# Research Papers — 2026-03 · bundle page 152 of 243 > Full-text markdown of papers #7551–7600 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/152 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/151.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/153.md) ### InSpatio-WorldFM: An Open-Source Real-Time Generative Frame Model Authors: InSpatio Team, Donghui Shen, Guofeng Zhang, Haomin Liu, Haoyu Ji, Jialin Liu, Jing Guo, Nan Wang, Siji Pan, Weihong Pan, Weijian Xie, Xiaojun Xiang et al. Published: 2026-03-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.11911v3 We present InSpatio-WorldFM, an open-source real-time frame model for spatial intelligence. Unlike video-based world models that rely on sequential frame generation and incur substantial latency due to window-level processing, InSpatio-WorldFM adopts a frame-based paradigm that generates each frame independently, enabling low-latency real-time spatial inference. By enforcing multi-view spatial consistency through explicit 3D anchors and implicit spatial memory, the model preserves global scene geometry while maintaining fine-grained visual details across viewpoint changes. We further introduce a progressive three-stage training pipeline that transforms a pretrained image diffusion model into a controllable frame model and finally into a real-time generator through few-step distillation. Experimental results show that InSpatio-WorldFM achieves strong multi-view consistency while supporting interactive exploration on consumer-grade GPUs, providing an efficient alternative to traditional video-based world models for real-time world simulation. --- ### Deep Generative Transformers for Probabilistic Time Series and Spatiotemporal Forecasting Authors: Rajdeep Pathak, Rahul Goswami, Madhurima Panja, Palash Ghosh, Tanujit Chakraborty Published: 2026-03-12 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2603.11909v2 Reliable uncertainty quantification is paramount for forecasting multivariate time series and spatiotemporal data. While Transformer architectures excel at sequence modeling, current probabilistic approaches typically rely on restrictive parametric likelihoods or quantile-based objectives, thereby limiting their ability to capture complex joint distributions in correlated time series. To overcome these limitations, we propose \textit{Enformer} and its spatiotemporal extension, \textit{GEnformer}. These models synthesize the expressive power of Transformers with engression, a stochastic learning paradigm for modeling conditional distributions. By injecting stochastic noise and optimizing a strictly proper scoring objective, our frameworks directly learn conditional predictive distributions without imposing parametric assumptions. This design ensures the generation of coherent multivariate trajectories while maintaining the Transformer's efficacy in modeling long-range dependencies and cross-series interactions. The probabilistic capability of Enformer is achieved with an asymptotic overhead of only a constant factor over a deterministic Transformer with an identical configuration. We extensively evaluate our frameworks on prominent multivariate benchmarks for temporal dynamics and real-world epidemic datasets for spatiotemporal dynamics. Empirical results demonstrate that both frameworks yield calibrated probabilistic forecasts and consistently outperform state-of-the-art baselines. --- ### Causal Representation Learning with Optimal Compression under Complex Treatments Authors: Wanting Liang, Haoang Chi, Zhiheng Zhang Published: 2026-03-12 Categories: cs.LG, stat.ME arXiv: https://arxiv.org/abs/2603.11907v2 Estimating Individual Treatment Effects (ITE) in multi-treatment scenarios faces two critical challenges: the Hyperparameter Selection Dilemma for balancing weights and the Curse of Dimensionality in computational scalability. This paper derives a novel multi-treatment generalization bound and proposes a theoretical estimator for the optimal balancing weight $α$, eliminating expensive heuristic tuning. We investigate three balancing strategies: Pairwise, One-vs-All (OVA), and Treatment Aggregation. While OVA achieves superior precision in low-dimensional settings, our proposed Treatment Aggregation ensures both accuracy and O(1) scalability as the treatment space expands. Furthermore, we extend our framework to a generative architecture, Multi-Treatment CausalEGM, which preserves the Wasserstein geodesic structure of the treatment manifold. Experiments on semi-synthetic and image datasets demonstrate that our approach significantly outperforms traditional models in estimation accuracy and efficiency, particularly in large-scale intervention scenarios. --- ### FlexRec: Adapting LLM-based Recommenders for Flexible Needs via Reinforcement Learning Authors: Yijun Pan, Weikang Qiu, Qiyao Ma, Mingxuan Ju, Tong Zhao, Neil Shah, Rex Ying Published: 2026-03-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.11901v1 Modern recommender systems must adapt to dynamic, need-specific objectives for diverse recommendation scenarios, yet most traditional recommenders are optimized for a single static target and struggle to reconfigure behavior on demand. Recent advances in reinforcement-learning-based post-training have unlocked strong instruction-following and reasoning capabilities in LLMs, suggesting a principled route for aligning them to complex recommendation goals. Motivated by this, we study closed-set autoregressive ranking, where an LLM generates a permutation over a fixed candidate set conditioned on user context and an explicit need instruction. However, applying RL to this setting faces two key obstacles: (i) sequence-level rewards yield coarse credit assignment that fails to provide fine-grained training signals, and (ii) interaction feedback is sparse and noisy, which together lead to inefficient and unstable updates. We propose FlexRec, a post-training RL framework that addresses both issues with (1) a causally grounded item-level reward based on counterfactual swaps within the remaining candidate pool, and (2) critic-guided, uncertainty-aware scaling that explicitly models reward uncertainty and down-weights low-confidence rewards to stabilize learning under sparse supervision. Across diverse recommendation scenarios and objectives, FlexRec achieves substantial gains: it improves NDCG@5 by up to \textbf{59\%} and Recall@5 by up to \textbf{109.4\%} in need-specific ranking, and further achieves up to \textbf{24.1\%} Recall@5 improvement under generalization settings, outperforming strong traditional recommenders and LLM-based baselines. --- ### Think While Watching: Online Streaming Segment-Level Memory for Multi-Turn Video Reasoning in Multimodal Large Language Models Authors: Lu Wang, Zhuoran Jin, Yupu Hao, Yubo Chen, Kang Liu, Yulong Ao, Jun Zhao Published: 2026-03-12 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.11896v1 Multimodal large language models (MLLMs) have shown strong performance on offline video understanding, but most are limited to offline inference or have weak online reasoning, making multi-turn interaction over continuously arriving video streams difficult. Existing streaming methods typically use an interleaved perception-generation paradigm, which prevents concurrent perception and generation and leads to early memory decay as streams grow, hurting long-range dependency modeling. We propose Think While Watching, a memory-anchored streaming video reasoning framework that preserves continuous segment-level memory during multi-turn interaction. We build a three-stage, multi-round chain-of-thought dataset and adopt a stage-matched training strategy, while enforcing strict causality through a segment-level streaming causal mask and streaming positional encoding. During inference, we introduce an efficient pipeline that overlaps watching and thinking and adaptively selects the best attention backend. Under both single-round and multi-round streaming input protocols, our method achieves strong results. Built on Qwen3-VL, it improves single-round accuracy by 2.6% on StreamingBench and by 3.79% on OVO-Bench. In the multi-round setting, it maintains performance while reducing output tokens by 56%. Code is available at: https://github.com/wl666hhh/Think_While_Watching/ --- ### Single-View Rolling-Shutter SfM Authors: Sofía Errázuriz Muñoz, Kim Kiehn, Petr Hruby, Kathlén Kohn Published: 2026-03-12 Categories: cs.CV, math.AG arXiv: https://arxiv.org/abs/2603.11888v1 Rolling-shutter (RS) cameras are ubiquitous, but RS SfM (structure-from-motion) has not been fully solved yet. This work suggests an approach to remedy this: We characterize RS single-view geometry of observed world points or lines. Exploiting this geometry, we describe which motion and scene parameters can be recovered from a single RS image and systematically derive minimal reconstruction problems. We evaluate several representative cases with proof-of-concept solvers, highlighting both feasibility and practical limitations. --- ### Bielik-Minitron-7B: Compressing Large Language Models via Structured Pruning and Knowledge Distillation for the Polish Language