# Research Papers — 2026-03 · bundle page 59 of 243 > Full-text markdown of papers #2901–2950 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/59 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/58.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/60.md) ### FCL-COD: Weakly Supervised Camouflaged Object Detection with Frequency-aware and Contrastive Learning Authors: Jingchen Ni, Quan Zhang, Dan Jiang, Keyu Lv, Ke Zhang, Chun Yuan Published: 2026-03-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.22969v2 Existing camouflage object detection (COD) methods typically rely on fully-supervised learning guided by mask annotations. However, obtaining mask annotations is time-consuming and labor-intensive. Compared to fully-supervised methods, existing weakly-supervised COD methods exhibit significantly poorer performance. Even for the Segment Anything Model (SAM), there are still challenges in handling weakly-supervised camouflage object detection (WSCOD), such as: a. non-camouflage target responses, b. local responses, c. extreme responses, and d. lack of refined boundary awareness, which leads to unsatisfactory results in camouflage scenes. To alleviate these issues, we propose a frequency-aware and contrastive learning-based WSCOD framework in this paper, named FCL-COD. To mitigate the problem of non-camouflaged object responses, we propose the Frequency-aware Low-rank Adaptation (FoRA) method, which incorporates frequency-aware camouflage scene knowledge into SAM. To overcome the challenges of local and extreme responses, we introduce a gradient-aware contrastive learning approach that effectively delineates precise foreground-background boundaries. Additionally, to address the lack of refined boundary perception, we present a multi-scale frequency-aware representation learning strategy that facilitates the modeling of more refined boundaries. We validate the effectiveness of our approach through extensive empirical experiments on three widely recognized COD benchmarks. The results confirm that our method surpasses both state-of-the-art weakly supervised and even fully supervised techniques. --- ### Beyond Theoretical Bounds: Empirical Privacy Loss Calibration for Text Rewriting Under Local Differential Privacy Authors: Weijun Li, Arnaud Grivet Sébert, Qiongkai Xu, Annabelle McIver, Mark Dras Published: 2026-03-24 Categories: cs.CR, cs.CL arXiv: https://arxiv.org/abs/2603.22968v1 The growing use of large language models has increased interest in sharing textual data in a privacy-preserving manner. One prominent line of work addresses this challenge through text rewriting under Local Differential Privacy (LDP), where input texts are locally obfuscated before release with formal privacy guarantees. These guarantees are typically expressed by a parameter $\varepsilon$ that upper bounds the worst-case privacy loss. However, nominal $\varepsilon$ values are often difficult to interpret and compare across mechanisms. In this work, we investigate how to empirically calibrate across text rewriting mechanisms under LDP. We propose TeDA, which formulates calibration via a hypothesis-testing framework that instantiates text distinguishability audits in both surface and embedding spaces, enabling empirical assessment of indistinguishability from privatized texts. Applying this calibration to several representative mechanisms, we demonstrate that similar nominal $\varepsilon$ bounds can imply very different levels of distinguishability. Empirical calibration thus provides a more comparable footing for evaluating privacy-utility trade-offs, as well as a practical tool for mechanism comparison and analysis in real-world LDP text rewriting deployments. --- ### Set-Valued Prediction for Large Language Models with Feasibility-Aware Coverage Guarantees Authors: Ye Li, Anqi Hu, Yuanchang Ye, Shiyan Tong, Zhiyuan Wang, Bo Fu Published: 2026-03-24 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.22966v1 Large language models (LLMs) inherently operate over a large generation space, yet conventional usage typically reports the most likely generation (MLG) as a point prediction, which underestimates the model's capability: although the top-ranked response can be incorrect, valid answers may still exist within the broader output space and can potentially be discovered through repeated sampling. This observation motivates moving from point prediction to set-valued prediction, where the model produces a set of candidate responses rather than a single MLG. In this paper, we propose a principled framework for set-valued prediction, which provides feasibility-aware coverage guarantees. We show that, given the finite-sampling nature of LLM generation, coverage is not always achievable: even with multiple samplings, LLMs may fail to yield an acceptable response for certain questions within the sampled candidate set. To address this, we establish a minimum achievable risk level (MRL), below which statistical coverage guarantees cannot be satisfied. Building on this insight, we then develop a data-driven calibration procedure that constructs prediction sets from sampled responses by estimating a rigorous threshold, ensuring that the resulting set contains a correct answer with a desired probability whenever the target risk level is feasible. Extensive experiments on six language generation tasks with five LLMs demonstrate both the statistical validity and the predictive efficiency of our framework. --- ### Few-Shot Generative Model Adaption via Identity Injection and Preservation Authors: Yeqi He, Liang Li, Jiehua Zhang, Yaoqi Sun, Xichun Sheng, Zhidong Zhao, Chenggang Yan Published: 2026-03-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.22965v1 Training generative models with limited data presents severe challenges of mode collapse. A common approach is to adapt a large pretrained generative model upon a target domain with very few samples (fewer than 10), known as few-shot generative model adaptation. However, existing methods often suffer from forgetting source domain identity knowledge during adaptation, which degrades the quality of generated images in the target domain. To address this, we propose Identity Injection and Preservation (I$^2$P), which leverages identity injection and consistency alignment to preserve the source identity knowledge. Specifically, we first introduce an identity injection module that integrates source domain identity knowledge into the target domain's latent space, ensuring the generated images retain key identity knowledge of the source domain. Second, we design an identity substitution module, which includes a style-content decoupler and a reconstruction modulator, to further enhance source domain identity preservation. We enforce identity consistency constraints by aligning features from identity substitution, thereby preserving identity knowledge. Both quantitative and qualitative experiments show that our method achieves substantial improvements over state-of-the-art methods on multiple public datasets and 5 metrics. --- ### A PAC-Bayesian approach to generalization for quantum models Authors: Pablo Rodriguez-Grasa, Matthias C. Caro, Jens Eisert, Elies Gil-Fuster, Franz J. Schreiber, Carlos Bravo-Prieto Published: 2026-03-24 Categories: quant-ph, cond-mat.quant-gas, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2603.22964v1 Generalization is a central concept in machine learning theory, yet for quantum models, it is predominantly analyzed through uniform bounds that depend on a model's overall capacity rather than the specific function learned. These capacity-based uniform bounds are often too loose and entirely insensitive to the actual training and learning process. Previous theoretical guarantees have failed to provide non-uniform, data-dependent bounds that reflect the specific properties of the learned solution rather than the worst-case behavior of the entire hypothesis class. To address this limitation, we derive the first PAC-Bayesian generalization bounds for a broad class of quantum models by analyzing layered circuits composed of general quantum channels, which include dissipative operations such as mid-circuit measurements and feedforward. Through a channel perturbation analysis, we establish non-uniform bounds that depend on the norms of learned parameter matrices; we extend these results to symmetry-constrained equivariant quantum models; and we validate our theoretical framework with numerical experiments. This work provides actionable model design insights and establishes a foundational tool for a more nuanced understanding of generalization in quantum machine learning. --- ### Asymptotic Learning Curves for Diffusion Models with Random Features Score and Manifold Data Authors: Anand Jerry George, Nicolas Macris Published: 2026-03-24 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2603.22962v3 We study the theoretical behavior of denoising score matching--the learning task associated to diffusion models--when the data distribution is supported on a low-dimensional manifold and the score is parameterized using a random feature neural network. We derive asymptotically exact expressions for the test, train, and score errors in the high-dimensional limit. Our analysis reveals that, for linear manifolds the sample complexity required to learn the score function scales linearly with the intrinsic dimension of the manifold, rather than with the ambient dimension. Perhaps surprisingly, the benefits of low-dimensional structure starts to diminish once we have a non-linear manifold. These results indicate that diffusion models can benefit from structured data; however, the dependence on the specific type of structure is subtle and intricate. --- ### Stepwise Variational Inference with Vine Copulas Authors: Elisabeth Griesbauer, Leiv Rønneberg, Arnoldo Frigessi, Claudia Czado, Ingrid Hobæk Haff Published: 2026-03-24 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2603.22959v1 We propose stepwise variational inference (VI) with vine copulas: a universal VI procedure that combines vine copulas with a novel stepwise estimation procedure of the variational