# Research Papers — 2026-03 · bundle page 188 of 243 > Full-text markdown of papers #9351–9400 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/188 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/187.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/189.md) ### Neural Dynamics-Informed Pre-trained Framework for Personalized Brain Functional Network Construction Authors: Hongjie Jiang, Yifei Tang, Shuqiang Wang Published: 2026-03-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.07524v1 Brain activity is intrinsically a neural dynamic process constrained by anatomical space. This leads to significant variations in spatial distribution patterns and correlation patterns of neural activity across variable and heterogeneous scenarios. However, dominant brain functional network construction methods, which relies on pre-defined brain atlases and linear assumptions, fails to precisely capture varying neural activity patterns in heterogeneous scenarios. This limits the consistency and generalizability of the brain functional networks constructed by dominant methods. Here, a neural dynamics-informed pre-trained framework is proposed for personalized brain functional network construction. The proposed framework extracts personalized representations of neural activity patterns in heterogeneous scenarios. Personalized brain functional networks are obtained by utilizing these representations to guide brain parcellation and neural activity correlation estimation. Systematic evaluations were employed on 18 datasets across tasks, such as virtual neural modulation and abnormal neural circuit identification. Experimental results demonstrate that the proposed framework attains superior performance in heterogeneous scenarios. Overall, the proposed framework challenges the dominant brain functional network construction method. --- ### Breaking the Scale Barrier: One-Shot Knowledge Transfer via Frequency Transform Authors: Jianlu Shen, Fu Feng, Yucheng Xie, Jiaqi Lv, Xin Geng Published: 2026-03-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.07523v3 Transferring knowledge by fine-tuning large-scale pre-trained networks has become a standard paradigm for downstream tasks, yet the knowledge of a pre-trained model is tightly coupled with monolithic architecture, which restricts flexible reuse across models of varying scales. In response to this challenge, recent approaches typically resort to either parameter selection, which fails to capture the interdependent structure of this knowledge, or parameter prediction using generative models that depend on impractical access to large network collections. In this paper, we identify the low-frequency components of model weights as the concrete carrier of foundational, task-agnostic knowledge, its ``learngene", and validate this by demonstrating its efficient inheritance by downstream models and tasks. Based on this insight, we propose FRONT (FRequency dOmain kNowledge Transfer), a novel framework that uses the Discrete Cosine Transform (DCT) to isolate the low-frequency ``learngene". This learngene can be seamlessly adapted to initialize models of arbitrary size via simple truncation or padding, a process that is entirely training-free. For enhanced performance, we propose an optional low-cost refinement process that introduces a spectral regularizer to further improve the learngene's transferability. Extensive experiments demonstrate that FRONT achieves the state-of-the-art performance, accelerates convergence by up to $15\times$ in vision tasks, and reduces training FLOPs by an average of 40.5% in language tasks. Code is available at https://github.com/LUcy0505/FRONT. --- ### Beyond Data Splitting: Full-Data Conformal Prediction by Differential Privacy Authors: Young Hyun Cho, Jordan Awan Published: 2026-03-08 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2603.07522v1 Privacy protection and uncertainty quantification are increasingly important in data-driven decision making. Conformal prediction provides finite-sample marginal coverage, but existing private approaches often rely on data splitting, reducing the effective sample size. We propose a full-data privacy-preserving conformal prediction framework that avoids splitting. Our framework leverages stability induced by differential privacy to control the gap between in-sample and out-of-sample conformal scores, and pairs this with a conservative private quantile routine designed to prevent under-coverage. We show that a generic differential privacy guarantee yields a universal coverage floor, yet cannot generally recover the nominal $1-α$ level. We then provide a refined, mechanism-specific stability analysis and yields asymptotic recovery of the nominal level. Experiments demonstrate sharper prediction sets than the split-based private baseline. --- ### SketchGraphNet: A Memory-Efficient Hybrid Graph Transformer for Large-Scale Sketch Corpora Recognition Authors: Shilong Chen, Mingyuan Li, Zhaoyang Wang, Zhonglin Ye, Haixing Zhao Published: 2026-03-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.07521v1 This work investigates large-scale sketch recognition from a graph-native perspective, where free-hand sketches are directly modeled as structured graphs rather than raster images or stroke sequences. We propose SketchGraphNet, a hybrid graph neural architecture that integrates local message passing with a memory-efficient global attention mechanism, without relying on auxiliary positional or structural encodings. To support systematic evaluation, we construct SketchGraph, a large-scale benchmark comprising 3.44 million graph-structured sketches across 344 categories, with two variants (A and R) to reflect different noise conditions. Each sketch is represented as a spatiotemporal graph with normalized stroke-order attributes. On SketchGraph-A and SketchGraph-R, SketchGraphNet achieves Top-1 accuracies of 83.62% and 87.61%, respectively, under a unified training configuration. MemEffAttn further reduces peak GPU memory by over 40% and training time by more than 30% compared with Performer-based global attention, while maintaining comparable accuracy. --- ### Reinforcement learning-based dynamic cleaning scheduling framework for solar energy system Authors: Heungjo An Published: 2026-03-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.07518v1 Advancing autonomous green technologies in solar photovoltaic (PV) systems is key to improving sustainability and efficiency in renewable energy production. This study presents a reinforcement learning (RL)-based framework to autonomously optimize the cleaning schedules of PV panels in arid regions, where soiling from dust and other airborne particles significantly reduces energy output. By employing advanced RL algorithms, Proximal Policy Optimization (PPO) and Soft Actor-Critic (SAC), the framework dynamically adjusts cleaning intervals based on uncertain environmental conditions. The proposed approach was applied to a case study in Abu Dhabi, UAE, demonstrating that PPO outperformed SAC and traditional simulation optimization (Sim-Opt) methods, achieving up to 13% cost savings by dynamically responding to weather uncertainties. The results highlight the superiority of flexible, autonomous scheduling over fixed-interval methods, particularly in adapting to stochastic environmental dynamics. This aligns with the goals of autonomous green energy production by reducing operational costs and improving the efficiency of solar power generation systems. This work underscores the potential of RL-driven autonomous decision-making to optimize maintenance operations in renewable energy systems. In future research, it is important to enhance the generalization ability of the proposed RL model, while also considering additional factors and constraints to apply it to different regions. --- ### InterReal: A Unified Physics-Based Imitation Framework for Learning Human-Object Interaction Skills Authors: Dayang Liang, Yuhang Lin, Xinzhe Liu, Jiyuan Shi, Yunlong Liu, Chenjia Bai Published: 2026-03-08 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2603.07516v1 Interaction is one of the core abilities of humanoid robots. However, most existing frameworks focus on non-interactive whole-body control, which limits their practical applicability. In this work, we develop InterReal, a unified physics-based imitation learning framework for Real-world human-object Interaction (HOI) control. InterReal enables humanoid robots to track HOI reference motions, facilitating the learning of fine-grained interactive skills and their deployment in real-world settings. Within this framework, we first introduce a HOI motion data augmentation scheme with hand-object contact constraints, and utilize the augmented motions to improve policy stability under object perturbations. Second, we propose an automatic reward learner to address the challenge of large-scale reward shaping. A meta-policy guided by critical tracking error metrics explores and allocates reward signals to the low-level reinforcement learning objective, which enables more effective learning of interactive policies. Experiments on HOI tasks of box-picking and box-pushing demonstrate that InterReal achieves the best tracking accuracy and the highest task success rate compared to recent baselines. Furthermore, we validate the framework on the real-world robot Unitree G1, which demonstrates its practical effectiveness and robustness beyond simulation. --- ### EvolveReason: Self-Evolving Reasoning Paradigm for Explainable Deepfake Facial Image Identification Authors: Binjia Zhou, Dawei Luo, Shuai Chen, Feng Xu, Seow, Haoyuan Li, Jiachi Wang, Jiawen Wang, Zunlei Feng, Yijun Bei Published: 2026-03-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07515v1 With the rapid advancement of AIGC technology, developing identification methods to address the security challenges posed by deepfakes has become urgent. Face forgery identification techniques can be categorized into two types: traditional classification methods and explainable VLM approaches. The former provides classification results but lacks explanatory ability, while the latter, although capable of providing coarse-grained explanations, often suffers from hallucinations and insufficient