry, and predictions at test time arise from kernel-weighted retrieval and aggregation of these stored features, with generalization governed by alignment between test points and the learned feature memory. --- ### TransDex: Pre-training Visuo-Tactile Policy with Point Cloud Reconstruction for Dexterous Manipulation of Transparent Objects Authors: Fengguan Li, Yifan Ma, Chen Qian, Wentao Rao, Weiwei Shang Published: 2026-03-14 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2603.13869v2 Dexterous manipulation enables complex tasks but suffers from self-occlusion, severe depth noise, and depth information loss when manipulating transparent objects. To solve this problem, this paper proposes TransDex, a 3D visuo-tactile fusion motor policy based on point cloud reconstruction pre-training. Specifically, we first propose a self-supervised point cloud reconstruction pre-training approach based on Transformer. This method accurately recovers the 3D structure of objects from interactive point clouds of dexterous hands, even when random noise and large-scale masking are added. Building on this, TransDex is constructed in which perceptual encoding adopts a fine-grained hierarchical scheme and multi-round attention mechanisms adaptively fuse features of the robotic arm and dexterous hand to enable differentiated motion prediction. Results from transparent object manipulation experiments conducted on a real robotic system demonstrate that TransDex outperforms existing baseline methods. Further analysis validates the generalization capabilities of TransDex and the effectiveness of its individual components. --- ### Inevitable Encounters: Backdoor Attacks Involving Lossy Compression Authors: Qian Li, Yunuo Chen, Yuntian Chen Published: 2026-03-14 Categories: cs.CR, cs.CV arXiv: https://arxiv.org/abs/2603.13864v2 Real-world backdoor attacks often require poisoned datasets to be stored and transmitted before being used to compromise deep learning systems. However, in the era of big data, the inevitable use of lossy compression poses a fundamental challenge to invisible backdoor attacks. We find that triggers embedded in RGB images often become ineffective after the images are lossily compressed into binary bitstreams (e.g., JPEG files) for storage and transmission. As a result, the poisoned data lose its malicious effect after compression, causing backdoor injection to fail. In this paper, we highlight the necessity of explicitly accounting for the lossy compression process in backdoor attacks. This requires attackers to ensure that the transmitted binary bitstreams preserve malicious trigger information, so that effective triggers can be recovered in the decompressed data. Building on the region-of-interest (ROI) coding mechanism in image compression, we propose two poisoning strategies tailored to inevitable lossy compression. First, we introduce Universal Attack Activation, a universal method that uses sample-specific ROI masks to reactivate trigger information in binary bitstreams for learned image compression (LIC). Second, we present Compression-Adapted Attack, a new attack strategy that employs customized ROI masks to encode trigger information into binary bitstreams and is applicable to both traditional codecs and LIC. Extensive experiments demonstrate the effectiveness of both strategies. --- ### Geo-ID: Test-Time Geometric Consensus for Cross-View Consistent Intrinsics Authors: Alara Dirik, Stefanos Zafeiriou Published: 2026-03-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.13859v2 Intrinsic image decomposition aims to estimate physically based rendering (PBR) parameters such as albedo, roughness, and metallicity from images. While recent methods achieve strong single-view predictions, applying them independently to multiple views of the same scene often yields inconsistent estimates, limiting their use in downstream applications such as editable neural scenes and 3D reconstruction. Video-based models can improve cross-frame consistency but require dense, ordered sequences and substantial compute, limiting their applicability to sparse, unordered image collections. We propose Geo-ID, a novel test-time framework that repurposes pretrained single-view intrinsic predictors to produce cross-view consistent decompositions by coupling independent per-view predictions through sparse geometric correspondences that form uncertainty-aware consensus targets. Geo-ID is model-agnostic, requires no retraining or inverse rendering, and applies directly to off-the-shelf intrinsic predictors. Experiments on synthetic benchmarks and real-world scenes demonstrate substantial improvements in