parameters. Vine copulas consist of a nested sequence of trees built from copulas, where more complex latent dependence can be modeled with increasing number of trees. We propose to estimate the vine copula approximate posterior in a stepwise fashion, tree by tree along the vine structure. Further, we show that the usual backward Kullback-Leibler divergence cannot recover the correct parameters in the vine copula model, thus the evidence lower bound is defined based on the Rényi divergence. Finally, an intuitive stopping criterion for adding further trees to the vine eliminates the need to pre-define a complexity parameter of the variational distribution, as required for most other approaches. Thus, our method interpolates between mean-field VI (MFVI) and full latent dependence. In many applications, in particular sparse Gaussian processes, our method is parsimonious with parameters, while outperforming MFVI. --- ### Privacy-Preserving EHR Data Transformation via Geometric Operators: A Human-AI Co-Design Technical Report Authors: Maolin Wang, Beining Bao, Gan Yuan, Hongyu Chen, Bingkun Zhao, Baoshuo Kan, Jiming Xu, Qi Shi, Yinggong Zhao, Yao Wang, Wei Ying Ma, Jun Yan Published: 2026-03-24 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2603.22954v1 Electronic health records (EHRs) and other real-world clinical data are essential for clinical research, medical artificial intelligence, and life science, but their sharing is severely limited by privacy, governance, and interoperability constraints. These barriers create persistent data silos that hinder multi-center studies, large-scale model development, and broader biomedical discovery. Existing privacy-preserving approaches, including multi-party computation and related cryptographic techniques, provide strong protection but often introduce substantial computational overhead, reducing the efficiency of large-scale machine learning and foundation-model training. In addition, many such methods make data usable for restricted computation while leaving them effectively invisible to clinicians and researchers, limiting their value in workflows that still require direct inspection, exploratory analysis, and human interpretation. We propose a real-world-data transformation framework for privacy-preserving sharing of structured clinical records. Instead of converting data into opaque representations, our approach constructs transformed numeric views that preserve medical semantics and major statistical properties while, under a clearly specified threat model, provably breaking direct linkage between those views and protected patient-level attributes. Through collaboration between computer scientists and the AI agent \textbf{SciencePal}, acting as a constrained tool inventor under human guidance, we design three transformation operators that are non-reversible within this threat model, together with an additional mixing strategy for high-risk scenarios, supported by theoretical analysis and empirical evaluation under reconstruction, record linkage, membership inference, and attribute inference attacks. --- ### Cluster-Wise Spatio-Temporal Masking for Efficient Video-Language Pretraining Authors: Weijun Zhuang, Yuqing Huang, Weikang Meng, Xin Li, Ming Liu, Xiaopeng Hong, Yaowei Wang, Wangmeng Zuo Published: 2026-03-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.22953v1 Large-scale video-language pretraining enables strong generalization across multimodal tasks but often incurs prohibitive computational costs. Although recent advances in masked visual modeling help mitigate this issue, they still suffer from two fundamental limitations: severe visual information loss under high masking ratios and temporal information leakage caused by inter-frame correlations. To address these challenges, we propose ClusterSTM, a Cluster-Wise Spatio-Temporal Masking strategy for efficient video-language pretraining. ClusterSTM first performs intra-frame clustering to partition visual tokens into multiple semantically independent clusters, then conducts cluster-wise masking by retaining the token with the highest temporal density within each cluster. Our masking strategy ensure that the retained tokens capture holistic video content while exhibit strong temporal correlation. Additionally, we introduce a video-text relevance reconstruction objective that aligns high-level multimodal semantics beyond conventional visual reconstruction. Extensive experiments across multiple benchmarks demonstrate that ClusterSTM achieves superior performance on video-text retrieval, video question answering, and video captioning tasks, establishing a new state-of-the-art among efficient video-language models. --- ### Weak-PDE-Net: Discovering Open-Form PDEs via Differentiable Symbolic Networks and Weak Formulation Authors: Xinxin Li, Xingyu Cui, Jin Qi, Juan Zhang, Da Li, Junping Yin Published: 2026-03-24 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.22951v1 Discovering governing Partial Differential Equations (PDEs) from sparse and noisy data is a challenging issue in data-driven scientific computing. Conventional sparse regression methods often suffer from two major limitations: (i) the instability of numerical differentiation under sparse and noisy data, and (ii) the restricted flexibility of a pre-defined candidate library. We propose Weak-PDE-Net, an end-to-end differentiable framework that can robustly identify open-form PDEs. Weak-PDE-Net consists of two interconnected modules: a forward response learner and a weak-form PDE generator. The learner embeds learnable Gaussian kernels within a lightweight MLP, serving as a surrogate model that adaptively captures system dynamics from sparse observations. Meanwhile, the generator integrates a symbolic network with an integral module to construct weak-form PDEs, avoiding explicit numerical differentiation and improving robustness to noise. To relax the constraints of the pre-defined library, we leverage Differentiable Neural Architecture Search strategy during training to explore the functional space, which enables the efficient discovery of open-form PDEs. The capability of Weak-PDE-Net in multivariable systems discovery is further enhanced by incorporating Galilean Invariance constraints and symmetry equivariance hypotheses to ensure physical consistency. Experiments on several challenging PDE benchmarks demonstrate that Weak-PDE-Net accurately recovers governing equations, even under highly sparse and noisy observations. --- ### Caption Generation for Dongba Paintings via Prompt Learning and Semantic Fusion Authors: Shuangwu Qian, Xiaochan Yuan, Pengfei Liu Published: 2026-03-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.22946v1 Dongba paintings, the treasured pictorial legacy of the Naxi people in southwestern China, feature richly layered visual elements, vivid color palettes, and pronounced ethnic and regional cultural symbolism, yet their automatic textual description remains largely unexplored owing to severe domain shift when mainstream captioning models are applied directly. This paper proposes \textbf{PVGF-DPC} (\textit{Prompt and Visual Semantic-Generation Fusion-based Dongba Painting Captioning}), an encoder-decoder framework that integrates a content prompt module with a novel visual semantic-generation fusion loss to bridge the gap between generic natural-image captioning and the culturally specific imagery found in Dongba art. A MobileNetV2 encoder extracts discriminative visual features, which are injected into the layer normalization of a 10-layer Transformer decoder initialized with pretrained BERT weights; meanwhile, the content prompt module maps the image feature vector to culture-aware labels -- such as \emph{deity}, \emph{ritual pattern}, or \emph{hell ghost} -- and constructs a post-prompt that steers the decoder toward thematically accurate descriptions. The visual semantic-generation fusion loss jointly optimizes the cross-entropy objectives of both the prompt predictor and the caption generator, encouraging the model to extract key cultural and visual cues and to produce captions that are semantically aligned with the input image. We construct a dedicated Dongba painting captioning dataset comprising 9{}408 augmented images with culturally grounded annotations spanning seven thematic categories. --- ### PersonalQ: Select, Quantize, and Serve Personalized Diffusion Models for Efficient Inference Authors: Qirui Wang, Qi Guo, Yiding Sun, Junkai Yang, Dongxu Zhang, Shanmin Pang, Qing Guo Published: 2026-03-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.22943v1 Personalized text-to-image generation lets users fine-tune diffusion models into repositories of concept-specific checkpoints, but serving these repositories efficiently is difficult for two reasons: natural-language requests are often ambiguous and can be misrouted to visually similar checkpoints, and standard post-training quantization can distort the fragile representations that encode personalized concepts. We present PersonalQ, a unified framework that connects checkpoint selection and quantization through a shared signal -- the checkpoint's trigger token. Check-in performs intent-aligned selection by combining intent-aware hybrid retrieval with LLM-based reranking over checkpoint context and asks a brief clarification question only when multiple intents remain plausible; it then rewrites the prompt by inserting the selected checkpoint's canonical trigger. Complementing this, Trigger-Aware Quantization (TAQ) applies trigger-aware mixed precision in cross-attention, preserving trigger-conditioned key/value rows (and their attention weights) while aggressively quantizing the remaining pathways for memory-efficient inference. Experiments show that PersonalQ improves intent alignment over retrieval and reranking baselines, while TAQ consistently offers a stronger compression-quality trade-off than prior diffusion PTQ methods, enabling scalable serving of personalized checkpoints without sacrificing fidelity. --- ### Optimizing Small Language Models for NL2SQL via Chain-of-Thought Fine-Tuning Authors: Anshul Solanki, Sanchit Latawa, Koushik