detail. To overcome these limitations, we propose EvolveReason, which mimics the reasoning and observational processes of human auditors when identifying face forgeries. By constructing a chain-of-thought dataset, CoT-Face, tailored for advanced VLMs, our approach guides the model to think in a human-like way, prompting it to output reasoning processes and judgment results. This provides practitioners with reliable analysis and helps alleviate hallucination. Additionally, our framework incorporates a forgery latent-space distribution capture module, enabling EvolveReason to identify high-frequency forgery cues difficult to extract from the original images. To further enhance the reliability of textual explanations, we introduce a self-evolution exploration strategy, leveraging reinforcement learning to allow the model to iteratively explore and optimize its textual descriptions in a two-stage process. Experimental results show that EvolveReason not only outperforms the current state-of-the-art methods in identification performance but also accurately identifies forgery details and demonstrates generalization capabilities. --- ### A Unified View of Score-Based and Drifting Models Authors: Chieh-Hsin Lai, Bac Nguyen, Naoki Murata, Yuhta Takida, Toshimitsu Uesaka, Yuki Mitsufuji, Stefano Ermon, Molei Tao Published: 2026-03-08 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2603.07514v3 Drifting models train one-step generators by optimizing a kernel-induced mean-shift discrepancy between the data and model distributions, with Laplace kernels used by default in practice. At each point, this discrepancy compares the kernel-weighted displacement toward nearby data samples with the corresponding displacement toward nearby model samples, thereby defining a transport direction for generated samples. In this paper, we show that drifting is more closely connected to score-based generative modeling than it may first appear, establishing a precise link to the score-matching principle underlying diffusion models. For Gaussian kernels, the population mean-shift field exactly equals the difference between the scores (i.e., the gradient-log-densities) of the Gaussian-smoothed data and model distributions. This identity follows from Tweedie's formula, which links the score of a Gaussian-smoothed density to its conditional mean, and implies that Gaussian-kernel drifting is exactly a score-matching objective on smoothed distributions. More generally, we derive an exact decomposition for radial kernels in which mean shift equals a score-based field plus a residual term. For the practical Laplace kernel, we further show theoretically and empirically that this residual is negligible in high dimension, implying that the transport field used in practice is nearly score-based. Our results reveal a structural connection to diffusion models: both methods use score-mismatch transport directions, but drifting realizes the score nonparametrically through kernel-based estimates, whereas diffusion models learn it parametrically with neural networks. --- ### Bolbosh: Script-Aware Flow Matching for Kashmiri Text-to-Speech Authors: Tajamul Ashraf, Burhaan Rasheed Zargar, Saeed Abdul Muizz, Ifrah Mushtaq, Nazima Mehdi, Iqra Altaf Gillani, Aadil Amin Kak, Janibul Bashir Published: 2026-03-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.07513v1 Kashmiri is spoken by around 7 million people but remains critically underserved in speech technology, despite its official status and rich linguistic heritage. The lack of robust Text-to-Speech (TTS) systems limits digital accessibility and inclusive human-computer interaction for native speakers. In this work, we present the first dedicated open-source neural TTS system designed for Kashmiri. We show that zero-shot multilingual baselines trained for Indic languages fail to produce intelligible speech, achieving a Mean Opinion Score (MOS) of only 1.86, largely due to inadequate modeling of Perso-Arabic diacritics and language-specific phonotactics. To address these limitations, we propose Bolbosh, a supervised cross-lingual adaptation strategy based on Optimal Transport Conditional Flow Matching (OT-CFM) within the Matcha-TTS framework. This enables stable alignment under limited paired data. We further introduce a three-stage acoustic enhancement pipeline consisting of dereverberation, silence trimming, and loudness normalization to unify heterogeneous speech sources and stabilize alignment learning. The model vocabulary is expanded to explicitly encode Kashmiri graphemes, preserving fine-grained vowel distinctions. Our system achieves a MOS of 3.63 and a Mel-Cepstral Distortion (MCD) of 3.73, substantially outperforming multilingual baselines and establishing a new benchmark for Kashmiri speech synthesis. Our results demonstrate that script-aware and supervised flow-based adaptation are critical for low-resource TTS in diacritic-sensitive languages. Code and data are available at: https://github.com/gaash-lab/Bolbosh. --- ### Online Continual Learning for Anomaly Detection in IoT under Data Distribution Shifts Authors: Matea Marinova, Shashi Raj Pandey, Junya Shiraishi, Martin Voigt Vejling, Valentin Rakovic, Petar Popovski Published: 2026-03-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.07507v1 In this work, we present OCLADS, a novel communication framework with continual learning (CL) for Internet of Things (IoT) anomaly detection (AD) when operating in non-stationary environments. As the statistical properties of the observed data change with time, the on-device inference model becomes obsolete, which necessitates strategic model updating. OCLADS keeps track of data distribution shifts to timely update the on-device IoT AD model. To do so, OCLADS introduces two mechanisms during the interaction between the resource-constrained IoT device and an edge server (ES): i) an intelligent sample selection mechanism at the device for data transmission, and ii) a distribution-shift detection mechanism at the ES for model updating. Experimental results with TinyML demonstrate that our proposed framework achieves high inference accuracy while realizing a significantly smaller number of model updates compared to the baseline schemes. --- ### A Unified Framework for Knowledge Transfer in Bidirectional Model Scaling Authors: Jianlu Shen, Fu Feng, Jiaze Xu, Yucheng Xie, Jiaqi Lv, Xin Geng Published: 2026-03-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.07506v1 Transferring pre-trained knowledge from a source model to a target model of a different architectural size is a key challenge for flexible and efficient model scaling. However, current parameter-space methods treat Small-to-Large (S2L) and Large-to-Small (L2S) scaling as separate, incompatible problems, focusing on parameter synthesis and selection, respectively. This fragmented perspective has resulted in specialized tools, hindering a unified, bidirectional framework. In this paper, we propose BoT (Bidirectional knowledge Transfer), the first size-agnostic framework to unify S2L and L2S scaling. Our core insight is to treat model weights as continuous signals, where models of different sizes represent distinct discretizations of the transferable knowledge. This multi-resolution perspective directly casts S2L and L2S scaling as the signal processing operations of upsampling and downsampling, naturally leading to the adoption of the Discrete Wavelet Transform (DWT) and its Inverse (IDWT). BoT leverages the recursive nature of wavelets, using the decomposition level as a dynamic scaling factor to bridge disparate model sizes in a parameter-free and computationally efficient manner. Extensive experiments on DeiT, BERT, and GPT demonstrate significant pre-training FLOPs savings (up to 67.1% for S2L, 52.8% for L2S) and state-of-the-art performance on benchmarks like GLUE and SQuAD. --- ### High-Fidelity Medical Shape Generation via Skeletal Latent Diffusion Authors: Guoqing Zhang, Jingyun Yang, Siqi Chen, Anping Zhang, Yang Li Published: 2026-03-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07504v3 Anatomy shape modeling is a fundamental problem in medical data analysis. However, the geometric complexity and topological variability of anatomical structures pose significant challenges to accurate anatomical shape generation. In this work, we propose a skeletal latent diffusion framework that explicitly incorporates structural priors for efficient and high-fidelity medical shape generation. We introduce a shape auto-encoder in which the encoder captures global geometric information through a differentiable skeletonization module and aggregates local surface features into shape latents, while the decoder predicts the corresponding implicit fields over sparsely sampled coordinates. New shapes are generated via a latent-space diffusion model, followed by neural implicit decoding and mesh extraction. To address the limited availability of medical shape data, we construct a large-scale dataset, \textit{MedSDF}, comprising surface point clouds and corresponding signed distance fields across multiple anatomical categories. Extensive experiments on MedSDF and vessel datasets demonstrate that the proposed method achieves superior reconstruction and generation quality while maintaining a higher computational efficiency compared with existing approaches. Code is available at: https://github.com/wlsdzyzl/meshage. --- ### SeDa: A Unified System for Dataset Discovery and Multi-Entity Augmented Semantic Exploration Authors: Kan Ling, Zhen Qin, Yichi Zhu, Hengrun Zhang, Huiqun Yu, Guisheng Fan Published: 2026-03-08 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2603.07502v2 The continuous expansion of open data platforms and research repositories has led to a fragmented dataset ecosystem, posing significant challenges for cross-source data discovery and interpretation. To address these challenges, we introduce SeDa--a unified framework for dataset discovery, semantic annotation, and multi-entity augmented navigation. SeDa integrates more than 7.6 million datasets from over 200 platforms, spanning governmental, academic, and industrial domains. The framework first performs semantic extraction and standardization to harmonize heterogeneous metadata