cross-view intrinsic consistency as the number of views increases, while maintaining comparable single-view decomposition performance. We further show that the resulting consistent intrinsics enable coherent appearance editing and relighting in downstream neural scene representations. --- ### Learning through Creation: A Hash-Free Framework for On-the-Fly Category Discovery Authors: Bohan Zhang, Weidong Tang, Zhixiang Chi, Yi Jin, Zhenbo Li, Yang Wang, Yanan Wu Published: 2026-03-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.13858v2 On-the-Fly Category Discovery (OCD) aims to recognize known classes while simultaneously discovering emerging novel categories during inference, using supervision only from known classes during offline training. Existing approaches rely either on fixed label supervision or on diffusion-based augmentations to enhance the backbone, yet none of them explicitly train the model to perform the discovery task required at test time. It is fundamentally unreasonable to expect a model optimized on limited labeled data to carry out a qualitatively different discovery objective during inference. This mismatch creates a clear optimization misalignment between the offline learning stage and the online discovery stage. In addition, prior methods often depend on hash-based encodings or severe feature compression, which further limits representational capacity. To address these issues, we propose Learning through Creation (LTC), a fully feature-based and hash-free framework that injects novel-category awareness directly into offline learning. At its core is a lightweight, online pseudo-unknown generator driven by kernel-energy minimization and entropy maximization (MKEE). Unlike previous methods that generate synthetic samples once before training, our generator evolves jointly with the model dynamics and synthesizes pseudo-novel instances on the fly at negligible cost. These samples are incorporated through a dual max-margin objective with adaptive thresholding, strengthening the model's ability to delineate and detect unknown regions through explicit creation. Extensive experiments across seven benchmarks show that LTC consistently outperforms prior work, achieving improvements ranging from 1.5 percent to 13.1 percent in all-class accuracy. The code is available at https://github.com/brandinzhang/LTC --- ### OrigamiBench: An Interactive Environment to Synthesize Flat-Foldable Origamis Authors: Naaisha Agarwal, Yihan Wu, Yichang Jian, Yikuan Hu, Nishad Mansoor, Mohan Li, Yifei Peng, Wang-Zhou Dai, Yao-Xiang Ding, Emanuele Sansone Published: 2026-03-14 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2603.13856v2 Building AI systems that can plan, act, and create in the physical world requires more than pattern recognition. Such systems must understand the causal mechanisms and constraints governing physical processes in order to guide sequential decisions. This capability relies on internal representations, analogous to an internal language model, that relate observations, actions, and resulting environmental changes. However, many existing benchmarks treat visual perception and programmatic reasoning as separate problems, focusing either on visual recognition or on symbolic tasks. The domain of origami provides a natural testbed that integrates these modalities. Constructing shapes through folding operations requires visual perception, reasoning about geometric and physical constraints, and sequential planning, while remaining sufficiently structured for systematic evaluation. We introduce OrigamiBench, an interactive benchmark in which models iteratively propose folds and receive feedback on physical validity and similarity to a target configuration. Experiments with modern vision-language models show that scaling model size alone does not reliably produce causal reasoning about physical transformations. Models fail to generate coherent multi-step folding strategies, suggesting that visual and language representations remain weakly integrated. --- ### VFM-Loc: Training-Free Cross-View Geo-Localization via Aligning Discriminative Visual Hierarchies Authors: Jun Lu, Zehao Sang, Haoqi Wei, Xiangyun Liu, Kun Zhu, Haitao Guo, Zhihui Gong, Lei Ding Published: 2026-03-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.13855v2 Cross-View Geo-Localization (CVGL) in remote sensing aims to locate a drone-view query by matching it to geo-tagged satellite images. Although supervised methods have achieved strong results on close-set benchmarks, they often fail to generalize to unconstrained, real-world scenarios due to severe viewpoint differences and dataset bias. To