Authors: Remigiusz Kinas, Paweł Kiszczak, Sergio P. Perez, Krzysztof Ociepa, Łukasz Flis, Krzysztof Wróbel, Adrian Gwoździej Published: 2026-03-12 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.11881v1 This report details the creation of Bielik-Minitron-7B, a compressed 7.35B parameter version of the Bielik-11B-v3.0 model, specifically optimized for European languages. By leveraging a two-stage compression methodology inspired by the NVIDIA Minitron approach, we combined structured hybrid pruning and knowledge distillation to reduce the model's parameter count by 33.4%, from 11.04B to 7.35B. We utilized the NVIDIA Model Optimizer for structural pruning and the NVIDIA NeMo Framework for logit-based distillation for quality recovery. Following distillation, the model underwent a rigorous alignment pipeline consisting of Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO-P), and Reinforcement Learning (GRPO). Our final model successfully recovered approximately 90% of the baseline model's performance while providing up to 50% inference speedup. This approach demonstrates an efficient pathway to create language models for less-represented languages, preserving the original model quality while reducing inference deployment costs. --- ### The Mirror Design Pattern: Strict Data Geometry over Model Scale for Prompt Injection Detection Authors: J Alex Corll Published: 2026-03-12 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2603.11875v2 Prompt injection defenses are often framed as semantic understanding problems and delegated to increasingly large neural detectors. For the first screening layer, however, the requirements are different: the detector runs on every request and therefore must be fast, deterministic, non-promptable, and auditable. We introduce Mirror, a data-curation design pattern that organizes prompt injection corpora into matched positive and negative cells so that a classifier learns control-plane attack mechanics rather than incidental corpus shortcuts. Using 5,000 strictly curated open-source samples -- the largest corpus supportable under our public-data validity contract -- we define a 32-cell mirror topology, fill 31 of those cells with public data, train a sparse character n-gram linear SVM, compile its weights into a static Rust artifact, and obtain 95.97\% recall and 92.07\% F1 on a 524-case holdout at sub-millisecond latency with no external model runtime dependencies. On the same holdout, our next line of defense, a 22-million-parameter Prompt Guard~2 model reaches 44.35\% recall and 59.14\% F1 at 49\,ms median and 324\,ms p95 latency. Linear models still leave residual semantic ambiguities such as use-versus-mention for later pipeline layers, but within that scope our results show that for L1 prompt injection screening, strict data geometry can matter more than model scale. --- ### An Evolutionary Algorithm with Probabilistic Annealing for Large-scale Sparse Multi-objective Optimization Authors: Shuai Shao, Yuhao Sun, Xing Chen, Ye Tian, Guan Wang, Jin Li Published: 2026-03-12 Categories: cs.NE arXiv: https://arxiv.org/abs/2603.11874v1 Large-scale sparse multi-objective optimization problems (LSMOPs) are prevalent in real-world applications, where optimal solutions typically contain only a few nonzero variables, such as in adversarial attacks, critical node detection, and sparse signal reconstruction. Since the function evaluation of LSMOPs often relies on large-scale datasets involving a large number of decision variables, the search space becomes extremely high-dimensional. The coexistence of sparsity and high dimensionality greatly intensifies the conflict between exploration and exploitation, making it difficult for existing multi-objective evolutionary algorithms (MOEAs) to identify the critical nonzero decision variables within limited function evaluations. To address this challenge, this paper proposes an evolutionary algorithm with probabilistic annealing for large-scale sparse multi-objective optimization. The algorithm is driven by two probability vectors with distinct entropy characteristics: a convergence-oriented probability vector with relatively low entropy ensures stable exploitation, whereas an annealed probability vector with gradually decreasing entropy enables an adaptive transition from global exploration to local refinement. By integrating these complementary search dynamics, the proposed algorithm achieves a dynamic equilibrium between exploration and exploitation. Experimental results on benchmark problems and real-world applications demonstrate that the proposed algorithm outperforms state-of-the-art evolutionary algorithms in terms of both convergence and diversity. --- ### AdaFuse: Accelerating Dynamic Adapter Inference via Token-Level Pre-Gating and Fused Kernel Optimization Authors: Qiyang Li, Rui Kong, Yuchen Li, Hengyi Cai, Shuaiqiang Wang, Linghe Kong, Guihai Chen, Dawei Yin Published: 2026-03-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.11873v1 The integration of dynamic, sparse structures like Mixture-of-Experts (MoE) with parameter-efficient adapters (e.g., LoRA) is a powerful technique for enhancing Large Language Models (LLMs). However, this architectural enhancement comes at a steep cost: despite minimal increases in computational load, the inference latency often skyrockets, leading to decoding speeds slowing by over 2.5 times. Through a fine-grained performance analysis, we pinpoint the primary bottleneck not in the computation itself, but in the severe overhead from fragmented, sequential CUDA kernel launches required for conventional dynamic routing. To address this challenge, we introduce AdaFuse, a framework built on a tight co-design between the algorithm and the underlying hardware system to enable efficient dynamic adapter execution. Departing from conventional layer-wise or block-wise routing, AdaFuse employs a token-level pre-gating strategy, which makes a single, global routing decision for all adapter layers before a token is processed. This "decide-once, apply-everywhere" approach effectively staticizes the execution path for each token, creating an opportunity for holistic optimization. We capitalize on this by developing a custom CUDA kernel that performs a fused switching operation, merging the parameters of all selected LoRA adapters into the backbone model in a single, efficient pass. Experimental results on popular open-source LLMs show that AdaFuse achieves accuracy on par with state-of-the-art dynamic adapters while drastically cutting decoding latency by a factor of over 2.4x, thereby bridging the gap between model capability and inference efficiency. --- ### ELISA: An Interpretable Hybrid Generative AI Agent for Expression-Grounded Discovery in Single-Cell Genomics Authors: Omar Coser Published: 2026-03-12 Categories: q-bio.GN, cs.AI arXiv: https://arxiv.org/abs/2603.11872v3 Translating single-cell RNA sequencing (scRNA-seq) data into mechanistic biological hypotheses remains a critical bottleneck, as agentic AI systems lack direct access to transcriptomic representations while expression foundation models remain opaque to natural language. Here we introduce ELISA (Embedding-Linked Interactive Single-cell Agent), an interpretable framework that unifies scGPT expression embeddings with BioBERT-based semantic retrieval and LLM-mediated interpretation for interactive single-cell discovery. An automatic query classifier routes inputs to gene marker scoring, semantic matching, or reciprocal rank fusion pipelines depending on whether the query is a gene signature, natural language concept, or mixture of both. Integrated analytical modules perform pathway activity scoringacross 60+ gene sets, ligand-receptor interaction prediction using 280+ curated pairs, condition-aware comparative analysis, and cell-type proportion estimation all operating directly on embedded data without access to the original count matrix. Benchmarked across six diverse scRNA-seq datasets spanning inflammatory lung disease, pediatric and adult cancers, organoid models, healthy tissue, and neurodevelopment, ELISA significantly outperforms CellWhisperer, a classical lexical retriever (BM25), and a random baseline in cell type retrieval (combined permutation test, $p < 2\times10^{-5}$ for each), with particularly large gains on gene-signature queries (Cohen's $d = 5.98$ for MRR). ELISA replicates published biological findings (mean composite score 0.88), and generates candidate hypotheses through grounded LLM reasoning, bridging the gap between transcriptomic data exploration and biological discovery. --- ### On the Role of Reversible Instance Normalization Authors: Gaspard Berthelier, Tahar Nabil, Etienne Le Naour, Richard Niamke, Samir Perlaza, Giovanni Neglia Published: 2026-03-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.11869v1 Data normalization is a crucial component of deep learning models, yet its role in time series forecasting remains insufficiently understood. In this paper, we identify three central challenges for normalization in time series forecasting: temporal input distribution shift, spatial input distribution shift, and conditional