Chakraborty, Navneet Kamboj Published: 2026-03-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.22942v1 Translating Natural Language to SQL (NL2SQL) remains a critical bottleneck for democratization of data in enterprises. Although Large Language Models (LLMs) like Gemini 2.5 and other LLMs have demonstrated impressive zero-shot capabilities, their high inference costs limit deployment at scale. This paper explores the efficacy of fine-tuning both large and small language models on NL2SQL tasks. Our research reveals a counter-intuitive scaling phenomenon. Fine-tuning large models (Gemini 2.5 Flash/Lite) on standard datasets yields negligible returns, often leading to overfitting on complex queries. Conversely, small models (Qwen) show significant gains. Fine-tuning improved the small model baseline from 36% to 45%, and further enriching the dataset with explicit Chain-of-Thought (CoT) reasoning surged accuracy to 54.5%(Fig 2). While this is still lower than the accuracy of large models like Gemini 2.5 , it does serve the business goal of significant cost reduction, latency in inference time and also meeting the business critical performance accuracy threshold.This paper demonstrates that transferring reasoning patterns enables compute-efficient smaller models to approach production-grade performance. --- ### FixationFormer: Direct Utilization of Expert Gaze Trajectories for Chest X-Ray Classification Authors: Daniel Beckmann, Benjamin Risse Published: 2026-03-24 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.22939v1 Expert eye movements provide a rich, passive source of domain knowledge in radiology, offering a powerful cue for integrating diagnostic reasoning into computer-aided analysis. However, direct integration into CNN-based systems, which historically have dominated the medical image analysis domain, is challenging: gaze recordings are sequential, temporally dense yet spatially sparse, noisy, and variable across experts. As a consequence, most existing image-based models utilize reduced representations such as heatmaps. In contrast, gaze naturally aligns with transformer architectures, as both are sequential in nature and rely on attention to highlight relevant input regions. In this work, we introduce FixationFormer, a transformer-based architecture that represents expert gaze trajectories as sequences of tokens, thereby preserving their temporal and spatial structure. By modeling gaze sequences jointly with image features, our approach addresses sparsity and variability in gaze data while enabling a more direct and fine-grained integration of expert diagnostic cues through explicit cross-attention between the image and gaze token sequences. We evaluate our method on three publicly available benchmark chest X-ray datasets and demonstrate that it achieves state-of-the-art classification performance, highlighting the value of representing gaze as a sequence in transformer-based medical image analysis. --- ### Ran Score: a LLM-based Evaluation Score for Radiology Report Generation Authors: Ran Zhang, Yucong Lin, Zhaoli Su, Bowen Liu, Danni Ai, Tianyu Fu, Deqiang Xiao, Jingfan Fan, Yuanyuan Wang, Mingwei Gao, Yuwan Hu, Shuya Gao et al. Published: 2026-03-24 Categories: cs.AI, cs.HC arXiv: https://arxiv.org/abs/2603.22935v1 Chest X-ray report generation and automated evaluation are limited by poor recognition of low-prevalence abnormalities and inadequate handling of clinically important language, including negation and ambiguity. We develop a clinician-guided framework combining human expertise and large language models for multi-label finding extraction from free-text chest X-ray reports and use it to define Ran Score, a finding-level metric for report evaluation. Using three non-overlapping MIMIC-CXR-EN cohorts from a public chest X-ray dataset and an independent ChestX-CN validation cohort, we optimize prompts, establish radiologist-derived reference labels and evaluate report generation models. The optimized framework improves the macro-averaged score from 0.753 to 0.956 on the MIMIC-CXR-EN development cohort, exceeds the CheXbert benchmark by 15.7 percentage points on directly comparable labels, and shows robust generalization on the ChestX-CN validation cohort. Here we show that clinician-guided prompt optimization improves agreement with a radiologist-derived reference standard and that Ran Score enables finding-level evaluation of report fidelity, particularly for low-prevalence abnormalities. --- ### ProGRank: Probe-Gradient Reranking to Defend Dense-Retriever RAG from Corpus Poisoning Authors: Xiangyu Yin, Yi Qi, Chih-Hong Cheng Published: 2026-03-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.22934v3 Retrieval-Augmented Generation (RAG) improves large language model applications by grounding generation in retrieved evidence, but also introduces corpus poisoning as a new attack surface. In this setting, an adversary injects or edits passages so that they enter the Top-$K$ results for target queries and influence downstream generation. Existing defences often rely on content filtering, auxiliary models, or generator-side reasoning, which complicates deployment. We propose ProGRank, a post hoc, training-free retriever-side defence for dense-retriever RAG. ProGRank stress-tests each query--passage pair under mild randomized perturbations, extracts probe gradients from a small fixed parameter subset, and derives two instability signals: representational consistency and dispersion risk. It then combines these signals with a score gate for reranking. ProGRank preserves the original passage content, requires no retraining, and supports a surrogate-based variant when the deployed retriever is unavailable. Experiments across datasets, retrievers, attacks, and retrieval-stage and end-to-end settings show that ProGRank improves robustness and maintains a favorable robustness--utility trade-off, including under adaptive evasive attacks. --- ### Quality Over Clicks: Iterative Reinforcement Learning for Early-Stage E-Commerce Query Suggestion Authors: Qi Sun, Kejun Xiao, Huaipeng Zhao, Tao Luo, Xiaoyi Zeng Published: 2026-03-24 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.22922v2 Existing dialogue systems rely on query suggestion to enhance user engagement. Recent approaches mainly optimize generative models using click-through rate (CTR) models to align with user preferences. However, these methods are less effective in early-stage deployment scenarios, where click feedback is sparse and insufficient for training a reliable CTR model. To bridge this gap, we propose QualEQS, a quality-first iterative reinforcement learning framework for e-commerce query suggestion. We formalize actionable suggestion quality along three dimensions that directly affect downstream usability: answerability, factuality, and information gain. To continuously improve from online traffic without click supervision, we further propose group-level disagreement among candidate suggestions to identify ambiguous query contexts and mine hard training cases for iterative refinement. We also introduce EQS-Benchmark, a dataset of 16,949 real-world e-commerce queries for offline training and evaluation. Experiments show that our quality-based offline metrics correlate strongly with online performance, providing a practical evaluation recipe for sparse-feedback deployment. In both offline and online settings, QualEQS consistently outperforms strong baselines, yielding a 6.81% improvement in online ChatPV in a real-world enterprise-level conversational shopping assistant system. --- ### The EU AI Act and the Rights-based Approach to Technological Governance Authors: Georgios Pavlidis Published: 2026-03-24 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2603.22920v1 The EU AI Act constitutes an important development in shaping the Union's digital regulatory architecture. The Act places fundamental rights at the heart of a risk-based governance framework. The article examines how the AI Act institutionalises a human-centric approach to AI and how the AI Act's provisions explicitly and implicitly embed the protection of rights enshrined in the EU Charter of Fundamental Rights. It argues that fundamental rights function not merely as aspirational goals, but as legal thresholds and procedural triggers across the lifecycle of an AI system. The analysis suggests that the AI Act has the potential to serve as a model for rights-preserving AI systems, while acknowledging that challenges will emerge at the level of implementation. --- ### EVA: Efficient Reinforcement Learning for End-to-End Video Agent Authors: Yaolun Zhang, Ruohui Wang, Jiahao Wang, Yepeng Tang, Xuanyu Zheng, Haonan Duan, Hao Lu, Hanming Deng, Lewei Lu Published: 2026-03-24 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.22918v2 Video understanding with multimodal large language models (MLLMs) remains challenging due to the long token sequences of videos, which contain extensive temporal dependencies and redundant frames. Existing approaches typically treat MLLMs as passive recognizers, processing entire videos or uniformly sampled frames without adaptive reasoning. Recent agent-based methods introduce external tools, yet still depend on manually designed workflows and perception-first strategies, resulting in inefficiency on long videos. We present EVA, an Efficient Reinforcement Learning framework for End-to-End Video Agent, which enables planning-before-perception through iterative summary-plan-action-reflection reasoning. EVA autonomously decides what to watch, when to watch, and how to watch, achieving query-driven and efficient video understanding. To train such agents, we design a simple yet effective three-stage learning pipeline - comprising supervised fine-tuning (SFT), Kahneman-Tversky Optimization (KTO), and Group Relative Policy Optimization (GRPO) - that bridges supervised imitation and reinforcement learning. We further construct high-quality datasets for each stage, supporting stable and reproducible training. We evaluate EVA on six video understanding benchmarks, demonstrating its comprehensive capabilities. Compared with existing