representations. On this basis, a topic-tagging mechanism constructs an extensible tag graph that supports thematic retrieval and cross-domain association, while a provenance assurance module embedded within the annotation process continuously validates dataset sources and monitors link availability to ensure reliability and traceability. Furthermore, SeDa employs a multi-entity augmented navigation strategy that organizes datasets within a knowledge space of sites, institutions, and enterprises, enabling contextual and provenance-aware exploration beyond traditional search paradigms. Comparative experiments with popular dataset search platforms, such as ChatPD and Google Dataset Search, demonstrate that SeDa achieves superior coverage, timeliness, and traceability. Taken together, SeDa establishes a foundation for trustworthy, semantically enriched, and globally scalable dataset exploration. --- ### Enhanced Random Subspace Local Projections for High-Dimensional Time Series Analysis Authors: Eman Khalid, Moimma Ali Khan, Zarmeena Ali, Abdullah Illyas, Muhammad Usman, Saoud Ahmed Published: 2026-03-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.07500v1 High-dimensional time series forecasting suffers from severe overfitting when the number of predictors exceeds available observations, making standard local projection methods unstable and unreliable. We propose an enhanced Random Subspace Local Projection (RSLP) framework designed to deliver robust impulse response estimation in the presence of hundreds of correlated predictors. The method introduces weighted subspace aggregation, category-aware subspace sampling, adaptive subspace size selection, and a bootstrap inference procedure tailored to dependent data. These enhancements substantially improve estimator stability at longer forecast horizons while providing more reliable finite-sample inference. Experiments on synthetic data, macroeconomic indicators, and the FRED-MD dataset demonstrate a 33 percent reduction in estimator variability at horizons h >= 3 through adaptive subspace size selection. The bootstrap inference procedure produces conservative confidence intervals that are 14 percent narrower at policy-relevant horizons in very high-dimensional settings (FRED-MD with 126 predictors) while maintaining proper coverage. The framework provides practitioners with a principled approach for incorporating rich information sets into impulse response analysis without the instability of traditional high-dimensional methods. --- ### AMR-CCR: Anchored Modular Retrieval for Continual Chinese Character Recognition Authors: Yuchuan Wu, Yinglian Zhu, Haiyang Yu, Ke Niu, Bin Li, Xiangyang Xue Published: 2026-03-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07497v1 Ancient Chinese character recognition is a core capability for cultural heritage digitization, yet real-world workflows are inherently non-stationary: newly excavated materials are continuously onboarded, bringing new classes in different scripts, and expanding the class space over time. We formalize this process as Continual Chinese Character Recognition (Continual CCR), a script-staged, class-incremental setting that couples two challenges: (i) scalable learning under continual class growth with subtle inter-class differences and scarce incremental data, and (ii) pronounced intra-class diversity caused by writing-style variations across writers and carrier conditions. To overcome the limitations of conventional closed-set classification, we propose AMR-CCR, an anchored modular retrieval framework that performs recognition via embedding-based dictionary matching in a shared multimodal space, allowing new classes to be added by simply extending the dictionary. AMR-CCR further introduces a lightweight script-conditioned injection module (SIA+SAR) to calibrate newly onboarded scripts while preserving cross-stage embedding compatibility, and an image-derived multi-prototype dictionary that clusters within-class embeddings to better cover diverse style modes. To support systematic evaluation, we build EvoCON, a six-stage benchmark for continual script onboarding, covering six scripts (OBC, BI, SS, SAC, WSC, CS), augmented with meaning/shape descriptions and an explicit zero-shot split for unseen characters without image exemplars. --- ### From Thinker to Society: Security in Hierarchical Autonomy Evolution of AI Agents Authors: Xiaolei Zhang, Lu Zhou, Xiaogang Xu, Jiafei Wu, Tianyu Du, Heqing Huang, Hao Peng, Zhe Liu Published: 2026-03-08 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2603.07496v2 Artificial Intelligence (AI) agents have evolved from passive predictive tools into active entities capable of autonomous decision-making and environmental interaction, driven by the reasoning capabilities of Large Language Models (LLMs). However, this evolution has introduced critical security vulnerabilities that existing frameworks fail to address. The Hierarchical Autonomy Evolution (HAE) framework organizes agent security into three tiers: Cognitive Autonomy (L1) targets internal reasoning integrity; Execution Autonomy (L2) covers tool-mediated environmental interaction; Collective Autonomy (L3) addresses systemic risks in multi-agent ecosystems. We present a taxonomy of threats spanning cognitive manipulation, physical environment disruption, and multi-agent systemic failures, and evaluate existing defenses while identifying key research gaps. The findings aim to guide the development of multilayered, autonomy-aware defense architectures for trustworthy AI agent systems. --- ### DocCogito: Aligning Layout Cognition and Step-Level Grounded Reasoning for Document Understanding Authors: Yuchuan Wu, Minghan Zhuo, Teng Fu, Mengyang Zhao, Bin Li, Xiangyang Xue Published: 2026-03-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07494v1 Document understanding with multimodal large language models (MLLMs) requires not only accurate answers but also explicit, evidence-grounded reasoning, especially in high-stakes scenarios. However, current document MLLMs still fall short of forming a complete, human-like reasoning process, because even when they improve both layout encoding and CoT-style prompting, the interaction between the two is typically learned implicitly and remains loosely coupled rather than being enforced as a systematic mechanism. So we propose DocCogito, a unified framework that integrates global layout perception with structured, region-grounded reasoning. DocCogito introduces a lightweight layout tower that distills page structure into learnable global layout prior tokens, and a deterministic Visual-Semantic Chain (VSC)-a concise structured representation less ambiguous than free-form natural-language CoT-to supervise fine-grained intermediate reasoning aligned with evidence regions. Training follows a progressive recipe, including layout perception pretraining, VSC-guided cold start, rejection sampling, and GRPO. To further strengthen the internal coupling between layout priors and VSC execution, we augment standard rewards with a fine-grained region-confidence signal that encourages reasoning traces to stay aligned with corresponding evidence regions. Extensive experiments on six benchmarks (DocVQA, WTQ, ChartQA, TextVQA, OCRBench, and InfoVQA) demonstrate strong generalization, achieving state-of-the-art results on four benchmarks. --- ### RayD3D: Distilling Depth Knowledge Along the Ray for Robust Multi-View 3D Object Detection Authors: Rui Ding, Zhaonian Kuang, Zongwei Zhou, Meng Yang, Xinhu Zheng, Gang Hua Published: 2026-03-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07493v1 Multi-view 3D detection with bird's eye view (BEV) is crucial for autonomous driving and robotics, but its robustness in real-world is limited as it struggles to predict accurate depth values. A mainstream solution, cross-modal distillation, transfers depth information from LiDAR to camera models but also unintentionally transfers depth-irrelevant information (e.g. LiDAR density). To mitigate this issue, we propose RayD3D, which transfers crucial depth knowledge along the ray: a line projecting from the camera to true location of an object. It is based on the fundamental imaging principle that predicted location of this object can only vary along this ray, which is finally determined by predicted depth value. Therefore, distilling along the ray enables more effective depth information transfer. More specifically, we design two ray-based distillation modules. Ray-based Contrastive Distillation (RCD) incorporates contrastive learning into distillation by sampling along the ray to learn how LiDAR accurately locates objects. Ray-based Weighted Distillation (RWD) adaptively adjusts distillation weight based on the ray to minimize the interference of depth-irrelevant information in LiDAR. For validation, we widely apply RayD3D into three representative types of BEV-based models, including BEVDet, BEVDepth4D, and BEVFormer. Our method is trained on clean NuScenes, and tested on both clean NuScenes and RoboBEV with a variety types of data corruptions. Our method significantly improves the robustness of all the three base models in all scenarios without increasing inference costs, and achieves the best when compared to recently released multi-view and distillation models. --- ### Pushing Bistatic Wireless Sensing toward High Accuracy at the Sub-Wavelength Scale Authors: Wenwei Li, Jiarun Zhou, Qinxiao Quan, Fusang Zhang, Daqing Zhang Published: 2026-03-08 Categories: cs.IT, cs.ET, cs.HC, cs.LG arXiv: https://arxiv.org/abs/2603.07492v1 Contactless sensing using wireless communication signals has garnered significant attention due to its non-intrusive nature and ubiquitous infrastructure. Despite the promise, the inherent bistatic deployment of wireless communication introduces clock asynchronism, which leads to unknown phase offsets in channel response and hinders fine-grained sensing. State-of-the-art systems widely adopt the cross-antenna channel ratio to cancel these detrimental phase offsets. However, the channel ratio preserves sensing feature accuracy only at integer-wavelength target displacements, losing sub-wavelength fidelity. To overcome this limitation, we derive the first quantitative mapping between