output distribution shift. In this context, we revisit the widely used Reversible Instance Normalization (RevIN), by showing through ablation studies that several of its components are redundant or even detrimental. Based on these observations, we draw new perspectives to improve RevIN's robustness and generalization. --- ### Data Fusion with Distributional Equivalence Test-then-pool Authors: Linying Yang, Xing Liu, Robin J. Evans Published: 2026-03-12 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2603.11867v2 Randomized controlled trials (RCTs) are the gold standard for causal inference, yet practical constraints often limit the size of the concurrent control arm. Borrowing control data from previous trials offers a potential efficiency gain, but naive borrowing can induce bias when historical and current populations differ. Existing test-then-pool (TTP) procedures address this concern by testing for equality of control outcomes between historical and concurrent trials before borrowing; however, standard implementations may suffer from reduced power or inadequate control of the Type-I error rate. We develop a new TTP framework that fuses control arms while rigorously controlling the Type-I error rate of the final treatment effect test. Our method employs kernel two-sample testing via maximum mean discrepancy (MMD) to capture distributional differences, and equivalence testing to avoid introducing uncontrolled bias, providing a more flexible and informative criterion for pooling. To ensure valid inference, we introduce partial bootstrap and partial permutation procedures for approximating null distributions in the presence of heterogeneous controls. We further establish the overall validity and consistency. We provide empirical studies demonstrating that the proposed approach achieves higher power than standard TTP methods while maintaining nominal error control, highlighting its value as a principled tool for leveraging historical controls in modern clinical trials. --- ### Derain-Agent: A Plug-and-Play Agent Framework for Rainy Image Restoration Authors: Zhaocheng Yu, Xiang Chen, Runzhe Li, Zihan Geng, Guanglu Sun, Haipeng Li, Kui Jiang Published: 2026-03-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.11866v1 While deep learning has advanced single-image deraining, existing models suffer from a fundamental limitation: they employ a static inference paradigm that fails to adapt to the complex, coupled degradations (e.g., noise artifacts, blur, and color deviation) of real-world rain. Consequently, restored images often exhibit residual artifacts and inconsistent perceptual quality. In this work, we present Derain-Agent, a plug-and-play refinement framework that transitions deraining from static processing to dynamic, agent-based restoration. Derain-Agent equips a base deraining model with two core capabilities: 1) a Planning Network that intelligently schedules an optimal sequence of restoration tools for each instance, and 2) a Strength Modulation mechanism that applies these tools with spatially adaptive intensity. This design enables precise, region-specific correction of residual errors without the prohibitive cost of iterative search. Our method demonstrates strong generalization, consistently boosting the performance of state-of-the-art deraining models on both synthetic and real-world benchmarks. --- ### Social, Legal, Ethical, Empathetic and Cultural Norm Operationalisation for AI Agents Authors: Radu Calinescu, Ana Cavalcanti, Marsha Chechik, Lina Marsso, Beverley Townsend Published: 2026-03-12 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2603.11864v1 As AI agents are increasingly used in high-stakes domains like healthcare and law enforcement, aligning their behaviour with social, legal, ethical, empathetic, and cultural (SLEEC) norms has become a critical engineering challenge. While international frameworks have established high-level normative principles for AI, a significant gap remains in translating these abstract principles into concrete, verifiable requirements. To address this gap, we propose a systematic SLEEC-norm operationalisation process for determining, validating, implementing, and verifying normative requirements. Furthermore, we survey the landscape of methods and tools supporting this process, and identify key remaining challenges and research avenues for addressing them. We thus establish a framework - and define a research and policy agenda - for developing AI agents that are not only functionally useful but also demonstrably aligned with human norms and values. --- ### CreativeBench: Benchmarking and Enhancing Machine Creativity via Self-Evolving Challenges Authors: Zi-Han Wang, Lam Nguyen, Zhengyang Zhao, Mengyue Yang, Chengwei Qin, Yujiu Yang, Linyi Yang Published: 2026-03-12 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.11863v2 The saturation of high-quality pre-training data has shifted research focus toward evolutionary systems capable of continuously generating novel artifacts, leading to the success of AlphaEvolve. However, the progress of such systems is hindered by the lack of rigorous, quantitative evaluation. To tackle this challenge, we introduce CreativeBench, a benchmark for evaluating machine creativity in code generation, grounded in a classical cognitive framework. Comprising two subsets -- CreativeBench-Combo and CreativeBench-Explore -- the benchmark targets combinatorial and exploratory creativity through an automated pipeline utilizing reverse engineering and self-play. By leveraging executable code, CreativeBench objectively distinguishes creativity from hallucination via a unified metric defined as the product of quality and novelty. Our analysis of state-of-the-art models reveals distinct behaviors: (1) scaling significantly improves combinatorial creativity but yields diminishing returns for exploration; (2) larger models exhibit ``convergence-by-scaling,'' becoming more correct but less divergent; and (3) reasoning capabilities primarily benefit constrained exploration rather than combination. Finally, we propose EvoRePE, a plug-and-play inference-time steering strategy that internalizes evolutionary search patterns to consistently enhance machine creativity. --- ### You Told Me to Do It: Measuring Instructional Text-induced Private Data Leakage in LLM Agents Authors: Ching-Yu Kao, Xinfeng Li, Shenyu Dai, Tianze Qiu, Pengcheng Zhou, Eric Hanchen Jiang, Philip Sperl Published: 2026-03-12 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2603.11862v1 High-privilege LLM agents that autonomously process external documentation are increasingly trusted to automate tasks by reading and executing project instructions, yet they are granted terminal access, filesystem control, and outbound network connectivity with minimal security oversight. We identify and systematically measure a fundamental vulnerability in this trust model, which we term the \emph{Trusted Executor Dilemma}: agents execute documentation-embedded instructions, including adversarial ones, at high rates because they cannot distinguish malicious directives from legitimate setup guidance. This vulnerability is a structural consequence of the instruction-following design paradigm, not an implementation bug. To structure our measurement, we formalize a three-dimensional taxonomy covering linguistic disguise, structural obfuscation, and semantic abstraction, and construct \textbf{ReadSecBench}, a benchmark of 500 real-world README files enabling reproducible evaluation. Experiments on the commercially deployed computer-use agent show end-to-end exfiltration success rates up to 85\%, consistent across five programming languages and three injection positions. Cross-model evaluation on four LLM families in a simulation environment confirms that semantic compliance with injected instructions is consistent across model families. A 15-participant user study yields a 0\% detection rate across all participants, and evaluation of 12 rule-based and 6 LLM-based defenses shows neither category achieves reliable detection without unacceptable false-positive rates. Together, these results quantify a persistent \emph{Semantic-Safety Gap} between agents' functional compliance and their security awareness, establishing that documentation-embedded instruction injection is a persistent and currently unmitigated threat to high-privilege LLM agent deployments. --- ### Multi-Station WiFi CSI Sensing Framework Robust to Station-wise Feature Missingness and Limited Labeled Data Authors: Keita Kayano, Takayuki Nishio, Daiki Yoda, Yuta Hirai, Tomoko Adachi Published: 2026-03-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.11858v2 We propose a WiFi Channel State Information (CSI) sensing framework for multi-station deployments that addresses two fundamental challenges in practical CSI sensing: station-wise feature missingness and limited labeled data. Feature missingness is commonly handled by resampling unevenly spaced CSI measurements or by reconstructing missing samples, while label scarcity is mitigated by data augmentation or self-supervised representation learning. However, these techniques are