baselines, EVA achieves a substantial improvement of 6-12% over general MLLM baselines and a further 1-3% gain over prior adaptive agent methods. --- ### When AVSR Meets Video Conferencing: Dataset, Degradation, and the Hidden Mechanism Behind Performance Collapse Authors: Yihuan Huang, Jun Xue, Liu Jiajun, Daixian Li, Tong Zhang, Zhuolin Yi, Yanzhen Ren, Kai Li Published: 2026-03-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.22915v1 Audio-Visual Speech Recognition (AVSR) has achieved remarkable progress in offline conditions, yet its robustness in real-world video conferencing (VC) remains largely unexplored. This paper presents the first systematic evaluation of state-of-the-art AVSR models across mainstream VC platforms, revealing severe performance degradation caused by transmission distortions and spontaneous human hyper-expression. To address this gap, we construct \textbf{MLD-VC}, the first multimodal dataset tailored for VC, comprising 31 speakers, 22.79 hours of audio-visual data, and explicit use of the Lombard effect to enhance human hyper-expression. Through comprehensive analysis, we find that speech enhancement algorithms are the primary source of distribution shift, which alters the first and second formants of audio. Interestingly, we find that the distribution shift induced by the Lombard effect closely resembles that introduced by speech enhancement, which explains why models trained on Lombard data exhibit greater robustness in VC. Fine-tuning AVSR models on MLD-VC mitigates this issue, achieving an average 17.5% reduction in CER across several VC platforms. Our findings and dataset provide a foundation for developing more robust and generalizable AVSR systems in real-world video conferencing. MLD-VC is available at https://huggingface.co/datasets/nccm2p2/MLD-VC. --- ### Multilingual KokoroChat: A Multi-LLM Ensemble Translation Method for Creating a Multilingual Counseling Dialogue Dataset Authors: Ryoma Suzuki, Zhiyang Qi, Michimasa Inaba Published: 2026-03-24 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.22913v2 To address the critical scarcity of high-quality, publicly available counseling dialogue datasets, we created Multilingual KokoroChat by translating KokoroChat, a large-scale manually authored Japanese counseling corpus, into both English and Chinese. A key challenge in this process is that the optimal model for translation varies by input, making it impossible for any single model to consistently guarantee the highest quality. In a sensitive domain like counseling, where the highest possible translation fidelity is essential, relying on a single LLM is therefore insufficient. To overcome this challenge, we developed and employed a novel multi-LLM ensemble method. Our approach first generates diverse hypotheses from multiple distinct LLMs. A single LLM then produces a high-quality translation based on an analysis of the respective strengths and weaknesses of all presented hypotheses. The quality of ``Multilingual KokoroChat'' was rigorously validated through human preference studies. These evaluations confirmed that the translations produced by our ensemble method were preferred from any individual state-of-the-art LLM. This strong preference confirms the superior quality of our method's outputs. The Multilingual KokoroChat is available at https://github.com/UEC-InabaLab/MultilingualKokoroChat. --- ### From the AI Act to a European AI Agency: Completing the Union's Regulatory Architecture Authors: Georgios Pavlidis Published: 2026-03-24 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2603.22912v1 As artificial intelligence (AI) technologies continue to advance, effective risk assessment, regulation, and oversight are necessary to ensure that AI development and deployment align with ethical principles while preserving innovation and economic competitiveness. The adoption of the EU AI Act marks an important step in this direction, establishing a harmonised legal framework that includes detailed provisions on AI governance, as well as the creation of the European AI Office. This paper revisits the question of whether a more robust supranational agency dedicated to AI is still warranted and explores how such a body could enhance policy coherence, improve risk assessment capacities, and foster international cooperation. It also argues that a strengthened EU-level agency would also serve the Union's strategic aim of securing digital and technological sovereignty. --- ### ForestPrune: High-ratio Visual Token Compression for Video Multimodal Large Language Models via Spatial-Temporal Forest Modeling Authors: Shaobo Ju, Baiyang Song, Tao Chen, Jiapeng Zhang, Qiong Wu, Chao Chang, HuaiXi Wang, Yiyi Zhou, Rongrong Ji Published: 2026-03-24 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.22911v2 Due to the great saving of computation and memory overhead, token compression has become a research hot-spot for MLLMs and achieved remarkable progress in image-language tasks. However, for the video, existing methods still fall short of high-ratio token compression. We attribute this shortcoming to the insufficient modeling of temporal and continual video content, and propose a novel and training-free token pruning method for video MLLMs, termed ForestPrune, which achieves effective and high-ratio pruning via Spatial-temporal Forest Modeling. In practice, ForestPrune construct token forests across video frames based on the semantic, spatial and temporal constraints, making an overall comprehension of videos. Afterwards, ForestPrune evaluates the importance of token trees and nodes based on tree depth and node roles, thereby obtaining a globally optimal pruning decision. To validate ForestPrune, we apply it to two representative video MLLMs, namely LLaVA-Video and LLaVA-OneVision, and conduct extensive experiments on a bunch of video benchmarks. The experimental results not only show the great effectiveness for video MLLMs, e.g., retaining 95.8% average accuracy while reducing 90% tokens for LLaVA-OneVision, but also show its superior performance and efficiency than the compared token compression methods, e.g., +10.1% accuracy on MLVU and -81.4% pruning time than FrameFusion on LLaVA-Video. --- ### EchoKV: Efficient KV Cache Compression via Similarity-Based Reconstruction Authors: Shiyu Ji, Yixuan Wang, Yijun Liu, Qingfu Zhu, Wanxiang Che Published: 2026-03-24 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.22910v2 The increasing memory demand of the Key-Value (KV) cache poses a significant bottleneck for Large Language Models (LLMs) in long-context applications. Existing low-rank KV compression methods reduce this footprint by modifying model projections, limiting the flexibility to switch back to standard full-cache inference when sufficient memory is available. In this paper, we propose EchoKV, a flexible KV cache compression framework that supports on-demand transitions from full KV caching to compressed caching. Unlike traditional compression-decompression paradigms, EchoKV utilizes a lightweight network to reconstruct the discarded KV components from a partial subset, exploiting intrinsic inter-layer and intra-layer similarities among attention heads. We further introduce a lightweight two-stage fine-tuning strategy, requiring only a few minutes on a single A100 GPU for a 7B model. Experimental results on LongBench and RULER demonstrate that EchoKV consistently outperforms existing methods across multiple compression ratios and backbone models while preserving the throughput of full-cache inference in short-context scenarios. --- ### Adaptive Dual-Teacher Distillation with Subnetwork Rectification for Bridging Semantic Gaps in Black-Box Domain Adaptation Authors: Zhe Zhang, Jing Li, Wanli Xue, Xu Cheng, Jianhua Zhang, Qinghua Hu, Shengyong Chen Published: 2026-03-24 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.22908v3 Assuming that neither source data nor source model parameters are accessible, black-box domain adaptation (BBDA) represents a highly practical yet challenging setting, where transferable knowledge is limited to the predictions of a black-box source model. Existing approaches exploit such knowledge via pseudo-label refinement or by leveraging vision-language models (ViLs), but they often fail to reconcile the inherent discrepancy between task-specific knowledge from black-box models and language-aligned semantic priors of ViLs, resulting in suboptimal integration and degraded adaptation performance. To address this challenge, we propose adaptive Dual-Teacher Distillation with Subnetwork Rectification (DDSR), a framework that explicitly reconciles these complementary yet inconsistent knowledge sources. DDSR employs an adaptive prediction fusion strategy to integrate predictions from the black-box source model and a ViL, generating reliable pseudo-labels for the target domain. A subnetwork-based regularization mechanism mitigates overfitting to noisy supervision by enforcing output consistency and gradient divergency. Furthermore, progressively improved target predictions iteratively refine both pseudo-labels and ViL prompts, enhancing semantic alignment. Finally, class-wise prototypes are used to further optimize target predictions via self-training. Extensive experiments on multiple benchmark datasets demonstrate that DDSR consistently outperforms state-of-the-art methods, including those with access to source data or source model parameters. --- ### Separating Diagnosis from Control: Auditable Policy Adaptation in Agent-Based Simulations with LLM-Based Diagnostics Authors: Shaoxin Zhong, Yuchen Su, Michael Witbrock Published: 2026-03-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.22904v1 Mitigating elderly loneliness requires policy interventions that achieve both adaptability and auditability. Existing methods struggle to reconcile these objectives: traditional agent-based models suffer from static rigidity, while direct large language model (LLM) controllers lack essential traceability. This work proposes a three-layer framework that separates diagnosis from control to achieve both properties simultaneously. LLMs operate strictly