the distorted ratio feature and the ideal channel feature. Building on this foundation, we develop a robust framework that leverages channel response amplitude to recover the ideal channel feature from the distorted ratio. Real-world experiments across Wi-Fi and LoRa demonstrate that our method can effectively reconstruct sub-wavelength displacement details, achieving nearly an order-of-magnitude improvement in accuracy. --- ### RobustSCI: Beyond Reconstruction to Restoration for Snapshot Compressive Imaging under Real-World Degradations Authors: Hao Wang, Zhankuo Xu, Jiong Ni, Xing Liu, Haoyang Liu, Xin Yuan Published: 2026-03-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07489v2 Deep learning algorithms for video Snapshot Compressive Imaging (SCI) have achieved great success, yet they predominantly focus on reconstructing from clean measurements. This overlooks a critical real-world challenge: the captured signal itself is often severely degraded by motion blur and low light. Consequently, existing models falter in practical applications. To break this limitation, we pioneer the first study on robust video SCI restoration, shifting the goal from "reconstruction" to "restoration"--recovering the underlying pristine scene from a degraded measurement. To facilitate this new task, we first construct a large-scale benchmark by simulating realistic, continuous degradations on the DAVIS 2017 dataset. Second, we propose RobustSCI, a network that enhances a strong encoder-decoder backbone with a novel RobustCFormer block. This block introduces two parallel branches--a multi-scale deblur branch and a frequency enhancement branch--to explicitly disentangle and remove degradations during the recovery process. Furthermore, we introduce RobustSCI-C (RobustSCI-Cascade), which integrates a pre-trained Lightweight Post-processing Deblurring Network to significantly boost restoration performance with minimal overhead. Extensive experiments demonstrate that our methods outperform all SOTA models on the new degraded testbeds, with additional validation on real-world degraded SCI data confirming their practical effectiveness, elevating SCI from merely reconstructing what is captured to restoring what truly happened. --- ### A Joint Neural Baseline for Concept, Assertion, and Relation Extraction from Clinical Text Authors: Fei Cheng, Ribeka Tanaka, Sadao Kurohashi Published: 2026-03-08 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.07487v1 Clinical information extraction (e.g., 2010 i2b2/VA challenge) usually presents tasks of concept recognition, assertion classification, and relation extraction. Jointly modeling the multi-stage tasks in the clinical domain is an underexplored topic. The existing independent task setting (reference inputs given in each stage) makes the joint models not directly comparable to the existing pipeline work. To address these issues, we define a joint task setting and propose a novel end-to-end system to jointly optimize three-stage tasks. We empirically investigate the joint evaluation of our proposal and the pipeline baseline with various embedding techniques: word, contextual, and in-domain contextual embeddings. The proposed joint system substantially outperforms the pipeline baseline by +0.3, +1.4, +3.1 for the concept, assertion, and relation F1. This work bridges joint approaches and clinical information extraction. The proposed approach could serve as a strong joint baseline for future research. The code is publicly available. --- ### Multi-Modal Decouple and Recouple Network for Robust 3D Object Detection Authors: Rui Ding, Zhaonian Kuang, Yuzhe Ji, Meng Yang, Xinhu Zheng, Gang Hua Published: 2026-03-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07486v1 Multi-modal 3D object detection with bird's eye view (BEV) has achieved desired advances on benchmarks. Nonetheless, the accuracy may drop significantly in the real world due to data corruption such as sensor configurations for LiDAR and scene conditions for camera. One design bottleneck of previous models resides in the tightly coupling of multi-modal BEV features during fusion, which may degrade the overall system performance if one modality or both is corrupted. To mitigate, we propose a Multi-Modal Decouple and Recouple Network for robust 3D object detection under data corruption. Different modalities commonly share some high-level invariant features. We observe that these invariant features across modalities do not always fail simultaneously, because different types of data corruption affect each modality in distinct ways.These invariant features can be recovered across modalities for robust fusion under data corruption.To this end, we explicitly decouple Camera/LiDAR BEV features into modality-invariant and modality-specific parts. It allows invariant features to compensate each other while mitigates the negative impact of a corrupted modality on the other.We then recouple these features into three experts to handle different types of data corruption, respectively, i.e., LiDAR, camera, and both.For each expert, we use modality-invariant features as robust information, while modality-specific features serve as a complement.Finally, we adaptively fuse the three experts to exact robust features for 3D object detection. For validation, we collect a benchmark with a large quantity of data corruption for LiDAR, camera, and both based on nuScenes. Our model is trained on clean nuScenes and tested on all types of data corruption. Our model consistently achieves the best accuracy on both corrupted and clean data compared to recent models. --- ### Interpretable-by-Design Transformers via Architectural Stream Independence Authors: Clayton Kerce, Alexis Fox Published: 2026-03-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.07482v1 While transformers achieve strong performance, their internal decision-making processes remain opaque. We investigate whether architectural constraints can enforce interpretability by design through architectural stream independence: maintaining a token stream (carrying symbolic structure) and contextual semantics in separated streams that remain independently observable throughout processing, with integration delayed until output. We validate this principle through the Late Fusion Architecture (LFA), which demonstrates interpretable symbolic heads through all the final layers, while standard transformers show dissolution by the third of six layers; we quantify this effect by introducing the Token-Position Dependence Score (PDS), with $PDS_{max}$ = 0.276 and 0.058, respectively. Crucially, intervention experiments demonstrate functional modularity: suppressing LFA's recency heads causes minimal semantic damage (Cohen's d = -0.158) versus catastrophic entanglement in baselines (d = -0.672). LFA demonstrates that architectural constraints improve underlying learning mechanisms, averaging 42% stability versus 19% and 11% for baseline comparisons, with extremes from 50% on LFA's best pairs (6 of 12 heads position-invariant) down to 0% complete collapse in over-constrained cases. By preventing premature entanglement, architectural independence steers models toward semantic understanding over positional heuristics, establishing interpretability as an architectural design criterion enforceable through structural constraints rather than post-hoc analysis. --- ### EVLF: Early Vision-Language Fusion for Generative Dataset Distillation Authors: Wenqi Cai, Yawen Zou, Guang Li, Chunzhi Gu, Chao Zhang Published: 2026-03-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07476v1 Dataset distillation (DD) aims to synthesize compact training sets that enable models to achieve high accuracy with significantly fewer samples. Recent diffusion-based DD methods commonly introduce semantic guidance through late-stage cross-attention, where textual prompts tend to dominate the generative process. Although this strategy enforces label relevance, it diminishes the contribution of visual latents, resulting in over-corrected samples that mirror prompt patterns rather than reflecting intrinsic visual features. To solve this problem, we introduce an Early Vision-Language Fusion (EVLF) method that aligns textual and visual embeddings at the transition between the encoder and the generative backbone. By incorporating a lightweight cross-attention module at this transition, the early representations simultaneously encode local textures and global semantic directions across the denoising process. Importantly, EVLF is plug-and-play and can be easily integrated into any diffusion-based dataset distillation pipeline with an encoder. It works across different denoiser architectures and sampling schedules without any task-specific modifications. Extensive experiments demonstrate that EVLF generates semantically faithful and visually coherent synthetic data, yielding consistent improvements in downstream classification accuracy across varied settings. Source code is available at https://github.com/wenqi-cai297/earlyfusion-for-dd/. --- ### A Comparative analysis of Layer-wise Representational Capacity in AR and Diffusion LLMs Authors: Raghavv Goel, Risheek Garrepalli, Sudhanshu Agrawal, Chris Lott, Mingu Lee, Fatih Porikli Published: 2026-03-08 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.07475v4 Autoregressive (AR) language models build representations incrementally via left-to-right prediction, while diffusion language models (dLLMs) are trained through full-sequence denoising. Although recent dLLMs match AR performance, whether diffusion objectives fundamentally reshape internal representations remains unclear. We perform the first layer- and token-wise representational analysis comparing native dLLMs (LLaDA), native AR models (Qwen2.5), and AR-initialized dLLMs (Dream-7B), using cosine similarity across layers and tokens alongside static inference-time layer-skipping as an analytical probe of redundancy. We find that diffusion objectives produce more global representations with substantial early-layer redundancy and reduced recency bias, while AR objectives yield tightly coupled, locally structured representations. AR-initialized dLLMs retain AR-like dynamics despite diffusion training, revealing persistent initialization