typically developed in isolation and do not jointly address long-term, structured station unavailability together with label scarcity. To bridge this gap, we explicitly incorporate station unavailability into both representation learning and downstream model training. Specifically, we adapt cross-modal self-supervised learning (CroSSL), a representation learning framework originally designed for time-series sensory data, to multi-station CSI sensing in order to learn representations that are inherently invariant to station-wise feature missingness from unlabeled data. Furthermore, we introduce Station-wise Masking Augmentation (SMA) during downstream model training, which exposes the model to realistic station unavailability patterns under limited labeled data. Our experiments show that neither missingness-invariant pre-training nor station-wise augmentation alone is sufficient; their combination is essential to achieve robust performance under both station-wise feature missingness and label scarcity. The proposed framework provides a practical and robust foundation for multi-station WiFi CSI sensing in real-world deployments. --- ### Inverse Neural Operator for ODE Parameter Optimization Authors: Zhi-Song Liu, Wenqing Peng, Helmi Toropainen, Ammar Kheder, Andreas Rupp, Holger Froning, Xiaojie Lin, Michael Boy Published: 2026-03-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.11854v1 We propose the Inverse Neural Operator (INO), a two-stage framework for recovering hidden ODE parameters from sparse, partial observations. In Stage 1, a Conditional Fourier Neural Operator (C-FNO) with cross-attention learns a differentiable surrogate that reconstructs full ODE trajectories from arbitrary sparse inputs, suppressing high-frequency artifacts via spectral regularization. In Stage 2, an Amortized Drifting Model (ADM) learns a kernel-weighted velocity field in parameter space, transporting random parameter initializations toward the ground truth without backpropagating through the surrogate, avoiding the Jacobian instabilities that afflict gradient-based inversion in stiff regimes. Experiments on a real-world stiff atmospheric chemistry benchmark (POLLU, 25 parameters) and a synthetic Gene Regulatory Network (GRN, 40 parameters) show that INO outperforms gradient-based and amortized baselines in parameter recovery accuracy while requiring only 0.23s inference time, a 487x speedup over iterative gradient descent. --- ### Deep Learning-based Assessment of the Relation Between the Third Molar and Mandibular Canal on Panoramic Radiographs using Local, Centralized, and Federated Learning Authors: Johan Andreas Balle Rubak, Sara Haghighat, Sanyam Jain, Mostafa Aldesoki, Akhilanand Chaurasia, Sarah Sadat Ehsani, Faezeh Dehghan Ghanatkaman, Ahmad Badruddin Ghazali, Julien Issa, Basel Khalil, Rishi Ramani, Ruben Pauwels Published: 2026-03-12 Categories: eess.IV, cs.CV, cs.DC arXiv: https://arxiv.org/abs/2603.11850v1 Impaction of the mandibular third molar in proximity to the mandibular canal increases the risk of inferior alveolar nerve injury. Panoramic radiography is routinely used to assess this relationship. Automated classification of molar-canal overlap could support clinical triage and reduce unnecessary CBCT referrals, while federated learning (FL) enables multi-center collaboration without sharing patient data. We compared Local Learning (LL), FL, and Centralized Learning (CL) for binary overlap/no-overlap classification on cropped panoramic radiographs partitioned across eight independent labelers. A pretrained ResNet-34 was trained under each paradigm and evaluated using per-client metrics with locally optimized thresholds and pooled test performance with a global threshold. Performance was assessed using area under the receiver operating characteristic curve (AUC) and threshold-based metrics, alongside training dynamics, Grad-CAM visualizations, and server-side aggregate monitoring signals. On the test set, CL achieved the highest performance (AUC 0.831; accuracy = 0.782), FL showed intermediate performance (AUC 0.757; accuracy = 0.703), and LL generalized poorly across clients (AUC range = 0.619-0.734; mean = 0.672). Training curves suggested overfitting, particularly in LL models, and Grad-CAM indicated more anatomically focused attention in CL and FL. Overall, centralized training provided the strongest performance, while FL offers a privacy-preserving alternative that outperforms LL. --- ### ZeroSense:How Vision matters in Long Context Compression Authors: Yonghan Gao, Zehong Chen, Lijian Xu, Jingzhi Chen, Jingwei Guan, Xingyu Zeng Published: 2026-03-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.11846v1 Recent visual-text compression (VTC) methods, typified by DeepSeek-OCR, report impressive high token compression ratios for long-context modeling tasks by leveraging text-to-image rendering. However, existing evaluation protocols heavily rely on downstream task performance. Such evaluation metrics fail to accurately measure text preservation due to the strong inherent linguistic priors of Multimodal Large Language Models (MLLMs). In this work, we introduce a new evaluation framework that decouples MLLMs' capabilities to faithfully assess VTC quality. Within this framework, we further introduce the ZeroSense Benchmark to ensure low semantic correlation of testing samples. By eliminating contextual dependencies, our benchmark guarantees that the evaluation results are purely reflective of VTC quality, unaffected by the semantic inference capabilities of downstream models. Extensive experiments across multiple datasets demonstrate that VTC quality and downstream task accuracy diverge significantly, highlighting the necessity of our decoupled evaluation framework. --- ### The Landscape of Generative AI in Information Systems: A Synthesis of Secondary Reviews and Research Agendas Authors: Aleksander Jarzębowicz, Adam Przybyłek, Jacinto Estima, Yen Ying Ng, Jakub Swacha, Beata Zielosko, Lech Madeyski, Noel Carroll, Kai-Kristian Kemell, Bartosz Marcinkowski, Alberto Rodrigues da Silva, Viktoria Stray et al. Published: 2026-03-12 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2603.11842v3 The post-ChatGPT surge has rapidly reframed IS research and practice. As organizations and society grapple with GenAI adoption, a body of secondary studies and research agendas has emerged to synthesize early evidence and chart directions for future inquiry. This study reviews secondary and roadmap papers to synthesize the state of knowledge on GenAI's benefits and challenges in IS, and to identify future research directions. We performed a systematic search across Scopus, WoS, and eAIS for publications from 2023 onwards. Following a rigorous, multi-stage screening process, we selected a final set of 28 papers for analysis using bibliometric mapping and thematic analysis. We also conducted a quality assessment of all sources to gauge confidence in each source's contribution to the findings. GenAI offers transformative potential to drive productivity, accelerate innovation, personalize services, and democratize access to expertise. However, its adoption is constrained by interrelated challenges: technical unreliability, societal-ethical risks, and a governance vacuum. Interpreted through a socio-technical lens, our findings reveal a persistent misalignment between GenAI's fast-evolving technical subsystem and the slower-adapting social subsystem, positioning IS research as critical for achieving joint optimization. To bridge this gap, we propose a research agenda that reorients IS scholarship from analyzing impacts toward actively shaping the co-evolution of technical capabilities with organizational routines, societal values, and regulatory institutions: emphasizing hybrid human-AI ensembles, situated validation, design principles for probabilistic systems, and adaptive governance. For practitioners and policymakers, responsible adoption requires balancing automation with human augmentation alongside transparent governance and adaptive regulations to ensure broadly shared benefits. --- ### The Landscape of Generative AI in Information Systems: A Synthesis of Secondary Reviews and Research Agendas Authors: Aleksander Jarzębowicz, Adam Przybyłek, Jacinto Estima, Yen Ying Ng, Jakub Swacha, Beata Zielosko, Lech Madeyski, Noel Carroll, Kai-Kristian Kemell, Bartosz Marcinkowski, Alberto Rodrigues da Silva, Viktoria Stray et al. Published: 2026-03-12 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2603.11842v1 As organizations grapple with the rapid adoption of Generative AI (GenAI), this study synthesizes the state of knowledge through a systematic literature review of secondary studies and research agendas. Analyzing 28 papers published since 2023, we find that while GenAI offers transformative potential for productivity and innovation, its adoption is constrained by multiple interrelated challenges, including technical unreliability (hallucinations, performance drift), societal-ethical risks (bias, misuse, skill erosion), and a systemic governance vacuum (privacy, accountability, intellectual property). Interpreted through a socio-technical