overcome these limitations, we present VFM-Loc, a training-free CVGL framework that leverages the generalizable visual representations from vision foundational models (VFMs). VFM-Loc identifies and matches discriminative visual clues across different viewpoints through a progressive alignment strategy. First, we design a hierarchical clue extraction mechanism using Generalized Mean pooling and Scale-Weighted R-MAC to preserve distinctive visual clues across scales while maintaining hierarchical confidence. Second, we introduce a statistical manifold alignment pipeline based on domain-wise PCA and Orthogonal Procrustes analysis, linearly aligning heterogeneous feature distributions in a shared metric space. Experiments demonstrate that VFM-Loc exhibits high accuracy on standard benchmarks and surpasses supervised methods by over 20\% in Recall@1 on the challenging LO-UCV dataset with large oblique angles. This work highlights that principled alignment of pre-trained features can effectively bridge the cross-view gap, establishing a robust and training-free paradigm for real-world CVGL. The relevant code is made available at: github.com/DingLei14/VFM-Loc. --- ### Power Term Polynomial Algebra for Boolean Logic Authors: Emanuele Sansone, Armando Solar-Lezama Published: 2026-03-14 Categories: cs.LO, cs.AI, cs.SC arXiv: https://arxiv.org/abs/2603.13854v2 We introduce power term polynomial algebra, a representation language for Boolean formulae designed to bridge conjunctive normal form (CNF) and algebraic normal form (ANF). The language is motivated by the tiling mismatch between these representations: direct CNF<->ANF conversion may cause exponential blowup unless formulas are decomposed into smaller fragments, typically through auxiliary variables and side constraints. In contrast, our framework addresses this mismatch within the representation itself, compactly encoding structured families of monomials while representing CNF clauses directly, thereby avoiding auxiliary variables and constraints at the abstraction level. We formalize the language through power terms and power term polynomials, define their semantics, and show that they admit algebraic operations corresponding to Boolean polynomial addition and multiplication. We prove several key properties of the language: disjunctive clauses admit compact canonical representations; power terms support local shortening and expansion rewrite rules; and products of atomic terms can be systematically rewritten within the language. Together, these results yield a symbolic calculus that enables direct manipulation of formulas without expanding them into ordinary ANF. The resulting framework provides a new intermediate representation and rewriting calculus that bridges clause-based and algebraic reasoning and suggests new directions for structure-aware CNF<->ANF conversion and hybrid reasoning methods. --- ### APEX-Searcher: Refining Credit Assignment with Subgoaling for Agentic Retrieval-Augmented Generation Authors: Kun Chen, Qingchao Kong, Zhao Feifei, Wenji Mao Published: 2026-03-14 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.13853v3 Retrieval-augmented generation (RAG) connects large language models (LLMs) to external knowledge, but single-round retrieval is often insufficient for complex multi-hop questions. To enhance search capabilities for complex tasks, most existing works integrate multi-round iterative retrieval with reasoning processes via end-to-end training. While these approaches improve problem-solving performance, they still face challenges in task reasoning and model training, especially ambiguous retrieval execution paths and sparse rewards in end-to-end reinforcement learning (RL), which can lead to inaccurate retrieval results and lower performance. We attribute these failures to hierarchical credit entanglement: a single final reward updates planning and execution together, so the model cannot clearly separate plan errors from retrieval errors. We propose APEX-Searcher, which uses a Refining Credit Assignment paradigm: planning is optimized by RL with a plan-level reward, while execution is learned by SFT. Extensive experiments show consistent gains in both multi-hop RAG and task planning across benchmarks. --- ### Fronto-parietal and fronto-temporal EEG coherence as predictive neuromarkers of transcutaneous auricular vagus nerve stimulation response in treatment-resistant schizophrenia: A machine learning study Authors: Yapeng Cui, Ruoxi Yun, Shumin Zhang, Yi Gong, Zhiqin Li, Ying Chen, Mingbing Su, Dongniya Wu, Jingxia Wu, Qian Wang, Jianan Wang, Qianqian Tian et al. Published: 