bias. Leveraging this redundancy, native dLLMs absorb up to 18.75% FLOPs reduction while retaining over 90% performance on math-reasoning and coding benchmarks, whereas AR models collapse under identical skipping, revealing that diffusion objectives, rather than architecture alone, induce depth redundancy that enables principled compression. --- ### Cross-Modal Taxonomic Generalization in (Vision-) Language Models Authors: Tianyang Xu, Marcelo Sandoval-Castaneda, Karen Livescu, Greg Shakhnarovich, Kanishka Misra Published: 2026-03-08 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.07474v2 What is the interplay between semantic representations learned by language models (LM) from surface form alone to those learned from more grounded evidence? We study this question for a scenario where part of the input comes from a different modality -- in our case, in a vision-language model (VLM), where a pretrained LM is aligned with a pretrained image encoder. As a case study, we focus on the task of predicting hypernyms of objects represented in images. We do so in a VLM setup where the image encoder and LM are kept frozen, and only the intermediate mappings are learned. We progressively deprive the VLM of explicit evidence for hypernyms, and test whether knowledge of hypernyms is recoverable from the LM. We find that the LMs we study can recover this knowledge and generalize even in the most extreme version of this experiment (when the model receives no evidence of a hypernym during training). Additional experiments suggest that this cross-modal taxonomic generalization persists under counterfactual image-label mappings only when the counterfactual data have high visual similarity within each category. Taken together, these findings suggest that cross-modal generalization in LMs arises as a result of both coherence in the extralinguistic input and knowledge derived from language cues. --- ### Give Them an Inch and They Will Take a Mile:Understanding and Measuring Caller Identity Confusion in MCP-Based AI Systems Authors: Yuhang Huang, Boyang Ma, Biwei Yan, Xuelong Dai, Yechao Zhang, Minghui Xu, Kaidi Xu, Yue Zhang Published: 2026-03-08 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2603.07473v2 The Model Context Protocol (MCP) is an open and standardized interface that enables large language models (LLMs) to interact with external tools and services, and is increasingly adopted by AI agents. However, the security of MCP-based systems remains largely unexplored.In this work, we conduct a large-scale security analysis of MCP servers integrated within MCP clients. We show that treating MCP servers as trusted entities without authenticating the caller identity is fundamentally insecure. Since MCP servers often cannot distinguish who is invoking a request, a single authorization decision may implicitly grant access to multiple, potentially untrusted callers.Our empirical study reveals that most MCP servers rely on persistent authorization states, allowing tool invocations after an initial authorization without re-authentication, regardless of the caller. In addition, many MCP servers fail to enforce authentication at the per-tool level, enabling unauthorized access to sensitive operations.These findings demonstrate that one-time authorization and server-level trust significantly expand the attack surface of MCP-based systems, highlighting the need for explicit caller authentication and fine-grained authorization mechanisms. --- ### Contact-Guided 3D Genome Structure Generation of E. coli via Diffusion Transformers Authors: Mingxin Zhang, Xiaofeng Dai, Yu Yao, Ziqi Yin Published: 2026-03-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.07472v1 In this study, we present a conditional diffusion-transformer framework for generating ensembles of three-dimensional Escherichia coli genome conformations guided by Hi-C contact maps. Instead of producing a single deterministic structure, we formulate genome reconstruction as a conditional generative modeling problem that samples heterogeneous conformations whose ensemble-averaged contacts are consistent with the input Hi-C data. A synthetic dataset is constructed using coarse-grained molecular dynamics simulations to generate chromatin ensembles and corresponding Hi-C maps under circular topology. Our models operate in a latent diffusion setting with a variational autoencoder that preserves per-bin alignment and supports replication-aware representations. Hi-C information is injected through a transformer-based encoder and cross-attention, enforcing a physically interpretable one-way constraint from Hi-C to structure. The model is trained using a flow-matching objective for stable optimization. On held-out ensembles, generated structures reproduce the input Hi-C distance-decay and structural correlation metrics while maintaining substantial conformational diversity, demonstrating the effectiveness of diffusion-based generative modeling for ensemble-level 3D genome reconstruction. --- ### Towards Lightweight Adaptation of Speech Enhancement Models in Real-World Environments Authors: Longbiao Cheng, Shih-Chii Liu Published: 2026-03-08 Categories: eess.AS, cs.AI, cs.LG, cs.SD arXiv: https://arxiv.org/abs/2603.07471v1 Recent studies have shown that post-deployment adaptation can improve the robustness of speech enhancement models in unseen noise conditions. However, existing methods often incur prohibitive computational and memory costs, limiting their suitability for on-device deployment. In this work, we investigate model adaptation in realistic settings with dynamic acoustic scene changes and propose a lightweight framework that augments a frozen backbone with low-rank adapters updated via self-supervised training. Experiments on sequential scene evaluations spanning 111 environments across 37 noise types and three signal-to-noise ratio ranges, including the challenging (-8, 0) dB range, show that our method updates fewer than 1% of the base model's parameters while achieving an average 1.51 dB SI-SDR improvement within only 20 updates per scene. Compared to state-of-the-art approaches, our framework achieves competitive or superior perceptual quality with smoother and more stable convergence, demonstrating its practicality for lightweight on-device adaptation of speech enhancement models under real-world acoustic conditions. --- ### FedEU: Evidential Uncertainty-Driven Federated Fine-Tuning of Vision Foundation Models for Remote Sensing Image Segmentation Authors: Xiaokang Zhang, Xuran Xiong, Jianzhong Huang, Lefei Zhang Published: 2026-03-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07468v1 Remote sensing image segmentation (RSIS) in federated environments has gained increasing attention because it enables collaborative model training across distributed datasets without sharing raw imagery or annotations. Federated RSIS combined with parameter-efficient fine-tuning (PEFT) can unleash the generalization power of pretrained foundation models for real-world applications, with minimal parameter aggregation and communication overhead. However, the dynamic adaptation of pretrained models to heterogeneous client data inevitably increases update uncertainty and compromises the reliability of collaborative optimization due to the lack of uncertainty estimation for each local model. To bridge this gap, we present FedEU, a federated optimization framework for fine-tuning RSIS models driven by evidential uncertainty. Specifically, personalized evidential uncertainty modeling is introduced to quantify epistemic variations of local models and identify high-risk areas under local data distributions. Furthermore, the client-specific feature embedding (CFE) is exploited to enhance channel-aware feature representation while preserving client-specific properties through personalized attention and an element-aware parameter update approach. These uncertainty estimates are uploaded to the server to enable adaptive global aggregation via a Top-k uncertainty-guided weighting (TUW) strategy, which mitigates the impact of distribution shifts and unreliable updates. Extensive experiments on three large-scale heterogeneous datasets demonstrate the superior performance of FedEU. More importantly, FedEU enables balanced model adaptation across diverse clients by explicitly reducing prediction uncertainty, resulting in more robust and reliable federated outcomes. The source codes will be available at https://github.com/zxk688/FedEU. --- ### Probabilistic Inference and Learning with Stein's Method Authors: Qiang Liu, Lester Mackey, Chris Oates Published: 2026-03-08 Categories: stat.ML, cs.LG, math.PR, math.ST, stat.ME arXiv: https://arxiv.org/abs/2603.07467v1 This monograph provides a rigorous overview of theoretical and methodological aspects of probabilistic inference and learning with Stein's method. Recipes are provided for constructing Stein discrepancies from Stein operators and Stein sets, and properties of these discrepancies such as computability, separation, convergence detection, and convergence control are discussed. Further, the connection between Stein operators and Stein variational gradient descent is set out in detail. The main definitions and results are precisely stated, and references to all proofs are provided. --- ### Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI Authors: Heng Jin, Chaoyu Zhang, Hexuan Yu, Shanghao Shi, Ning Zhang, Y. Thomas Hou, Wenjing Lou Published: 2026-03-08 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2603.07466v2 Cloud-based infrastructure has become the dominant platform for deploying large models, particularly large language models (LLMs). Fine-tuning and inference are increasingly delegated to cloud providers for simplified deployment and access to proprietary models, yet this creates a fundamental trust gap. Although cryptographic and TEE-based verification approaches exist, prohibitive proving costs and limited TEE memory prevent them from scaling to modern LLMs, leaving clients unable to practically audit these processes. This lack of transparency creates concrete security risks that can silently compromise service integrity. We present AFTUNE, an auditable and verifiable framework that ensures the computational integrity of