lens, these findings reveal a persistent misalignment between GenAI's fast-evolving technical subsystem and the slower-adapting social subsystem, positioning IS research as critical for achieving joint optimization. To bridge this gap, we discuss a research agenda that reorients IS scholarship from analyzing impacts toward actively shaping the co-evolution of technical capabilities with organizational procedures, societal values, and regulatory institutions--emphasizing hybrid human--AI ensembles, situated validation, design principles for probabilistic systems, and adaptive governance. --- ### DatedGPT: Preventing Lookahead Bias in Large Language Models with Time-Aware Pretraining Authors: Yutong Yan, Raphael Tang, Zhenyu Gao, Wenxi Jiang, Yao Lu Published: 2026-03-12 Categories: cs.CL, q-fin.GN arXiv: https://arxiv.org/abs/2603.11838v2 Large language models pretrained on internet-scale data risk lookahead bias in forecasting tasks, as they may have already seen the true outcome during training. To address this, we present DatedGPT, a family of twelve 1.3B-parameter language models trained from scratch on approximately 100 billion tokens each with strict annual data cutoffs spanning 2013 to 2024, together with DatedInstruct, an instruction dataset grounded in each year's documents to prevent leakage during post-training. The models are competitive with open models of similar scale, and perplexity-based probing confirms that each model's knowledge is bounded by its cutoff year. On stock return prediction over 61,000 firm-day news headlines, DatedGPT-instruct achieves an annualised Sharpe ratio of $3.20$ under the lookahead-bias-free setup. Lookahead-biased models, whose training data covers the outcome period, add a lookahead premium of $26.4$ b.p. per standard deviation, significant at the 1% level. The series thus enables direct analysis of lookahead bias in financial forecasting. We provide an interactive web demo that allows users to query and compare responses from models across different cutoff years, available at www.datedgpt.com. --- ### A Decade of Generative Adversarial Networks for Porous Material Reconstruction Authors: Ali Sadeghkhani, Brandon Bennett, Masoud Babaei, Arash Rabbani Published: 2026-03-12 Categories: cs.CV, cond-mat.mtrl-sci, physics.geo-ph arXiv: https://arxiv.org/abs/2603.11836v1 Digital reconstruction of porous materials has become increasingly critical for applications ranging from geological reservoir characterization to tissue engineering and electrochemical device design. While traditional methods such as micro-computed tomography and statistical reconstruction approaches have established foundations in this field, the emergence of deep learning techniques, particularly Generative Adversarial Networks (GANs), has revolutionized porous media reconstruction capabilities. This review systematically analyzes 96 peer-reviewed articles published from 2017 to early 2026, examining the evolution and applications of GAN-based approaches for porous material image reconstruction. We categorize GAN architectures into six distinct classes, namely Vanilla GANs, Multi-Scale GANs, Conditional GANs, Attention-Enhanced GANs, Style-based GANs, and Hybrid Architecture GANs. Our analysis reveals substantial progress including improvements in porosity accuracy (within 1% of original samples), permeability prediction (up to 79% reduction in mean relative errors), and achievable reconstruction volumes (from initial $64^3$ to current $2{,}200^3$ voxels). Despite these advances, persistent challenges remain in computational efficiency, memory constraints for large-scale reconstruction, and maintaining structural continuity in 2D-to-3D transformations. This systematic analysis provides a comprehensive framework for selecting appropriate GAN architectures based on specific application requirements. --- ### Hypercomplex Widely Linear Processing: Fundamentals for Quaternion Machine Learning Authors: Sayed Pouria Talebi, Clive Cheong Took Published: 2026-03-12 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2603.11835v1 Numerous attempts have been made to replicate the success of complex-valued algebra in engineering and science to other hypercomplex domains such as quaternions, tessarines, biquaternions, and octonions. Perhaps, none have matched the success of quaternions. The most useful feature of quaternions lies in their ability to model three-dimensional rotations which, in turn, have found various industrial applications such as in aeronautics and computergraphics. Recently, we have witnessed a renaissance of quaternions due to the rise of machine learning. To equip the reader to contribute to this emerging research area, this chapter lays down the foundation for: - augmented statistics for modelling quaternion-valued random processes, - widely linear models to exploit such advanced statistics, - quaternion calculus and algebra for algorithmic derivations, - mean square estimation for practical considerations. For ease of exposure, several examples are offered to facilitate the learning, understanding, and(hopefully) the adoption of this multidimensional domain. --- ### Hybrid Human-Agent Social Dilemmas in Energy Markets Authors: Isuri Perera, Frits de Nijs, Julian Garcia Published: 2026-03-12 Categories: cs.MA, cs.AI, cs.GT arXiv: https://arxiv.org/abs/2603.11834v1 In hybrid populations where humans delegate strategic decision-making to autonomous agents, understanding when and how cooperative behaviors can emerge remains a key challenge. We study this problem in the context of energy load management: consumer agents schedule their appliance use under demand-dependent pricing. This structure can create a social dilemma where everybody would benefit from coordination, but in equilibrium agents often choose to incur the congestion costs that cooperative turn-taking would avoid. To address the problem of coordination, we introduce artificial agents that use globally observable signals to increase coordination. Using evolutionary dynamics, and reinforcement learning experiments, we show that artificial agents can shift the learning dynamics to favour coordination outcomes. An often neglected problem is partial adoption: what happens when the technology of artificial agents is in the early adoption stages? We analyze mixed populations of adopters and non-adopters, demonstrating that unilateral entry is feasible: adopters are not structurally penalized, and partial adoption can still improve aggregate outcomes. However, in some parameter regimes, non-adopters may benefit disproportionately from the cooperation induced by adopters. This asymmetry, while not precluding beneficial entry, warrants consideration in deployment, and highlights strategic issues around the adoption of AI technology in multiagent settings. --- ### Towards High-Fidelity CAD Generation via LLM-Driven Program Generation and Text-Based B-Rep Primitive Grounding Authors: Jiahao Li, Qingwang Zhang, Qiuyu Chen, Guozhan Qiu, Yunzhong Lou, Xiangdong Zhou Published: 2026-03-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.11831v2 The field of Computer-Aided Design (CAD) generation has made significant progress in recent years. Existing methods typically fall into two separate categories: parametric CAD modeling and direct boundary representation (B-Rep) synthesis. In modern feature-based CAD systems, parametric modeling and B-Rep are inherently intertwined, as advanced parametric operations (e.g., fillet and chamfer) require explicit selection of B-Rep geometric primitives, and the B-Rep itself is derived from parametric operations. Consequently, this paradigm gap remains a critical factor limiting AI-driven CAD modeling for complex industrial product design. This paper presents FutureCAD, a novel text-to-CAD framework that leverages large language models (LLMs) and a B-Rep grounding transformer (BRepGround) for high-fidelity CAD generation. Our method generates executable CadQuery scripts, and introduces a text-based query mechanism that enables the LLM to specify geometric selections via natural language, which BRepGround then grounds to the target primitives. To train our framework, we construct a new dataset comprising real-world CAD models. For the LLM, we apply supervised fine-tuning (SFT) to establish fundamental CAD generation capabilities, followed by reinforcement learning (RL) to improve generalization. Experiments show that FutureCAD achieves state-of-the-art CAD generation performance. Code and dataset are available at: https://github.com/JohanStackk/FutureCAD --- ### Multimodal classification of Radiation-Induced Contrast Enhancements and tumor recurrence using deep learning Authors: Robin Peretzke, Marlin Hanstein, Maximilian Fischer, Lars Badhi Wessel, Obada Alhalabi, Sebastian Regnery, Andreas Kudak, Maximilian Deng, Tanja Eichkorn, Philipp Hoegen Saßmannshausen, Fabian Allmendinger, Jan-Hendrik Bolten et al. Published: 2026-03-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.11827v2 The differentiation between tumor recurrence and radiation-induced contrast enhancements in post-treatment glioblastoma patients remains a major