as diagnostic instruments that assess population state and generate structured risk evaluations, while deterministic formulas with explicit bounds translate these assessments into traceable parameter updates. This separation ensures that every policy decision can be attributed to inspectable rules while maintaining adaptive response to emergent needs. We validate the framework through systematic ablation across five experimental conditions in elderly care simulation. Results demonstrate that explicit control rules outperform end-to-end black-box LLM approaches by 11.7\% while preserving full auditability, confirming that transparency need not compromise adaptive performance. --- ### Off-Policy Evaluation and Learning for Survival Outcomes under Censoring Authors: Kohsuke Kubota, Mitsuhiro Takahashi, Yuta Saito Published: 2026-03-24 Categories: stat.ME, cs.AI, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2603.22900v1 Optimizing survival outcomes, such as patient survival or customer retention, is a critical objective in data-driven decision-making. Off-Policy Evaluation~(OPE) provides a powerful framework for assessing such decision-making policies using logged data alone, without the need for costly or risky online experiments in high-stakes applications. However, typical estimators are not designed to handle right-censored survival outcomes, as they ignore unobserved survival times beyond the censoring time, leading to systematic underestimation of the true policy performance. To address this issue, we propose a novel framework for OPE and Off-Policy Learning~(OPL) tailored for survival outcomes under censoring. Specifically, we introduce IPCW-IPS and IPCW-DR, which employ the Inverse Probability of Censoring Weighting technique to explicitly deal with censoring bias. We theoretically establish that our estimators are unbiased and that IPCW-DR achieves double robustness, ensuring consistency if either the propensity score or the outcome model is correct. Furthermore, we extend this framework to constrained OPL to optimize policy value under budget constraints. We demonstrate the effectiveness of our proposed methods through simulation studies and illustrate their practical impacts using public real-world data for both evaluation and learning tasks. --- ### SLARM: Streaming and Language-Aligned Reconstruction Model for Dynamic Scenes Authors: Zhicheng Qiu, Jiarui Meng, Tong-an Luo, Yican Huang, Xuan Feng, Xuanfu Li, ZHan Xu Published: 2026-03-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.22893v3 We propose SLARM, a feed-forward model that unifies dynamic scene reconstruction, semantic understanding, and real-time streaming inference. SLARM captures complex, non-uniform motion through higher-order motion modeling, trained solely on differentiable renderings without any flow supervision. Besides, SLARM distills semantic features from LSeg to obtain language-aligned representations. This design enables semantic querying via natural language, and the tight coupling between semantics and geometry further enhances the accuracy and robustness of dynamic reconstruction. Moreover, SLARM processes image sequences using window-based causal attention, achieving stable, low-latency streaming inference without accumulating memory cost. Within this unified framework, SLARM achieves state-of-the-art results in dynamic estimation, rendering quality, and scene parsing, improving motion accuracy by 21%, reconstruction PSNR by 1.6 dB, and segmentation mIoU by 20% over existing methods. --- ### VLGOR: Visual-Language Knowledge Guided Offline Reinforcement Learning for Generalizable Agents Authors: Pengsen Liu, Maosen Zeng, Nan Tang, Kaiyuan Li, Jing-Cheng Pang, Yunan Liu, Yang Yu Published: 2026-03-24 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.22892v1 Combining Large Language Models (LLMs) with Reinforcement Learning (RL) enables agents to interpret language instructions more effectively for task execution. However, LLMs typically lack direct perception of the physical environment, which limits their understanding of environmental dynamics and their ability to generalize to unseen tasks. To address this limitation, we propose Visual-Language Knowledge-Guided Offline Reinforcement Learning (VLGOR), a framework that integrates visual and language knowledge to generate imaginary rollouts, thereby enriching the interaction data. The core premise of VLGOR is to fine-tune a vision-language model to predict future states and actions conditioned on an initial visual observation and high-level instructions, ensuring that the generated rollouts remain temporally coherent and spatially plausible. Furthermore, we employ counterfactual prompts to produce more diverse rollouts for offline RL training, enabling the agent to acquire knowledge that facilitates following language instructions while grounding in environments based on visual cues. Experiments on robotic manipulation benchmarks demonstrate that VLGOR significantly improves performance on unseen tasks requiring novel optimal policies, achieving a success rate over 24% higher than the baseline methods. --- ### Conditionally Identifiable Latent Representation for Multivariate Time Series with Structural Dynamics Authors: Minkey Chang, Jae-Young Kim Published: 2026-03-24 Categories: cs.LG, q-fin.GN, q-fin.ST arXiv: https://arxiv.org/abs/2603.22886v1 We propose the Identifiable Variational Dynamic Factor Model (iVDFM), which learns latent factors from multivariate time series with identifiability guarantees. By applying iVAE-style conditioning to the innovation process driving the dynamics rather than to the latent states, we show that factors are identifiable up to permutation and component-wise affine (or monotone invertible) transformations. Linear diagonal dynamics preserve this identifiability and admit scalable computation via companion-matrix and Krylov methods. We demonstrate improved factor recovery on synthetic data, stable intervention accuracy on synthetic SCMs, and competitive probabilistic forecasting on real-world benchmarks. --- ### A Heterogeneous Long-Micro Scale Cascading Architecture for General Aviation Health Management Authors: Xinhang Chen, Zhihuan Wei, Yang Hu, Zhiguo Zeng, Kang Zeng, Wei Wang Published: 2026-03-24 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.22885v5 BACKGROUND: General aviation fleet expansion demands intelligent health monitoring under computational constraints. Real-world aircraft health diagnosis requires balancing accuracy with computational constraints under extreme class imbalance and environmental uncertainty. Existing end-to-end approaches suffer from the receptive field paradox: global attention introduces excessive operational heterogeneity noise for fine-grained fault classification, while localized constraints sacrifice critical cross-temporal context essential for anomaly detection. METHODS: This paper presents an AI-driven heterogeneous cascading architecture for general aviation health management. The proposed Long-Micro Scale Diagnostician (LMSD) explicitly decouples global anomaly detection (full-sequence attention) from micro-scale fault classification (restricted receptive fields), resolving the receptive field paradox while minimizing training overhead. A knowledge distillation-based interpretability module provides physically traceable explanations for safety-critical validation. RESULTS: Experiments on the public National General Aviation Flight Information Database (NGAFID) dataset (28,935 flights, 36 categories) demonstrate 4--8% improvement in safety-critical metrics (MCWPM) with 4.2 times training acceleration and 46% model compression compared to end-to-end baselines. CONCLUSIONS: The AI-driven heterogeneous architecture offers deployable solutions for aviation equipment health management, with potential for digital twin integration in future work. The proposed framework substantiates deployability in resource-constrained aviation environments while maintaining stringent safety requirements. --- ### Group Editing: Edit Multiple Images in One Go Authors: Yue Ma, Xinyu Wang, Qianli Ma, Qinghe Wang, Mingzhe Zheng, Xiangpeng Yang, Hao Li, Chongbo Zhao, Jixuan Ying, Harry Yang, Hongyu Liu, Qifeng Chen Published: 2026-03-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.22883v3 In this paper, we tackle the problem of performing consistent and unified modifications across a set of related images. This task is particularly challenging because these images may vary significantly in pose, viewpoint, and spatial layout. Achieving coherent edits requires establishing reliable correspondences across the images, so that modifications can be applied accurately to semantically aligned regions. To address this, we propose GroupEditing, a novel framework that builds both explicit and implicit relationships among images within a group. On the explicit side, we extract geometric correspondences using VGGT, which provides spatial alignment based on visual features. On the implicit side, we reformulate the image group as a pseudo-video and leverage the temporal coherence priors learned by pre-trained video models to capture latent relationships. To effectively fuse these two types of correspondences, we inject the explicit geometric cues from VGGT into the video model through a novel fusion mechanism. To support large-scale training, we construct GroupEditData, a new dataset containing high-quality masks and detailed captions for numerous image groups. Furthermore, to ensure identity preservation during editing, we introduce an alignment-enhanced RoPE module, which improves the model's ability to maintain consistent appearance across multiple images. Finally, we present GroupEditBench, a dedicated benchmark designed to evaluate the effectiveness of group-level image editing. Extensive experiments demonstrate that GroupEditing significantly outperforms existing methods in terms of visual quality, cross-view consistency, and semantic alignment. --- ### TreeTeaming: Autonomous Red-Teaming of Vision-Language Models via Hierarchical Strategy Exploration Authors: Chunxiao Li, Lijun Li, Jing Shao Published: 