cloud-based fine-tuning and inference. AFTUNE incorporates a lightweight recording and spot-check mechanism that produces verifiable traces of execution. These traces enable clients to later audit whether the fine-tuning and inference processes followed the agreed configurations, by verifying sampled execution blocks inside a TEE, each covering only a small portion of the model and the execution trace. Our evaluation shows that AFTUNE adds modest overhead and makes auditing practical for clients. --- ### Classifying Novel 3D-Printed Objects without Retraining: Towards Post-Production Automation in Additive Manufacturing Authors: Fanis Mathioulakis, Gorjan Radevski, Silke GC Cleuren, Michel Janssens, Brecht Das, Koen Schauwaert, Tinne Tuytelaars Published: 2026-03-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07465v1 Reliable classification of 3D-printed objects is essential for automating post-production workflows in industrial additive manufacturing. Despite extensive automation in other stages of the printing pipeline, this task still relies heavily on manual inspection, as the set of objects to be classified can change daily, making frequent model retraining impractical. Automating the identification step is therefore critical for improving operational efficiency. A vision model that could classify any set of objects by utilizing their corresponding CAD models and avoiding retraining would be highly beneficial in this setting. To enable systematic evaluation of vision models on this task, we introduce ThingiPrint, a new publicly available dataset that pairs CAD models with real photographs of their 3D-printed counterparts. Using ThingiPrint, we benchmark a range of existing vision models on the task of 3D-printed object classification. We additionally show that contrastive fine-tuning with a rotation-invariant objective allows effective prototype-based classification of previously unseen 3D-printed objects. By relying solely on the available CAD models, this avoids the need for retraining when new objects are introduced. Experiments show that this approach outperforms standard pretrained baselines, suggesting improved generalization and practical relevance for real-world use. --- ### Selective Transfer Learning of Cross-Modality Distillation for Monocular 3D Object Detection Authors: Rui Ding, Meng Yang, Nanning Zheng Published: 2026-03-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07464v1 Monocular 3D object detection is a promising yet ill-posed task for autonomous vehicles due to the lack of accurate depth information. Cross-modality knowledge distillation could effectively transfer depth information from LiDAR to image-based network. However, modality gap between image and LiDAR seriously limits its accuracy. In this paper, we systematically investigate the negative transfer problem induced by modality gap in cross-modality distillation for the first time, including not only the architecture inconsistency issue but more importantly the feature overfitting issue. We propose a selective learning approach named MonoSTL to overcome these issues, which encourages positive transfer of depth information from LiDAR while alleviates the negative transfer on image-based network. On the one hand, we utilize similar architectures to ensure spatial alignment of features between image-based and LiDAR-based networks. On the other hand, we develop two novel distillation modules, namely Depth-Aware Selective Feature Distillation (DASFD) and Depth-Aware Selective Relation Distillation (DASRD), which selectively learn positive features and relationships of objects by integrating depth uncertainty into feature and relation distillations, respectively. Our approach can be seamlessly integrated into various CNN-based and DETR-based models, where we take three recent models on KITTI and a recent model on NuScenes for validation. Extensive experiments show that our approach considerably improves the accuracy of the base models and thereby achieves the best accuracy compared with all recently released SOTA models. --- ### SIGMAE: A Spectral-Index-Guided Foundation Model for Multispectral Remote Sensing Authors: Xiaokang Zhang, Bo Li, Chufeng Zhou, Weikang Yu, Lefei Zhang Published: 2026-03-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07463v1 Pretraining and fine-tuning have emerged as a new paradigm in remote sensing image interpretation. Among them, Masked Autoencoder (MAE)-based pretraining stands out for its strong capability to learn general feature representations via reconstructing masked image regions. However, applying MAE to multispectral remote sensing images remains challenging due to complex backgrounds, indistinct targets, and the lack of semantic guidance during masking, which hinders the learning of underlying structures and meaningful spatial-spectral features. To address this, we propose a simple yet effective approach, Spectral Index-Guided MAE (SIGMAE), for multispectral image pretraining. The core idea is to incorporate domain-specific spectral indices as prior knowledge to guide dynamic token masking toward informative regions. SIGMAE introduces Semantic Saliency-Guided Dynamic Token Masking (SSDTM), a curriculum-style strategy that quantifies each patch's semantic richness and internal heterogeneity to adaptively select the most informative tokens during training. By prioritizing semantically salient regions and progressively increasing sample difficulty, SSDTM enhances spectrally rich and structurally aware representation learning, mitigates overfitting, and reduces redundant computation compared with random masking. Extensive experiments on five widely used datasets covering various downstream tasks, including scene classification, semantic segmentation, object extraction and change detection, demonstrate that SIGMAE outperforms other pretrained geospatial foundation models. Moreover, it exhibits strong spatial-spectral reconstruction capability, even with a 90% mask ratio, and improves complex target recognition under limited labeled data. The source codes and model weights will be released at https://github.com/zxk688/SIGMAE. --- ### Do Machines Fail Like Humans? A Human-Centred Out-of-Distribution Spectrum for Mapping Error Alignment Authors: Binxia Xu, Xiaoliang Luo, Luke Dickens, Robert M. Mok Published: 2026-03-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.07462v2 Determining whether AI systems process information similarly to humans is central to cognitive science and trustworthy AI. While modern AI models can match human accuracy on standard tasks, such parity does not guarantee that their underlying decision-making strategies resemble those of humans. Assessing performance using error alignment metrics to compare how humans and models fail, and how this changes for distorted, or otherwise more challenging, stimuli, provides a viable pathway toward a finer characterization of model-human alignment. However, existing out-of-distribution (OOD) analyses for challenging stimuli are limited due to methodological choices: they define OOD shift relative to model training data or use arbitrary distortion-specific parameters with little correspondence to human perception, hindering principled comparisons. We propose a human-centred framework that redefines the degree of OOD as a spectrum of human perceptual difficulty. By quantifying how much a collection of stimuli deviates from an undistorted reference set based on human accuracy, we construct an OOD spectrum and identify four distinct regimes of perceptual challenge. This approach enables principled model-human comparisons at calibrated difficulty levels. We apply this framework to object recognition and reveal unique, regime-dependent model-human alignment rankings and profiles across deep learning architectures. Vision-language models are most consistently human aligned across near- and far-OOD conditions, but convolutional neural networks (CNNs) are more aligned than vision transformers (ViTs) for near-OOD and ViTs are more aligned than CNNs for far-OOD. Our work demonstrates the critical importance of accounting for cross-condition differences, such as perceptual difficulty, for a principled assessment of model-human alignment. --- ### The Dual-Stream Transformer: Channelized Architecture for Interpretable Language Modeling Authors: J. Clayton Kerce, Alexis Fox Published: 2026-03-08 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.07461v1 Standard transformers entangle all computation in a single residual stream, obscuring which components perform which functions. We introduce the Dual-Stream Transformer, which decomposes the residual stream into two functionally distinct components: a token stream updated by attention and a context stream updated by feed-forward networks. Information flow between attention heads is controlled through a hierarchy of mixing strategies, from fully independent (maximum interpretability) to dense (standard transformer behavior). This design exposes a tunable tradeoff between interpretability and performance. We measure this tradeoff on language modeling tasks at 29M parameters. Fully independent head mixing increases validation loss by 8\% relative to dense baselines. The recommended Kronecker mixing strategy, which permits scalar communication between heads while preserving within-head structure, costs only 2.5\%. All configurations maintain functional generation under attention amplification (scaling logits by factors up to 16 at inference time), with degradation ranging from 16\% to 27\%. This robustness suggests the architectures learn discrete algorithms that operate independently of soft probabilistic mixing. The architecture provides a foundation for interpretable language models where internal structure is exposed by design. \footnote{This work was partially supported by DARPA Contract HR001125C0302.