clinical challenge. Existing approaches rely on clinically sparsely available diffusion MRI or do not consider radiation maps, which are gaining increasing interest in the tumor board for this differentiation. We introduce RICE-NET, a multimodal 3D deep learning model that integrates longitudinal MRI data with radiotherapy dose distributions for automated lesion classification using conventional T1-weighted MRI data. Using a cohort of 92 patients, the model achieved an F1 score of 0.92 on an independent test set. During extensive ablation experiments, we quantified the contribution of each timepoint and modality and showed that reliable classification largely depends on the radiation map. Occlusion-based interpretability analyses further confirmed the model's focus on clinically relevant regions. These findings highlight the potential of multimodal deep learning to enhance diagnostic accuracy and support clinical decision-making in neuro-oncology. --- ### OMNIA: Closing the Loop by Leveraging LLMs for Knowledge Graph Completion Authors: Frédéric Ieng, Soror Sahri, Mourad Ouzzani, Massinissa Hammaz, Salima Benbernou, Hanieh Khorashadizadeh, Sven Groppe, Farah Benamara Published: 2026-03-12 Categories: cs.DB, cs.AI arXiv: https://arxiv.org/abs/2603.11820v1 Knowledge Graphs (KGs) are widely used to represent structured knowledge, yet their automatic construction, especially with Large Language Models (LLMs), often results in incomplete or noisy outputs. Knowledge Graph Completion (KGC) aims to infer and add missing triples, but most existing methods either rely on structural embeddings that overlook semantics or language models that ignore the graph's structure and depend on external sources. In this work, we present OMNIA, a two-stage approach that bridges structural and semantic reasoning for KGC. It first generates candidate triples by clustering semantically related entities and relations within the KG, then validates them through lightweight embedding filtering followed by LLM-based semantic validation. OMNIA performs on the internal KG, without external sources, and specifically targets implicit semantics that are most frequent in LLM-generated graphs. Extensive experiments on multiple datasets demonstrate that OMNIA significantly improves F1-score compared to traditional embedding-based models. These results highlight OMNIA's effectiveness and efficiency, as its clustering and filtering stages reduce both search space and validation cost while maintaining high-quality completion. --- ### Automated Detection of Malignant Lesions in the Ovary Using Deep Learning Models and XAI Authors: Md. Hasin Sarwar Ifty, Nisharga Nirjan, Labib Islam, M. A. Diganta, Reeyad Ahmed Ornate, Anika Tasnim, Md. Saiful Islam Published: 2026-03-12 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2603.11818v1 The unrestrained proliferation of cells that are malignant in nature is cancer. In recent times, medical professionals are constantly acquiring enhanced diagnostic and treatment abilities by implementing deep learning models to analyze medical data for better clinical decision, disease diagnosis and drug discovery. A majority of cancers are studied and treated by incorporating these technologies. However, ovarian cancer remains a dilemma as it has inaccurate non-invasive detection procedures and a time consuming, invasive procedure for accurate detection. Thus, in this research, several Convolutional Neural Networks such as LeNet-5, ResNet, VGGNet and GoogLeNet/Inception have been utilized to develop 15 variants and choose a model that accurately detects and identifies ovarian cancer. For effective model training, the dataset OvarianCancer&SubtypesDatasetHistopathology from Mendeley has been used. After constructing a model, we utilized Explainable Artificial Intelligence (XAI) models such as LIME, Integrated Gradients and SHAP to explain the black box outcome of the selected model. For evaluating the performance of the model, Accuracy, Precision, Recall, F1-Score, ROC Curve and AUC have been used. From the evaluation, it was seen that the slightly compact InceptionV3 model with ReLu had the overall best result achieving an average score of 94% across all the performance metrics in the augmented dataset. Lastly for XAI, the three aforementioned XAI have been used for an overall comparative analysis. It is the aim of this research that the contributions of the study will help in achieving a better detection method for ovarian cancer. --- ### VisiFold: Long-Term Traffic Forecasting via Temporal Folding Graph and Node Visibility Authors: Zhiwei Zhang, Xinyi Du, Weihao Wang, Xuanchi Guo, Wenjuan Han Published: 2026-03-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.11816v1 Traffic forecasting is a cornerstone of intelligent transportation systems. While existing research has made significant progress in short-term prediction, long-term forecasting remains a largely uncharted and challenging frontier. Extending the prediction horizon intensifies two critical issues: escalating computational resource consumption and increasingly complex spatial-temporal dependencies. Current approaches, which rely on spatial-temporal graphs and process temporal and spatial dimensions separately, suffer from snapshot-stacking inflation and cross-step fragmentation. To overcome these limitations, we propose \textit{VisiFold}. Our framework introduces a novel temporal folding graph that consolidates a sequence of temporal snapshots into a single graph. Furthermore, we present a node visibility mechanism that incorporates node-level masking and subgraph sampling to overcome the computational bottleneck imposed by large node counts. Extensive experiments show that VisiFold not only drastically reduces resource consumption but also outperforms existing baselines in long-term forecasting tasks. Remarkably, even with a high mask ratio of 80\%, VisiFold maintains its performance advantage. By effectively breaking the resource constraints in both temporal and spatial dimensions, our work paves the way for more realistic long-term traffic forecasting. The code is available at~ https://github.com/PlanckChang/VisiFold. --- ### RADAR: Closed-Loop Robotic Data Generation via Semantic Planning and Autonomous Causal Environment Reset Authors: Yongzhong Wang, Keyu Zhu, Yong Zhong, Liqiong Wang, Jinyu Yang, Feng Zheng Published: 2026-03-12 Categories: cs.RO, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2603.11811v2 The acquisition of large-scale physical interaction data, a critical prerequisite for modern robot learning, is severely bottlenecked by the prohibitive cost and scalability limits of human-in-the-loop collection paradigms. To break this barrier, we introduce Robust Autonomous Data Acquisition for Robotics (RADAR), a fully autonomous, closed-loop data generation engine that completely removes human intervention from the collection cycle. RADAR elegantly divides the cognitive load into a four-module pipeline. Anchored by 2-5 3D human demonstrations as geometric priors, a Vision-Language Model first orchestrates scene-relevant task generation via precise semantic object grounding and skill retrieval. Next, a Graph Neural Network policy translates these subtasks into physical actions via in-context imitation learning. Following execution, the VLM performs automated success evaluation using a structured Visual Question Answering pipeline. Finally, to shatter the bottleneck of manual resets, a Finite State Machine orchestrates an autonomous environment reset and asymmetric data routing mechanism. Driven by simultaneous forward-reverse planning with a strict Last-In, First-Out causal sequence, the system seamlessly restores unstructured workspaces and robustly recovers from execution failures. This continuous brain-cerebellum synergy transforms data collection into a self-sustaining process. Extensive evaluations highlight RADAR's exceptional versatility. In simulation, our framework achieves up to 90% success rates on complex, long-horizon tasks, effortlessly solving challenges where traditional baselines plummet to near-zero performance. In real-world deployments, the system reliably executes diverse, contact-rich skills (e.g., deformable object manipulation) via few-shot adaptation without domain-specific fine-tuning, providing a highly scalable paradigm for robotic data acquisition. --- ### CEI-3D: Collaborative Explicit-Implicit 3D Reconstruction for Realistic and Fine-Grained Object Editing Authors: Yue Shi, Rui Shi, Yuxuan Xiong, Bingbing Ni, Wenjun Zhang Published: 2026-03-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.11810v1 Existing 3D editing methods often produce unrealistic and unrefined results due to the deeply integrated nature of their reconstruction networks. To address the challenge, this paper introduces CEI-3D, an editing-oriented reconstruction pipeline designed to facilitate realistic and fine-grained editing. Specifically, we propose a collaborative explicit-implicit reconstruction approach, which represents the target object using an implicit SDF network and a differentially sampled, locally controllable set of handler points. The