2026-03-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.13850v1 Response variability limits the clinical utility of transcutaneous auricular vagus nerve stimulation (taVNS) for negative symptoms in treatment-resistant schizophrenia (TRS). This study aimed to develop an electroencephalography (EEG)-based machine learning (ML) model to predict individual response and explore associated neurophysiological mechanisms. We used ML to develop and validate predictive models based on pre-treatment EEG data features (power, coherence, and dynamic functional connectivity) from 50 TRS patients enrolled in the taVNS trial, within a nested cross-validation framework. Participants received 20 sessions of active or sham taVNS (n = 25 each) over two weeks, followed by a two-week follow-up. The prediction target was the percentage change in the positive and negative syndrome scale-factor score for negative symptoms (PANSS-FSNS) from baseline to post-treatment, with further evaluation of model specificity and neurophysiological relevance.The optimal model accurately predicted taVNS response in the active group, with predicted PANSS-FSNS changes strongly correlated with observed changes (r = 0.87, p < .001); permutation testing confirmed performance above chance (p < .001). Nine consistently retained features were identified, predominantly fronto-parietal and fronto-temporal coherence features. Negligible predictive performance in the sham group and failure to predict positive symptom change support the predictive specificity of this oscillatory signature for taVNS-related negative symptom improvement. Two coherence features within fronto-parietal-temporal networks showed post-taVNS changes significantly associated with symptom improvement, suggesting dual roles as predictors and potential therapeutic targets. EEG oscillatory neuromarkers enable accurate prediction of individual taVNS response in TRS, supporting mechanism-informed precision neuromodulation strategies. --- ### Exploring the Dimensions of a Variational Neuron Authors: Yves Ruffenach Published: 2026-03-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.13849v1 We introduce EVE (Elemental Variational Expanse), a variational distributional neuron formulated as a local probabilistic computational unit with an explicit prior, an amortized posterior, and unit-level variational regularization. In most modern architectures, uncertainty is modeled through global latent variables or parameter uncertainty, while the computational unit itself remains scalar. EVE instead relocates probabilistic structure to the neuron level, making it locally observable and controllable. In this paper, the term dimensions refers primarily to the neuron's internal latent dimensionality, denoted by k. We study how varying k, from the atomic case k = 1 to higher-dimensional latent spaces, changes the neuron's learned operating regime. We then examine how this main axis interacts with two additional structural properties: local capacity control and temporal persistence through a neuron-level autoregressive extension. To support this study, EVE is instrumented with internal diagnostics and constraints, including effective KL, a target band on mu^2, out-of-band fractions, and indicators of drift and collapse. Across selected forecasting and tabular settings, we show that latent dimensionality, control, and temporal extension shape the neuron's internal regime, and that some neuron-level variables are measurable, informative, and related to downstream behavior. Overall, the paper provides an experimentally grounded first map of the design space opened by a variational neuron. --- ### Sirens' Whisper: Inaudible Near-Ultrasonic Jailbreaks of Speech-Driven LLMs Authors: Zijian Ling, Pingyi Hu, Xiuyong Gao, Xiaojing Ma, Man Zhou, Jun Feng, Songfeng Lu, Dongmei Zhang, Bin Benjamin Zhu Published: 2026-03-14 Categories: cs.CR, cs.AI, cs.SD arXiv: https://arxiv.org/abs/2603.13847v1 Speech-driven large language models (LLMs) are increasingly accessed through speech interfaces, introducing new security risks via open acoustic channels. We present Sirens' Whisper (SWhisper), the first practical framework for covert prompt-based attacks against speech-driven LLMs under realistic black-box conditions using commodity hardware. SWhisper enables robust, inaudible delivery of arbitrary target baseband audio-including long and structured prompts-on commodity devices by encoding it into near-ultrasound waveforms that demodulate faithfully after acoustic transmission and microphone nonlinearity. This is achieved through a simple yet effective approach to modeling nonlinear channel characteristics across devices and