} --- ### Where Do LLM-based Systems Break? A System-Level Security Framework for Risk Assessment and Treatment Authors: Neha Nagaraja, Hayretdin Bahsi Published: 2026-03-08 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2603.07460v1 Large Language Models (LLMs) are increasingly integrated into safety-critical workflows, yet existing security analyses remain fragmented and often isolate model behavior from the broader system context. This work introduces a goal-driven risk assessment framework for LLM-powered systems that combines system modeling with Attack-Defense Trees (ADTrees) and Common Vulnerability Scoring System (CVSS)-based exploitability scoring to support structured, comparable analysis. We demonstrate the framework through a healthcare case study, modeling multi-step attack paths targeting intervention in medical procedures, leakage of electronic health record (EHR) data, and disruption of service availability. Our analysis indicates that threats spanning (i) conventional cyber, (ii) adversarial ML, and (iii) conversational attacks that manipulate prompts or context often consolidate into a small number of dominant paths and shared system choke points, enabling targeted defenses to yield meaningful reductions in path exploitability. By systematically comparing defense portfolios, we align these risks with established vulnerability management practices and provide a domain-agnostic workflow applicable to other LLM-enabled critical systems. --- ### "Better Ask for Forgiveness than Permission": Practices and Policies of AI Disclosure in Freelance Work Authors: Angel Hsing-Chi Hwang, Senya Wong, Baixiao Chen, Jessica He, Hyo Jin Do Published: 2026-03-08 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2603.07459v1 The growing use of AI applications among freelance workers is reshaping trust and relationships with clients. This paper investigates how both workers and clients perceive AI use and disclosure in the freelance economy through a three-stage study: interviews with workers and two survey studies with workers and clients. Findings first reveal a key expectation gap around disclosure: Workers often adopt passive disclosure practices, revealing AI use only when asked, as they assume clients can already detect it. Clients, however, are far less confident in recognizing AI-assisted work and prefer proactive disclosure. A second finding highlights the role of unclear or absent client AI policies, which leave workers consistently misinterpreting clients' expectations for AI use and disclosure. Together, these gaps point to the need for clearer guidelines and practices for AI disclosure. Insights extend beyond freelancing, offering implications for trust, accountability, and policy design in other AI-mediated work domains. --- ### Image Generation Models: A Technical History Authors: Rouzbeh Shirvani Published: 2026-03-08 Categories: cs.CV, cs.AI, cs.CL, cs.GR arXiv: https://arxiv.org/abs/2603.07455v2 Image generation has advanced rapidly over the past decade, yet the literature seems fragmented across different models and application domains. This paper aims to offer a comprehensive survey of breakthrough image generation models, including variational autoencoders (VAEs), generative adversarial networks (GANs), normalizing flows, autoregressive and transformer-based generators, and diffusion-based methods. We provide a detailed technical walkthrough of each model type, including their underlying objectives, architectural building blocks, and algorithmic training steps. For each model type, we present the optimization techniques as well as common failure modes and limitations. We also go over recent developments in video generation and present the research works that made it possible to go from still frames to high quality videos. Lastly, we cover the growing importance of robustness and responsible deployment of these models, including deepfake risks, detection, artifacts, and watermarking. --- ### SLNet: A Super-Lightweight Geometry-Adaptive Network for 3D Point Cloud Recognition Authors: Mohammad Saeid, Amir Salarpour, Pedram MohajerAnsari, Mert D. Pesé Published: 2026-03-08 Categories: cs.CV, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2603.07454v1 We present SLNet, a lightweight backbone for 3D point cloud recognition designed to achieve strong performance without the computational cost of many recent attention, graph, and deep MLP based models. The model is built on two simple ideas: NAPE (Nonparametric Adaptive Point Embedding), which captures spatial structure using a combination of Gaussian RBF and cosine bases with input adaptive bandwidth and blending, and GMU (Geometric Modulation Unit), a per channel affine modulator that adds only 2D learnable parameters. These components are used within a four stage hierarchical encoder with FPS+kNN grouping, nonparametric normalization, and shared residual MLPs. In experiments, SLNet shows that a very small model can still remain highly competitive across several 3D recognition tasks. On ModelNet40, SLNet-S with 0.14M parameters and 0.31 GFLOPs achieves 93.64% overall accuracy, outperforming PointMLP-elite with 5x fewer parameters, while SLNet-M with 0.55M parameters and 1.22 GFLOPs reaches 93.92%, exceeding PointMLP with 24x fewer parameters. On ScanObjectNN, SLNet-M achieves 84.25% overall accuracy within 1.2 percentage points of PointMLP while using 28x fewer parameters. For large scale scene segmentation, SLNet-T extends the backbone with local Point Transformer attention and reaches 58.2% mIoU on S3DIS Area 5 with only 2.5M parameters, more than 17x fewer than Point Transformer V3. We also introduce NetScore+, which extends NetScore by incorporating latency and peak memory so that efficiency can be evaluated in a more deployment oriented way. Across multiple benchmarks and hardware settings, SLNet delivers a strong overall balance between accuracy and efficiency. Code is available at: https://github.com/m-saeid/SLNet. --- ### Backdoor4Good: Benchmarking Beneficial Uses of Backdoors in LLMs Authors: Yige Li, Wei Zhao, Zhe Li, Nay Myat Min, Hanxun Huang, Yunhan Zhao, Xingjun Ma, Yu-Gang Jiang, Jun Sun Published: 2026-03-08 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2603.07452v1 Backdoor mechanisms have traditionally been studied as security threats that compromise the integrity of machine learning models. However, the same mechanism -- the conditional activation of specific behaviors through input triggers -- can also serve as a controllable and auditable interface for trustworthy model behavior. In this work, we present \textbf{Backdoor4Good (B4G)}, a unified benchmark and framework for \textit{beneficial backdoor} applications in large language models (LLMs). Unlike conventional backdoor studies focused on attacks and defenses, B4G repurposes backdoor conditioning for Beneficial Tasks that enhance safety, controllability, and accountability. It formalizes beneficial backdoor learning under a triplet formulation $(T, A, U)$, representing the \emph{Trigger}, \emph{Activation mechanism}, and \emph{Utility function}, and implements a benchmark covering four trust-centric applications. Through extensive experiments across Llama3.1-8B, Gemma-2-9B, Qwen2.5-7B, and Llama2-13B, we show that beneficial backdoors can achieve high controllability, tamper-resistance, and stealthiness while preserving clean-task performance. Our findings demonstrate new insights that backdoors need not be inherently malicious; when properly designed, they can serve as modular, interpretable, and beneficial building blocks for trustworthy AI systems. Our code and datasets are available at https://github.com/bboylyg/BackdoorLLM/B4G. --- ### Dial: A Knowledge-Grounded Dialect-Specific NL2SQL System Authors: Xiang Zhang, Hongming Xu, Le Zhou, Wei Zhou, Xuanhe Zhou, Guoliang Li, Yuyu Luo, Changdong Liu, Guorun Chen, Jiang Liao, Fan Wu Published: 2026-03-08 Categories: cs.DB, cs.AI, cs.CL, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2603.07449v2 Enterprises commonly deploy heterogeneous database systems, each of which owns a distinct SQL dialect with different syntax rules, built-in functions, and execution constraints. However, most existing NL2SQL methods assume a single canonical dialect (e.g., SQLite) and struggle to produce queries that are both semantically correct and executable on target engines. Prompt-based approaches tightly couple intent reasoning with dialect syntax, rule-based translators often degrade native operators into generic constructs, and multi-dialect fine-tuning suffers from cross-dialect interference. In this paper, we present Dial, a knowledge-grounded framework for dialect-specific NL2SQL. Dial introduces: (1) a Dialect-Aware Logical Query Planning module that converts natural language into a dialect-aware logical query plan via operator-level intent decomposition and divergence-aware specification; (2) HINT-KB, a hierarchical intent-aware knowledge base that organizes dialect knowledge into i a Canonical Syntax Reference, ii a declarative function repository, and iii a procedural constraint repository; and (3) an execution-driven debugging and semantic verification loop that separates syntactic recovery from logic auditing to prevent semantic drift. We construct DS-NL2SQL, a benchmark covering six major database systems with 2,218 dialect-specific test cases. Experimental results show that Dial consistently improves translation accuracy by 10.25% and dialect feature coverage by 15.77% over state-of-the-art baselines. --- ### Dial: A Knowledge-Grounded Dialect-Specific NL2SQL System Authors: Xiang Zhang, Hongming Xu, Le Zhou, Wei Zhou, Xuanhe Zhou, Guoliang Li, Yuyu Luo, Changdong Liu, Guorun Chen, Jiang Liao, Fan Wu Published: 2026-03-08 Categories: cs.DB, cs.AI, cs.CL, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2603.07449v1 Enterprises commonly deploy heterogeneous database systems, each of which owns a distinct SQL dialect with different syntax rules, built-in functions, and execution constraints. However, most existing NL2SQL methods assume a single dialect (e.g., SQLite) and struggle to produce queries that are both semantically correct and executable on target engines. Prompt-based approaches tightly couple intent reasoning with dialect syntax, rule-based translators often degrade native operators into generic constructs, and multi-dialect fine-tuning suffers from cross-dialect interference. In this paper, we present Dial, a knowledge-grounded framework for dialect-specific NL2SQL. Dial introduces: (1) a Dialect-Aware Logical Query Planning module that converts natural language into a dialect-aware