2026-03-24 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2603.22882v1 The rapid advancement of Vision-Language Models (VLMs) has brought their safety vulnerabilities into sharp focus. However, existing red teaming methods are fundamentally constrained by an inherent linear exploration paradigm, confining them to optimizing within a predefined strategy set and preventing the discovery of novel, diverse exploits. To transcend this limitation, we introduce TreeTeaming, an automated red teaming framework that reframes strategy exploration from static testing to a dynamic, evolutionary discovery process. At its core lies a strategic Orchestrator, powered by a Large Language Model (LLM), which autonomously decides whether to evolve promising attack paths or explore diverse strategic branches, thereby dynamically constructing and expanding a strategy tree. A multimodal actuator is then tasked with executing these complex strategies. In the experiments across 12 prominent VLMs, TreeTeaming achieves state-of-the-art attack success rates on 11 models, outperforming existing methods and reaching up to 87.60\% on GPT-4o. The framework also demonstrates superior strategic diversity over the union of previously public jailbreak strategies. Furthermore, the generated attacks exhibit an average toxicity reduction of 23.09\%, showcasing their stealth and subtlety. Our work introduces a new paradigm for automated vulnerability discovery, underscoring the necessity of proactive exploration beyond static heuristics to secure frontier AI models. --- ### Confidence Calibration under Ambiguous Ground Truth Authors: Linwei Tao, Haoyang Luo, Minjing Dong, Chang Xu Published: 2026-03-24 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.22879v1 Confidence calibration assumes a unique ground-truth label per input, yet this assumption fails wherever annotators genuinely disagree. Post-hoc calibrators fitted on majority-voted labels, the standard single-label targets used in practice, can appear well-calibrated under conventional evaluation yet remain substantially miscalibrated against the underlying annotator distribution. We show that this failure is structural: under simplifying assumptions, Temperature Scaling is biased toward temperatures that underestimate annotator uncertainty, with true-label miscalibration increasing monotonically with annotation entropy. To address this, we develop a family of ambiguity-aware post-hoc calibrators that optimise proper scoring rules against the full label distribution and require no model retraining. Our methods span progressively weaker annotation requirements: Dirichlet-Soft leverages the full annotator distribution and achieves the best overall calibration quality across settings; Monte Carlo Temperature Scaling with a single annotation per example (MCTS S=1) matches full-distribution calibration across all benchmarks, demonstrating that pre-aggregated label distributions are unnecessary; and Label-Smooth Temperature Scaling (LS-TS) operates with voted labels alone by constructing data-driven pseudo-soft targets from the model's own confidence. Experiments on four benchmarks with real multi-annotator distributions (CIFAR-10H, ChaosNLI) and clinically-informed synthetic annotations (ISIC~2019, DermaMNIST) show that Dirichlet-Soft reduces true-label ECE by 55-87% relative to Temperature Scaling, while LS-TS reduces ECE by 9-77% without any annotator data. --- ### Continuous Optimization for Satisfiability Modulo Theories on Linear Real Arithmetic Authors: Yunuo Cen, Daniel Ebler, Xuanyao Fong Published: 2026-03-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.22877v1 Efficient solutions for satisfiability modulo theories (SMT) are integral in industrial applications such as hardware verification and design automation. Existing approaches are predominantly based on conflict-driven clause learning, which is structurally difficult to parallelize and therefore scales poorly. In this work, we introduce FourierSMT as a scalable and highly parallelizable continuous-variable optimization framework for SMT. We generalize the Walsh-Fourier expansion (WFE), called extended WFE (xWFE), from the Boolean domain to a mixed Boolean-real domain, which allows the use of gradient methods for SMT. This addresses the challenge of finding satisfying variable assignments to high-arity constraints by local updates of discrete variables. To reduce the evaluation complexity of xWFE, we present the extended binary decision diagram (xBDD) and map the constraints from xWFE to xBDDs. We then show that sampling the circuit-output probability (COP) of xBDDs under randomized rounding is equivalent to the expectation value of the xWFEs. This allows for efficient computation of the constraints. We show that the reduced problem is guaranteed to converge and preserves satisfiability, ensuring the soundness of the solutions. The framework is benchmarked for large-scale scheduling and placement problems with up to 10,000 variables and 700,000 constraints, achieving 8-fold speedups compared to state-of-the-art SMT solvers. These results pave the way for GPU-based optimization of SMTs with continuous systems. --- ### Grounding Sim-to-Real Generalization in Robotic Manipulation: An Empirical Study with Vision-Language-Action Models Authors: Ruixing Jin, Zicheng Zhu, Ruixiang Ouyang, Sheng Xu, Bo Yue, Zhizheng Wu, Guiliang Liu Published: 2026-03-24 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2603.22876v2 Learning a generalist control policy for robotic manipulation typically relies on large-scale datasets. Given the high cost of real-world data collection, a practical alternative is to generate synthetic data through simulation. However, the resulting synthetic data often exhibits a significant gap from real-world distributions. While many prior studies have proposed algorithms to bridge the Sim-to-Real discrepancy, there remains a lack of principled research that grounds these methods in real-world manipulation tasks, particularly their performance on generalist policies such as Vision-Language-Action (VLA) models. In this study, we empirically examine the primary determinants of Sim-to-Real generalization across four dimensions: multi-level domain randomization, photorealistic rendering, physics-realistic modeling, and reinforcement learning updates. To support this study, we design a comprehensive evaluation protocol to quantify the real-world performance of manipulation tasks. The protocol accounts for key variations in background, lighting, distractors, object types, and spatial features. Through experiments involving over 10k real-world trials, we derive critical insights into Sim-to-Real transfer. To inform and advance future studies, we release both the robotic platforms and the evaluation protocol for public access to facilitate independent verification, thereby establishing a realistic and standardized benchmark for robotic manipulation policies. --- ### Template-Based Feature Aggregation Network for Industrial Anomaly Detection Authors: Wei Luo, Haiming Yao, Wenyong Yu Published: 2026-03-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.22874v1 Industrial anomaly detection plays a crucial role in ensuring product quality control. Therefore, proposing an effective anomaly detection model is of great significance. While existing feature-reconstruction methods have demonstrated excellent performance, they face challenges with shortcut learning, which can lead to undesirable reconstruction of anomalous features. To address this concern, we present a novel feature-reconstruction model called the \textbf{T}emplate-based \textbf{F}eature \textbf{A}ggregation \textbf{Net}work (TFA-Net) for anomaly detection via template-based feature aggregation. Specifically, TFA-Net first extracts multiple hierarchical features from a pre-trained convolutional neural network for a fixed template image and an input image. Instead of directly reconstructing input features, TFA-Net aggregates them onto the template features, effectively filtering out anomalous features that exhibit low similarity to normal template features. Next, TFA-Net utilizes the template features that have already fused normal features in the input features to refine feature details and obtain the reconstructed feature map. Finally, the defective regions can be located by comparing the differences between the input and reconstructed features. Additionally, a random masking strategy for input features is employed to enhance the overall inspection performance of the model. Our template-based feature aggregation schema yields a nontrivial and meaningful feature reconstruction task. The simple, yet efficient, TFA-Net exhibits state-of-the-art detection performance on various real-world industrial datasets. Additionally, it fulfills the real-time demands of industrial scenarios, rendering it highly suitable for practical applications in the industry. Code is available at https://github.com/luow23/TFA-Net. --- ### ForeSea: AI Forensic Search with Multi-modal Queries for Video Surveillance Authors: Hyojin Park, Yi Li, Janghoon Cho, Sungha Choi, Jungsoo Lee, Taotao Jing, Shuai Zhang, Munawar Hayat, Dashan Gao, Ning Bi, Fatih Porikli Published: 2026-03-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.22872v2 Despite decades of work, surveillance still struggles in searching and reasoning about specific targets across long, multi-camera videos. Existing methods - tracking, retrieval, and video LLMs require heavy manual filtering, capture only shallow attributes, and fail at temporal understanding. Prior benchmarks are also limited to basic retrieval and question answering, without addressing real world challenges that often involve multimodal queries and temporal grounding (e.g., "When did this person join the fight?" with the person's image). To address this gap, we introduce ForeSeaQA, a new benchmark specifically designed for video QA with image-and-text queries and timestamped annotations of key events. The dataset consists of long-horizon surveillance footage paired with diverse multimodal questions, enabling systematic evaluation of retrieval, temporal