implicit network provides a smooth and continuous geometry prior, while the explicit handler points offer localized control, enabling mutual guidance between the global 3D structure and user-specified local editing regions. To independently control each attribute of the handler points, we design a physical properties disentangling module to decouple the color of the handler points into separate physical properties. We also propose a dual-diffuse-albedo network in this module to process the edited and non-edited regions through separate branches, thereby preventing undesired interference from editing operations. Building on the reconstructed collaborative explicit-implicit representation with disentangled properties, we introduce a spatial-aware editing module that enables part-wise adjustment of relevant handler points. This module employs a cross-view propagation-based 3D segmentation strategy, which helps users to edit the specified physical attributes of a target part efficiently. Extensive experiments on both real and synthetic datasets demonstrate that our approach achieves more realistic and fine-grained editing results than the state-of-the-art (SOTA) methods while requiring less editing time. Our code is available on https://github.com/shiyue001/CEI-3D. --- ### Automating Skill Acquisition through Large-Scale Mining of Open-Source Agentic Repositories: A Framework for Multi-Agent Procedural Knowledge Extraction Authors: Shuzhen Bi, Mengsong Wu, Hao Hao, Keqian Li, Wentao Liu, Siyu Song, Hongbo Zhao, Aimin Zhou Published: 2026-03-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.11808v2 The transition from monolithic large language models (LLMs) to modular, skill-equipped agents represents a fundamental architectural shift in artificial intelligence deployment. While general-purpose models demonstrate remarkable breadth in declarative knowledge, their utility in autonomous workflows is frequently constrained by insufficient specialized procedural expertise. This report investigates a systematic framework for automated acquisition of high-quality agent skills through mining of open-source repositories on platforms such as GitHub. We focus on the extraction of visualization and educational capabilities from state-of-the-art systems including TheoremExplainAgent and Code2Video, both utilizing the Manim mathematical animation engine. The framework encompasses repository structural analysis, semantic skill identification through dense retrieval, and translation to the standardized SKILL.md format. We demonstrate that systematic extraction from agentic repositories, combined with rigorous security governance and multi-dimensional evaluation metrics, enables scalable acquisition of procedural knowledge that augments LLM capabilities without requiring model retraining. Our analysis reveals that agent-generated educational content can achieve 40\% gains in knowledge transfer efficiency while maintaining pedagogical quality comparable to human-crafted tutorials. --- ### A Diffeomorphism Groupoid and Algebroid Framework for Discontinuous Image Registration Authors: Lili Bao, Bin Xiao, Shihui Ying, Stefan Sommer Published: 2026-03-12 Categories: math.GR, cs.CV arXiv: https://arxiv.org/abs/2603.11806v2 In this paper, we propose a novel mathematical framework for piecewise diffeomorphic image registration that involves discontinuous sliding motion using a diffeomorphism groupoid and algebroid approach. The traditional Large Deformation Diffeomorphic Metric Mapping (LDDMM) registration method builds on Lie groups, which assume continuity and smoothness in velocity fields, limiting its applicability in handling discontinuous sliding motion. To overcome this limitation, we extend the diffeomorphism Lie groups to a framework of discontinuous diffeomorphism Lie groupoids, allowing for discontinuities along sliding boundaries while maintaining diffeomorphism within homogeneous regions. We provide a rigorous analysis of the associated mathematical structures, including Lie algebroids and their duals, and derive specific Euler-Arnold equations to govern optimal flows for discontinuous deformations. Numerical tests are performed to validate the efficiency of the proposed approach. --- ### OSMDA: OpenStreetMap-based Domain Adaptation for Remote Sensing VLMs Authors: Stefan Maria Ailuro, Mario Markov, Mohammad Mahdi, Delyan Boychev, Luc Van Gool, Danda Pani Paudel Published: 2026-03-12 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.11804v3 Vision-Language Models (VLMs) adapted to remote sensing rely heavily on domain-specific image-text supervision, yet high-quality annotations for satellite and aerial imagery remain scarce and expensive to produce. Prevailing pseudo-labeling pipelines address this gap by distilling knowledge from large frontier models, but this dependence on large teachers is costly, limits scalability, and caps achievable performance at the ceiling of the teacher. We propose OSMDA: a self-contained domain adaptation framework that eliminates this dependency. Our key insight is that a capable base VLM can serve as its own annotation engine: by pairing aerial images with rendered OpenStreetMap (OSM) tiles, we leverage optical character recognition and chart comprehension capabilities of the model to generate captions enriched by OSM's vast auxiliary metadata. The model is then fine-tuned on the resulting corpus with satellite imagery alone, yielding OSMDA-VLM, a domain-adapted VLM that requires no manual labeling and no stronger external VLM teacher. We conduct exhaustive evaluations spanning six zero-shot and five in-distribution benchmarks across vision-language tasks, where OSMDA leads to substantial improvement. We further compare against nine competitive baselines, demonstrating that our method achieves superior overall performance, while being substantially cheaper to train than teacher-dependent alternatives. These results suggest that, given a strong foundation model, alignment with crowd-sourced geographic data is a practical and scalable path towards remote sensing domain adaptation. Dataset and model weights will be made publicly available upon acceptance. --- ### A Semi-Decentralized Approach to Multiagent Control Authors: Mahdi Al-Husseini, Mykel J. Kochenderfer, Kyle H. Wray Published: 2026-03-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.11802v1 We introduce an expressive framework and algorithms for the semi-decentralized control of cooperative agents in environments with communication uncertainty. Whereas semi-Markov control admits a distribution over time for agent actions, semi-Markov communication, or what we refer to as semi-decentralization, gives a distribution over time for what actions and observations agents can store in their histories. We extend semi-decentralization to the partially observable Markov decision process (POMDP). The resulting SDec-POMDP unifies decentralized and multiagent POMDPs and several existing explicit communication mechanisms. We present recursive small-step semi-decentralized A* (RS-SDA*), an exact algorithm for generating optimal SDec-POMDP policies. RS-SDA* is evaluated on semi-decentralized versions of several standard benchmarks and a maritime medical evacuation scenario. This paper provides a well-defined theoretical foundation for exploring many classes of multiagent communication problems through the lens of semi-decentralization. --- ### Exponential-Family Membership Inference: From LiRA and RMIA to BaVarIA Authors: Rickard Brännvall Published: 2026-03-12 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2603.11799v2 Membership inference attacks (MIAs) are becoming standard tools for auditing the privacy of machine learning models. The leading attacks -- LiRA (Carlini et al., 2022) and RMIA (Zarifzadeh et al., 2024) -- appear to use distinct scoring strategies, while the recently proposed BASE (Lassila et al., 2025) was shown to be equivalent to RMIA, making it difficult for practitioners to choose among them. We show that all three are instances of a single exponential-family log-likelihood ratio framework, differing only in their distributional assumptions and the number of parameters estimated per data point. This unification reveals a hierarchy (BASE1-4) that connects RMIA and LiRA as endpoints of a spectrum of increasing model complexity, and yields a practical rule -- match the attack's complexity to the available shadow-model budget. Within this framework, we identify variance estimation as a primary bottleneck at small shadow-model budgets and propose BaVarIA, a Bayesian variance inference attack that replaces threshold-based parameter switching with conjugate normal-inverse-gamma priors. BaVarIA yields a Student-t predictive (BaVarIA-t) or a Gaussian with stabilized variance (BaVarIA-n), providing stable performance without per-dataset hyperparameter tuning. Across 12 testbeds and 7 shadow-model budgets, BaVarIA is a drop-in replacement for LiRA that matches or, on average, improves upon it. The gains are largest in the practically important low-shadow-model and offline regimes: offline, the Bayesian prior replaces LiRA's heuristic and