environments, combined with lightweight channel-inversion pre-compensation. Building on this high-fidelity covert channel, we design a voice-aware jailbreak generation method that ensures intelligibility, brevity, and transferability under speech-driven interfaces. Experiments across both commercial and open-source speech-driven LLMs demonstrate strong black-box effectiveness. On commercial models, SWhisper achieves up to 0.94 non-refusal (NR) and 0.925 specific-convincing (SC). A controlled user study further shows that the injected jailbreak audio is perceptually indistinguishable from background-only playback for human listeners. Although jailbreaks serve as a case study, the underlying covert acoustic channel enables a broader class of high-fidelity prompt-injection and commandexecution attacks. --- ### Is Seeing Believing? Evaluating Human Sensitivity to Synthetic Video Authors: David Wegmann, Emil Stevnsborg, Søren Knudsen, Luca Rossi, Aske Mottelson Published: 2026-03-14 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2603.13846v3 Advances in machine learning have enabled the creation of realistic synthetic videos known as deepfakes. As deepfakes proliferate, concerns about rapid spread of disinformation and manipulation of public perception are mounting. Despite the alarming implications, our understanding of how individuals perceive synthetic media remains limited, obstructing the development of effective mitigation strategies. This paper aims to narrow this gap by investigating human responses to visual and auditory distortions of videos and deepfake-generated visuals and narration. In two between-subjects experiments, we study whether audio-visual distortions affect cognitive processing, such as subjective credibility assessment and objective learning outcomes. A third study reveals that artifacts from deepfakes influence credibility. The three studies show that video distortions and deepfake artifacts can reduce credibility. Our research contributes to the ongoing exploration of the cognitive processes involved in the evaluation and perception of synthetic videos, and underscores the need for further theory development concerning deepfake exposure. --- ### MOGeo: Beyond One-to-One Cross-View Object Geo-localization Authors: Bo Lv, Qingwang Zhang, Le Wu, Yuanyuan Li, Yingying Zhu Published: 2026-03-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.13843v2 Cross-View Object Geo-Localization (CVOGL) aims to locate an object of interest in a query image within a corresponding satellite image. Existing methods typically assume that the query image contains only a single object, which does not align with the complex, multi-object geo-localization requirements in real-world applications, making them unsuitable for practical scenarios. To bridge the gap between the realistic setting and existing task, we propose a new task, called Cross-View Multi-Object Geo-Localization (CVMOGL). To advance the CVMOGL task, we first construct a benchmark, CMLocation, which includes two datasets: CMLocation-V1 and CMLocation-V2. Furthermore, we propose a novel cross-view multi-object geo-localization method, MOGeo, and benchmark it against existing state-of-the-art methods. Extensive experiments are conducted under various application scenarios to validate the effectiveness of our method. The results demonstrate that cross-view object geo-localization in the more realistic setting remains a challenging problem, encouraging further research in this area. --- ### Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving Authors: Zhexi Lian, Haoran Wang, Xuerun Yan, Weimeng Lin, Xianhong Zhang, Yongyu Chen, Jia Hu Published: 2026-03-14 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2603.13842v3 End-to-end autonomous driving is typically built upon imitation learning (IL), yet its performance is constrained by the quality of human demonstrations. To overcome this limitation, recent methods incorporate reinforcement learning (RL) through sequential fine-tuning. However, such a paradigm remains suboptimal: sequential RL fine-tuning can introduce policy drift and often leads to a performance ceiling due to its dependence on the pretrained IL policy. To address these issues, we propose PaIR-Drive, a general Parallel framework for collaborative Imitation and Reinforcement learning in end-to-end autonomous driving. During training, PaIR-Drive separates IL and RL into two parallel branches with conflict-free training objectives, enabling fully collaborative optimization. This design eliminates the need to retrain RL when applying a new IL policy. During inference, RL leverages the IL policy to