grounding, and multimodal reasoning in realistic forensic conditions. Not limited to this benchmark, we propose ForeSea, an AI forensic search system with a 3-stage, plug-and-play pipeline. (1) A tracking module filters irrelevant footage; (2) a multimodal embedding module indexes the remaining clips; and (3) during inference, the system retrieves top-K candidate clips for a video LLM to answer queries and localize events. On ForeSeaQA benchmark, ForeSea improves accuracy by 3.1 points and temporal IoU by 10.1 points over prior retrieval-augmented baselines. To our knowledge, ForeSeaQA is the first benchmark to support complex multimodal queries with precise temporal grounding, and ForeSea is the first VideoRAG system built to excel in this setting. --- ### Dynamical Systems Theory Behind a Hierarchical Reasoning Model Authors: Vasiliy A. Es'kin, Mikhail E. Smorkalov Published: 2026-03-24 Categories: cs.AI, cs.LG, math.DS arXiv: https://arxiv.org/abs/2603.22871v1 Current large language models (LLMs) primarily rely on linear sequence generation and massive parameter counts, yet they severely struggle with complex algorithmic reasoning. While recent reasoning architectures, such as the Hierarchical Reasoning Model (HRM) and Tiny Recursive Model (TRM), demonstrate that compact recursive networks can tackle these tasks, their training dynamics often lack rigorous mathematical guarantees, leading to instability and representational collapse. We propose the Contraction Mapping Model (CMM), a novel architecture that reformulates discrete recursive reasoning into continuous Neural Ordinary and Stochastic Differential Equations (NODEs/NSDEs). By explicitly enforcing the convergence of the latent phase point to a stable equilibrium state and mitigating feature collapse with a hyperspherical repulsion loss, the CMM provides a mathematically grounded and highly stable reasoning engine. On the Sudoku-Extreme benchmark, a 5M-parameter CMM achieves a state-of-the-art accuracy of 93.7 %, outperforming the 27M-parameter HRM (55.0 %) and 5M-parameter TRM (87.4 %). Remarkably, even when aggressively compressed to an ultra-tiny footprint of just 0.26M parameters, the CMM retains robust predictive power, achieving 85.4 % on Sudoku-Extreme and 82.2 % on the Maze benchmark. These results establish a new frontier for extreme parameter efficiency, proving that mathematically rigorous latent dynamics can effectively replace brute-force scaling in artificial reasoning. --- ### Designing to Forget: Deep Semi-parametric Models for Unlearning Authors: Amber Yijia Zheng, Yu-Shan Tai, Raymond A. Yeh Published: 2026-03-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.22870v1 Recent advances in machine unlearning have focused on developing algorithms to remove specific training samples from a trained model. In contrast, we observe that not all models are equally easy to unlearn. Hence, we introduce a family of deep semi-parametric models (SPMs) that exhibit non-parametric behavior during unlearning. SPMs use a fusion module that aggregates information from each training sample, enabling explicit test-time deletion of selected samples without altering model parameters. Empirically, we demonstrate that SPMs achieve competitive task performance to parametric models in image classification and generation, while being significantly more efficient for unlearning. Notably, on ImageNet classification, SPMs reduce the prediction gap relative to a retrained (oracle) baseline by $11\%$ and achieve over $10\times$ faster unlearning compared to existing approaches on parametric models. The code is available at https://github.com/amberyzheng/spm_unlearning. --- ### Chain-of-Authorization: Embedding authorization into large language models Authors: Yang Li, Yule Liu, Xinlei He, Youjian Zhao, Qi Li, Ke Xu Published: 2026-03-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.22869v2 Although Large Language Models (LLMs) have evolved from text generators into the cognitive core of modern AI systems, their inherent lack of authorization awareness exposes these systems to catastrophic risks, ranging from unintentional data leakage to unauthorized command execution. Existing defense mechanisms are fundamentally decoupled from internal reasoning, rendering them insufficient for the complex security demands of dynamic AI systems. Here, we propose the Chain-of-Authorization (CoA) framework, a paradigm that internalizes access control as a foundational cognitive capability. By systematically redesigning the input-output format and fine-tuning the model on synthesized data with complex permission topologies, CoA forces the model to generate a structured authorization trajectory as a causal prerequisite for any substantive response or action, thereby enabling LLMs to internalize access boundaries within dynamic reasoning environments. CoA maintains high utility in authorized scenarios while achieving high rejection rates of unauthorized prompts and robust defense against diverse adversarial attacks. By embedding authorization directly into the reasoning process, CoA provides a principled architectural blueprint for deploying secure LLMs as the cognitive cores of modern AI systems. --- ### Agent-Sentry: Bounding LLM Agents via Execution Provenance Authors: Rohan Sequeira, Stavros Damianakis, Umar Iqbal, Konstantinos Psounis Published: 2026-03-24 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2603.22868v2 Agentic computing systems, while immensely capable, raise serious security, privacy, and safety concerns. A key issue is that the full set of functionalities offered by these systems, combined with their probabilistic execution flows, is not known beforehand. Given this lack of characterization, it is challenging to validate whether a system has successfully carried out the user's intended task or instead executed irrelevant actions, potentially as a consequence of compromise. We present \emph{Agent Sentry}, a runtime defense that learns a bound on an agent's benign execution from prior legitimate executions and flags any action that falls outside this bound. Agent Sentry layers three complementary checks: a structural classifier over the sequence of actions and the provenance of each function's arguments; a deterministic allowlist check over sensitive argument values; and an LLM judge, invoked only on the residual of actions where the first two checks cannot safely decide between a legitimate new request and a carefully crafted injection. We demonstrate the effectiveness of Agent Sentry in AgentDojo and AgentDyn by blocking 94.3\% of successful injections while allowing 95.1\% of benign executions, without modifying the agent, its tools, or the LLM. --- ### TRINE: A Token-Aware, Runtime-Adaptive FPGA Inference Engine for Multimodal AI Authors: Hyunwoo Oh, Hanning Chen, Sanggeon Yun, Yang Ni, Suyeon Jang, Behnam Khaleghi, Fei Wen, Mohsen Imani Published: 2026-03-24 Categories: cs.AR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.22867v1 Multimodal stacks that mix ViTs, CNNs, GNNs, and transformer NLP strain embedded platforms because their compute/memory patterns diverge and hard real-time targets leave little slack. TRINE is a single-bitstream FPGA accelerator and compiler that executes end-to-end multimodal inference without reconfiguration. Layers are unified as DDMM/SDDMM/SpMM and mapped to a mode-switchable engine that toggles at runtime among weight/output-stationary systolic, 1xCS SIMD, and a routable adder tree (RADT) on a shared PE array. A width-matched, two-stage top-k unit enables in-stream token pruning, while dependency-aware layer offloading (DALO) overlaps independent kernels across reconfigurable processing units to sustain utilization. Evaluated on Alveo U50 and ZCU104, TRINE reduces latency by up to 22.57x vs. RTX 4090 and 6.86x vs. Jetson Orin Nano at 20-21 W; token pruning alone yields up to 7.8x on ViT-heavy pipelines, and DALO contributes up to 79% throughput improvement. With int8 quantization, accuracy drops remain <2.5% across representative tasks, delivering state-of-the-art latency and energy efficiency for unified vision, language, and graph workloads-in one bitstream. --- ### The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration Authors: Haoyuan Xu, Chang Li, Xinyan Ma, Xianhao Ou, Zihan Zhang, Tao He, Xiangyu Liu, Zixiang Wang, Jiafeng Liang, Zheng Chu, Runxuan Liu, Rongchuan Mu et al. Published: 2026-03-24 Categories: cs.SE, cs.CL arXiv: https://arxiv.org/abs/2603.22862v2 Tool use enables large language models (LLMs) to access external information, invoke software systems, and act in digital environments beyond what can be solved from model parameters alone. Early research mainly studied whether a model could select and execute a correct single tool call. As agent systems evolve, however, the central problem has shifted from isolated invocation to multi-tool orchestration over long trajectories with intermediate state, execution feedback, changing environments, and practical constraints such as safety, cost, and verifiability. We comprehensively review recent progress in multi-tool LLM agents and analyzes the state of the art in this rapidly developing area. First, we unify task formulations and distinguish single-call tool use from long-horizon orchestration. Then, we organize the literature around six core dimensions: inference-time planning and execution, training and trajectory construction, safety and control, efficiency under resource constraints, capability completeness in open environments, and benchmark design and evaluation. We further summarize representative applications in software engineering, enterprise workflows, graphical user interfaces, and mobile systems. Finally, we discuss major challenges and outline future directions for building reliable, scalable, and verifiable multi-tool agents. --- ### A Feature Shuffling and Restoration Strategy for Universal Unsupervised Anomaly Detection Authors: Wei Luo, Haiming Yao, Zhenfeng Qiang, Xiaotian Zhang, Weihang Zhang Published: 2026-03-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.22861v1 Unsupervised anomaly detection is vital in