logical query plan via operator-level intent decomposition and divergence-aware specification; (2) HINT-KB, a hierarchical intent-aware knowledge base that organizes dialect knowledge into (i) a canonical syntax reference, (ii) a declarative function repository, and (iii) a procedural constraint repository; and (3) an execution-driven debugging and semantic verification loop that separates syntactic recovery from logic auditing to prevent semantic drift. We construct DS-NL2SQL, a benchmark covering six major database systems with 2,218 dialect-specific test cases. Experimental results show that Dial consistently improves translation accuracy by 10.25% and dialect feature coverage by 15.77% over state-of-the-art baselines. The code is at https://github.com/weAIDB/Dial. --- ### Discrete Tokenization Unlocks Transformers for Calibrated Tabular Forecasting Authors: Yael S. Elmatad Published: 2026-03-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.07448v1 Gradient boosting still dominates Transformers on tabular benchmarks. Our tokenizer uses a deliberately simplistic discretized vocabulary so we can highlight how even basic tokenization unlocks the power of attention on tabular features, yet it already outperforms tuned gradient boosting when combined with Gaussian smoothing. Our solution discretizes environmental context while smoothing labels with adaptive Gaussians, yielding calibrated PDFs. On 600K entities (5M training examples) we outperform tuned XGBoost by 10.8% (35.94s vs 40.31s median MAE) and achieve KS=0.0045 with the adaptive-sigma checkpoint selected to minimize KS rather than median MAE. Ablations confirm architecture matters: losing sequential ordering costs about 2.0%, dropping the time-delta tokens costs about 1.8%, and a stratified calibration analysis reveals where miscalibration persists. --- ### Few Tokens, Big Leverage: Preserving Safety Alignment by Constraining Safety Tokens during Fine-tuning Authors: Guoli Wang, Haonan Shi, Tu Ouyang, An Wang Published: 2026-03-08 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.07445v3 Large language models (LLMs) often require fine-tuning (FT) to perform well on downstream tasks, but FT can induce safety-alignment drift even when the training dataset contains only benign data. Prior work shows that introducing a small fraction of harmful data can substantially compromise LLM refusal behavior, causing LLMs to comply with harmful requests. Existing defense methods often rely on model-wide interventions, such as restricting which parameters are updated or injecting additional safety data, which can limit generality and degrade downstream task performance. To address these limitations, we propose a fine-tuning framework called Preserving Safety Alignment via Constrained Tokens (PACT), which stabilizes the model's confidence on safety tokens. Our approach is motivated by the empirical observation that safety-aligned behavior is reflected in the model's token-level output confidence and is often concentrated on a small subset of safety-related tokens. During downstream fine-tuning, we regularize the fine-tuned model to match the aligned reference model's confidence on safety-related tokens at each response step, while leaving non-safety tokens largely unconstrained to allow effective task adaptation. This targeted constraint prevents alignment drift without imposing global restrictions that typically trade off with model utility. Our code is available at {https://github.com/Glresearch1/PACT}. --- ### HLER: Human-in-the-Loop Economic Research via Multi-Agent Pipelines for Empirical Discovery Authors: Chen Zhu, Xiaolu Wang Published: 2026-03-08 Categories: cs.AI, econ.GN arXiv: https://arxiv.org/abs/2603.07444v1 Large language models (LLMs) have enabled agent-based systems that aim to automate scientific research workflows. Most existing approaches focus on fully autonomous discovery, where AI systems generate research ideas, conduct analyses, and produce manuscripts with minimal human involvement. However, empirical research in economics and the social sciences poses additional constraints: research questions must be grounded in available datasets, identification strategies require careful design, and human judgment remains essential for evaluating economic significance. We introduce HLER (Human-in-the-Loop Economic Research), a multi-agent architecture that supports empirical research automation while preserving critical human oversight. The system orchestrates specialized agents for data auditing, data profiling, hypothesis generation, econometric analysis, manuscript drafting, and automated review. A key design principle is dataset-aware hypothesis generation, where candidate research questions are constrained by dataset structure, variable availability, and distributional diagnostics, reducing infeasible or hallucinated hypotheses. HLER further implements a two-loop architecture: a question quality loop that screens and selects feasible hypotheses, and a research revision loop where automated review triggers re-analysis and manuscript revision. Human decision gates are embedded at key stages, allowing researchers to guide the automated pipeline. Experiments on three empirical datasets show that dataset-aware hypothesis generation produces feasible research questions in 87% of cases (versus 41% under unconstrained generation), while complete empirical manuscripts can be produced at an average API cost of $0.8-$1.5 per run. These results suggest that Human-AI collaborative pipelines may provide a practical path toward scalable empirical research. --- ### Med-Evo: Test-time Self-evolution for Medical Multimodal Large Language Models Authors: Dunyuan Xu, Xikai Yang, Juzheng Miao, Yaoqian Li, Jinpeng Li, Pheng-Ann Heng Published: 2026-03-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07443v1 Medical Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities across diverse healthcare tasks. However, current post-training strategies, such as supervised fine-tuning and reinforcement learning, heavily depend on substantial annotated data while overlooking the potential of unlabeled test data for model enhancement. This limitation becomes particularly pronounced in medical domains, where acquiring extensive labeled medical data is difficult due to the strict data sensitivity and annotation complexity. Moreover, leveraging test data poses challenges in generating reliable supervision signals from unlabeled samples and maintaining stable self-evolution. To address these limitations, we propose Med-Evo, the first self-evolution framework for medical MLLMs that utilizes label-free reinforcement learning to promote model performance without requiring additional labeled data. Our framework introduces two key innovations: $1)$ Feature-driven Pseudo Labeling (FPL) that identifies semantic centroids from all heterogeneous candidate responses to select pseudo labels in each rollout, and $2)$ Hard-Soft Reward (HSR) that combines exact match with token-level assessment and semantic similarity to provide hierarchical reward. Experiments on three medical VQA benchmarks and two base MLLMs show clear advantages of our approach over SOTA methods, with significant improvements of 10.43\% accuracy and 4.68\% recall on the SLAKE dataset using Qwen2.5-VL, showing the effectiveness of our method. --- ### DogWeave: High-Fidelity 3D Canine Reconstruction from a Single Image via Normal Fusion and Conditional Inpainting Authors: Shufan Sun, Chenchen Wang, Zongfu Yu Published: 2026-03-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07441v1 Monocular 3D animal reconstruction is challenging due to complex articulation, self-occlusion, and fine-scale details such as fur. Existing methods often produce distorted geometry and inconsistent textures due to the lack of articulated 3D supervision and limited availability of back-view images in 2D datasets, which makes reconstructing unobserved regions particularly difficult. To address these limitations, we propose DogWeave, a model-based framework for reconstructing high-fidelity 3D canine models from a single RGB image. DogWeave improves geometry by refining a coarsely-initiated parametric mesh into a detailed SDF representation through multi-view normal field optimization using diffusion-enhanced normals. It then generates view-consistent textures through conditional partial inpainting guided by structure and style cues, enabling realistic reconstruction of unobserved regions. Using only about 7,000 dog images processed via our 2D pipeline for training, DogWeave produces complete, realistic 3D models and outperforms state-of-the-art single image to 3d reconstruction methods in both shape accuracy and texture realism for canines. --- ### How Wrong Can Your Counterfactual Be? Quantifying Confounding Bias for Continuous Treatments without a Control Group Authors: Yu Wang, Xiangchen Liu, Siguang Li Published: 2026-03-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.07438v2 Stress testing poses a causal question: how would portfolio credit losses change if the macroeconomy followed an adverse counterfactual path? Yet standard practice remains predictive and might be therefore vulnerable to omitted-variable bias. We propose a partial identification framework for causal stress testing in panel data with a continuous common treatment and no control group. By assuming that the unobserved confounder affects outcome and macro variables additively, we derive a closed-form confounding envelope parameterized by two interpretable sensitivity parameters. We further analyze two practical estimators -- recursive rollout and direct multi-horizon prediction -- derive non-asymptotic error bounds, and characterize when recursive compounding makes direct estimation preferable. For inference, we combine the identification envelope with importance-weighted conformal prediction, yielding finite-sample intervals that separate estimation uncertainty from identification uncertainty under covariate shift. In semi-synthetic experiments built from real U.S. unemployment paths, standard high-accuracy predictive models remain causally biased and substantially under-cover, whereas the proposed framework achieves near-nominal coverage across stress horizons. ---