further optimize the final plan, allowing performance beyond prior knowledge of IL. Furthermore, we introduce a tree-structured trajectory neural sampler to group relative policy optimization (GRPO) in the RL branch, which enhances exploration capability. Extensive analysis on NAVSIMv1 and v2 benchmark demonstrates that PaIR-Drive achieves Competitive performance of 91.2 PDMS and 87.9 EPDMS, building upon Transfuser and DiffusionDrive IL baselines. PaIR-Drive consistently outperforms existing RL fine-tuning methods, and could even correct human experts' suboptimal behaviors. Qualitative results further confirm that PaIR-Drive can effectively explore and generate high-quality trajectories. --- ### MICRO: A Lightweight Middleware for Optimizing Cross-store Cross-model Graph-Relation Joins (Technical Report) Authors: Xiuwen Zheng, Arun Kumar, Amarnath Gupta Published: 2026-03-14 Categories: cs.DB, cs.LG arXiv: https://arxiv.org/abs/2603.13835v1 Modern data applications increasingly involve heterogeneous data managed in different models and stored across disparate database engines, often deployed as separate installs. Limited research has addressed cross-model query processing in federated environments. This paper takes a step toward bridging this gap by: (1) formally defining a class of cross-model join queries between a graph store and a relational store by proposing a unified algebra; (2) introducing one real-world benchmark and four semi-synthetic benchmarks to evaluate such queries; and (3) proposing a lightweight middleware, MICRO, for efficient query execution. At the core of MICRO is CMLero, a learning-to-rank-based query optimizer that selects efficient execution plans without requiring exact cost estimation. By avoiding the need to materialize or convert all data into a single model, which is often infeasible due to third-party data control or cost, MICRO enables native querying across heterogeneous systems. Experimental results on the benchmark workloads demonstrate that MICRO outperforms the state-of-the-art federated relational system XDB by up to 2.1x in total runtime across the full test set. On the 93 test queries of real-world benchmark, 14 queries achieve over 100 speedup, including 4 queries with more than 100x speedup; however, 4 queries experienced slowdowns of over 5 seconds, highlighting opportunities for future improvement of MICRO. Further comparisons show that CMLero consistently outperforms rule-based and regression-based optimizers, highlighting the advantage of learning-to-rank in complex cross-model optimization. --- ### Intelligent Materials Modelling: Large Language Models Versus Partial Least Squares Regression for Predicting Polysulfone Membrane Mechanical Performance Authors: Dingding Cao, Mieow Kee Chan, Wan Sieng Yeo, Said Bey, Alberto Figoli Published: 2026-03-14 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.13834v1 Predicting the mechanical properties of polysulfone (PSF) membranes from structural descriptors remains challenging due to extreme data scarcity typical of experimental studies. To investigate this issue, this study benchmarked knowledge-driven inference using four large language models (LLMs) (DeepSeek-V3, DeepSeek-R1, ChatGPT-4o, and GPT-5) against partial least squares (PLS) regression for predicting Young's modulus (E), tensile strength (TS), and elongation at break (EL) based on pore diameter (PD), contact angle (CA), thickness (T), and porosity (P) measurements. These knowledge-driven approaches demonstrated property-specific advantages over the chemometric baseline. For EL, LLMs achieved statistically significant improvements, with DeepSeek-R1 and GPT-5 delivering 40.5% and 40.3% of Root Mean Square Error reductions, respectively, reducing mean absolute errors from $11.63\pm5.34$% to $5.18\pm0.17$%. Run-to-run variability was markedly compressed for LLMs ($\leq$3%) compared to PLS (up to 47%). E and TS predictions showed statistical parity between approaches ($q\geq0.05$), indicating sufficient performance of linear methods for properties with strong structure-property correlations. Error topology analysis revealed systematic regression-to-the-mean behavior dominated by data-regime effects rather than model-family limitations. These findings establish that LLMs excel for non-linear, constraint-sensitive properties under bootstrap instability, while PLS remains competitive for linear relationships requiring interpretable latent-variable decompositions. The demonstrated complementarity suggests hybrid architectures leveraging LLM-encoded knowledge within interpretable frameworks may optimise small-data materials discovery. ---