industrial fields, with reconstruction-based methods favored for their simplicity and effectiveness. However, reconstruction methods often encounter an identical shortcut issue, where both normal and anomalous regions can be well reconstructed and fail to identify outliers. The severity of this problem increases with the complexity of the normal data distribution. Consequently, existing methods may exhibit excellent detection performance in a specific scenario, but their performance sharply declines when transferred to another scenario. This paper focuses on establishing a universal model applicable to anomaly detection tasks across different settings, termed as universal anomaly detection. In this work, we introduce a novel, straightforward yet efficient framework for universal anomaly detection: \uline{F}eature \uline{S}huffling and \uline{R}estoration (FSR), which can alleviate the identical shortcut issue across different settings. First and foremost, FSR employs multi-scale features with rich semantic information as reconstruction targets, rather than raw image pixels. Subsequently, these multi-scale features are partitioned into non-overlapping feature blocks, which are randomly shuffled and then restored to their original state using a restoration network. This simple paradigm encourages the model to focus more on global contextual information. Additionally, we introduce a novel concept, the shuffling rate, to regulate the complexity of the FSR task, thereby alleviating the identical shortcut across different settings. Furthermore, we provide theoretical explanations for the effectiveness of FSR framework from two perspectives: network structure and mutual information. Extensive experimental results validate the superiority and efficiency of the FSR framework across different settings.Code is available at https://github.com/luow23/FSR. --- ### The Coordinate System Problem in Persistent Structural Memory for Neural Architectures Authors: Abhinaba Basu Published: 2026-03-24 Categories: cs.LG, cs.AI, cs.NE, q-bio.NC arXiv: https://arxiv.org/abs/2603.22858v1 We introduce the Dual-View Pheromone Pathway Network (DPPN), an architecture that routes sparse attention through a persistent pheromone field over latent slot transitions, and use it to discover two independent requirements for persistent structural memory in neural networks. Through five progressively refined experiments using up to 10 seeds per condition across 5 model variants and 4 transfer targets, we identify a core principle: persistent memory requires a stable coordinate system, and any coordinate system learned jointly with the model is inherently unstable. We characterize three obstacles -- pheromone saturation, surface-structure entanglement, and coordinate incompatibility -- and show that neither contrastive updates, multi-source distillation, Hungarian alignment, nor semantic decomposition resolves the instability when embeddings are learned from scratch. Fixed random Fourier features provide extrinsic coordinates that are stable, structure-blind, and informative, but coordinate stability alone is insufficient: routing-bias pheromone does not transfer (10 seeds, p>0.05). DPPN outperforms transformer and random sparse baselines for within-task learning (AULC 0.700 vs 0.680 vs 0.670). Replacing routing bias with learning-rate modulation eliminates negative transfer: warm pheromone as a learning-rate prior achieves +0.003 on same-family tasks (17 seeds, p<0.05) while never reducing performance. A structure completion function over extrinsic coordinates produces +0.006 same-family bonus beyond regularization, showing the catch-22 between stability and informativeness is partially permeable to learned functions. The contribution is two independent requirements for persistent structural memory: (a) coordinate stability and (b) graceful transfer mechanism. --- ### TorR: Towards Brain-Inspired Task-Oriented Reasoning via Cache-Oriented Algorithm-Architecture Co-design Authors: Hyunwoo Oh, SungHeon Jeong, Suyeon Jang, Hanning Chen, Sanggeon Yun, Tamoghno Das, Mohsen Imani Published: 2026-03-24 Categories: cs.AR, cs.LG arXiv: https://arxiv.org/abs/2603.22855v1 Task-oriented object detection (TOOD) atop CLIP offers open-vocabulary, prompt-driven semantics, yet dense per-window computation and heavy memory traffic hinder real-time, power-limited edge deployment. We present \emph{TorR}, a brain-inspired \textbf{algorithm--architecture co-design} that \textbf{replaces CLIP-style dense alignment with a hyperdimensional (HDC) associative reasoner} and turns temporal coherence into reuse. On the \emph{algorithm} side, TorR reformulates alignment as HDC similarity and graph composition, introducing \emph{partial-similarity reuse} via (i) query caching with per-class score accumulation, (ii) exact $δ$-updates when only a small set of hypervector bits change, and (iii) similarity/load-gated bypass under high system load. On the \emph{architecture} side, TorR instantiates a lane-scalable, bit-sliced item memory with bank/precision gating and a lightweight controller that schedules bypass/$δ$/full paths to meet RT-30/RT-60 targets as object counts vary. Synthesized in a TSMC 28\,nm process and exercised with a cycle-accurate simulator, TorR sustains real-time throughput with millijoule-scale energy per window ($\approx$50\,mJ at 60\,FPS; $\approx$113\,mJ at 30\,FPS) and low latency jitter, while delivering competitive AP@0.5 across five task prompts (mean 44.27\%) within a bounded margin to strong VLM baselines, but at orders-of-magnitude lower energy. The design exposes deployment-time configurability (effective dimension $D'$, thresholds, precision) to trade accuracy, latency, and energy for edge budgets. --- ### Avoiding Over-smoothing in Social Media Rumor Detection with Pre-trained Propagation Tree Transformer Authors: Chaoqun Cui, Caiyan Jia Published: 2026-03-24 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.22854v1 Deep learning techniques for rumor detection typically utilize Graph Neural Networks (GNNs) to analyze post relations. These methods, however, falter due to over-smoothing issues when processing rumor propagation structures, leading to declining performance. Our investigation into this issue reveals that over-smoothing is intrinsically tied to the structural characteristics of rumor propagation trees, in which the majority of nodes are 1-level nodes. Furthermore, GNNs struggle to capture long-range dependencies within these trees. To circumvent these challenges, we propose a Pre-Trained Propagation Tree Transformer (P2T3) method based on pure Transformer architecture. It extracts all conversation chains from a tree structure following the propagation direction of replies, utilizes token-wise embedding to infuse connection information and introduces necessary inductive bias, and pre-trains on large-scale unlabeled datasets. Experiments indicate that P2T3 surpasses previous state-of-the-art methods in multiple benchmark datasets and performs well under few-shot conditions. P2T3 not only avoids the over-smoothing issue inherent in GNNs but also potentially offers a large model or unified multi-modal scheme for future social media research. --- ### Agent Audit: A Security Analysis System for LLM Agent Applications Authors: Haiyue Zhang, Yi Nian, Yue Zhao Published: 2026-03-24 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2603.22853v1 What should a developer inspect before deploying an LLM agent: the model, the tool code, the deployment configuration, or all three? In practice, many security failures in agent systems arise not from model weights alone, but from the surrounding software stack: tool functions that pass untrusted inputs to dangerous operations, exposed credentials in deployment artifacts, and over-privileged Model Context Protocol (MCP) configurations. We present Agent Audit, a security analysis system for LLM agent applications. Agent Audit analyzes Python agent code and deployment artifacts through an agent-aware pipeline that combines dataflow analysis, credential detection, structured configuration parsing, and privilege-risk checks. The system reports findings in terminal, JSON, and SARIF formats, enabling direct integration with local development workflows and CI/CD pipelines. On a benchmark of 22 samples with 42 annotated vulnerabilities, Agent Audit detects 40 vulnerabilities with 6 false positives, substantially improving recall over common SAST baselines while maintaining sub-second scan times. Agent Audit is open source and installable via pip, making security auditing accessible for agent systems. In the live demonstration, attendees scan vulnerable agent repositories and observe how Agent Audit identifies security risks in tool functions, prompts, and more. Findings are linked to source locations and configuration paths, and can be exported into VS Code and GitHub Code Scanning for interactive inspection. --- ### Gau-Occ: Geometry-Completed Gaussians for Multi-Modal 3D Occupancy Prediction Authors: Chengxin Lv, Yihui Li, Hongyu Yang, YunHong Wang Published: 2026-03-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.22852v1 3D semantic occupancy prediction is crucial for autonomous driving. While multi-modal fusion improves accuracy over vision-only methods, it typically relies on computationally expensive dense voxel or BEV tensors. We present Gau-Occ, a multi-modal framework that bypasses dense volumetric processing by modeling the scene as a compact collection of semantic 3D Gaussians. To ensure geometric completeness, we propose a LiDAR Completion Diffuser (LCD) that recovers missing structures from sparse LiDAR to initialize robust Gaussian anchors. Furthermore, we introduce Gaussian Anchor Fusion (GAF), which efficiently integrates multi-view image semantics via geometry-aligned 2D sampling and cross-modal alignment. By refining these compact Gaussian descriptors, Gau-Occ captures both spatial consistency and semantic discriminability. Extensive experiments across challenging benchmarks demonstrate that Gau-Occ achieves state-of-the-art performance with significant computational efficiency. ---