outperforms it on 10 of 12 testbeds. --- ### Exponential-Family Membership Inference: From LiRA and RMIA to BaVarIA Authors: Rickard Brännvall Published: 2026-03-12 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2603.11799v1 Membership inference attacks (MIAs) are becoming standard tools for auditing the privacy of machine learning models. The leading attacks -- LiRA (Carlini et al., 2022) and RMIA (Zarifzadeh et al., 2024) -- appear to use distinct scoring strategies, while the recently proposed BASE (Lassila et al., 2025) was shown to be equivalent to RMIA, making it difficult for practitioners to choose among them. We show that all three are instances of a single exponential-family log-likelihood ratio framework, differing only in their distributional assumptions and the number of parameters estimated per data point. This unification reveals a hierarchy (BASE1-4) that connects RMIA and LiRA as endpoints of a spectrum of increasing model complexity. Within this framework, we identify variance estimation as the key bottleneck at small shadow-model budgets and propose BaVarIA, a Bayesian variance inference attack that replaces threshold-based parameter switching with conjugate normal-inverse-gamma priors. BaVarIA yields a Student-t predictive (BaVarIA-t) or a Gaussian with stabilized variance (BaVarIA-n), providing stable performance without additional hyperparameter tuning. Across 12 datasets and 7 shadow-model budgets, BaVarIA matches or improves upon LiRA and RMIA, with the largest gains in the practically important low-shadow-model and offline regimes. --- ### DocSage: An Information Structuring Agent for Multi-Doc Multi-Entity Question Answering Authors: Teng Lin, Yizhang Zhu, Zhengxuan Zhang, Yuyu Luo, Nan Tang Published: 2026-03-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.11798v1 Multi-document Multi-entity Question Answering inherently demands models to track implicit logic between multiple entities across scattered documents. However, existing Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) frameworks suffer from critical limitations: standard RAG's vector similarity-based coarse-grained retrieval often omits critical facts, graph-based RAG fails to efficiently integrate fragmented complex relationship networks, and both lack schema awareness, leading to inadequate cross-document evidence chain construction and inaccurate entity relationship deduction. To address these challenges, we propose DocSage, an end-to-end agentic framework that integrates dynamic schema discovery, structured information extraction, and schema-aware relational reasoning with error guarantees. DocSage operates through three core modules: (1) A schema discovery module dynamically infers query-specific minimal joinable schemas to capture essential entities and relationships; (2) An extraction module transforms unstructured text into semantically coherent relational tables, enhanced by error-aware correction mechanisms to reduce extraction errors; (3) A reasoning module performs multi-hop relational reasoning over structured tables, leveraging schema awareness to efficiently align cross-document entities and aggregate evidence. This agentic design offers three key advantages: precise fact localization via SQL-powered indexing, natural support for cross-document entity joins through relational tables, and mitigated LLM attention diffusion via structured representation. Evaluations on two MDMEQA benchmarks demonstrate that DocSage significantly outperforms state-of-the-art long-context LLMs and RAG systems, achieving more than 27% accuracy improvements respectively. --- ### Intrinsic Concept Extraction Based on Compositional Interpretability Authors: Hanyu Shi, Hong Tao, Guoheng Huang, Jianbin Jiang, Xuhang Chen, Chi-Man Pun, Shanhu Wang, Pan Pan Published: 2026-03-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.11795v2 Unsupervised Concept Extraction aims to extract concepts from a single image; however, existing methods suffer from the inability to extract composable intrinsic concepts. To address this, this paper introduces a new task called Compositional and Interpretable Intrinsic Concept Extraction (CI-ICE). The CI-ICE task aims to leverage diffusion-based text-to-image models to extract composable object-level and attribute-level concepts from a single image, such that the original concept can be reconstructed through the combination of these concepts. To achieve this goal, we propose a method called HyperExpress, which addresses the CI-ICE task through two core aspects. Specifically, first, we propose a concept learning approach that leverages the inherent hierarchical modeling capability of hyperbolic space to achieve accurate concept disentanglement while preserving the hierarchical structure and relational dependencies among concepts; second, we introduce a concept-wise optimization method that maps the concept embedding space to maintain complex inter-concept relationships while ensuring concept composability. Our method demonstrates outstanding performance in extracting compositionally interpretable intrinsic concepts from a single image. --- ### Locating Demographic Bias at the Attention-Head Level in CLIP's Vision Encoder Authors: Alaa Yasser, Kittipat Phunjanna, Marcos Escudero Viñolo, Catarina Barata, Jenny Benois-Pineau Published: 2026-03-12 Categories: cs.CV, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2603.11793v1 Standard fairness audits of foundation models quantify that a model is biased, but not where inside the network the bias resides. We propose a mechanistic fairness audit that combines projected residual-stream decomposition, zero-shot Concept Activation Vectors, and bias-augmented TextSpan analysis to locate demographic bias at the level of individual attention heads in vision transformers. As a feasibility case study, we apply this pipeline to the CLIP ViT-L-14 encoder on 42 profession classes of the FACET benchmark, auditing both gender and age bias. For gender, the pipeline identifies four terminal-layer heads whose ablation reduces global bias (Cramer's V: 0.381 -> 0.362) while marginally improving accuracy (+0.42%); a layer-matched random control confirms that this effect is specific to the identified heads. A single head in the final layer contributes to the majority of the reduction in the most stereotyped classes, and class-level analysis shows that corrected predictions shift toward the correct occupation. For age, the same pipeline identifies candidate heads, but ablation produces weaker and less consistent effects, suggesting that age bias is encoded more diffusely than gender bias in this model. These results provide preliminary evidence that head-level bias localisation is feasible for discriminative vision encoders and that the degree of localisability may vary across protected attributes. keywords: Bias . CLIP . Mechanistic Interpretability . Vision Transformer . Fairness --- ### Disentangled Representation Learning through Unsupervised Symmetry Group Discovery Authors: Barthélémy Dang-Nhu, Louis Annabi, Sylvain Argentieri Published: 2026-03-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.11790v3 Symmetry-based disentangled representation learning leverages the group structure of environment transformations to uncover the latent factors of variation. Prior approaches to symmetry-based disentanglement have required strong prior knowledge of the symmetry group's structure, or restrictive assumptions about the subgroup properties. In this work, we remove these constraints by proposing a method whereby an embodied agent autonomously discovers the group structure of its action space through unsupervised interaction with the environment. We prove the identifiability of the true symmetry group decomposition under minimal assumptions, and derive two algorithms: one for discovering the group decomposition from interaction data, and another for learning Linear Symmetry-Based Disentangled (LSBD) representations without assuming specific subgroup properties. Our method is validated on three environments exhibiting different group decompositions, where it outperforms existing LSBD approaches. --- ### Language Generation with Replay: A Learning-Theoretic View of Model Collapse Authors: Giorgio Racca, Michal Valko, Amartya Sanyal Published: 2026-03-12 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2603.11784v2 As scaling laws push the training of frontier large language models (LLMs) toward ever-growing data requirements, training pipelines are approaching a regime where much of the publicly available online text may be consumed. At the same time, widespread LLM usage increases the volume of machine-generated content on the web; together, these trends raise the likelihood of generated text re-entering future training corpora, increasing the associated risk of performance degradation often called model collapse. In practice, model developers address this concern through data cleaning, watermarking, synthetic-data policies, or, in some cases, blissful ignorance. However, the problem of model collapse in generative models has not been examined from a learning-theoretic perspective: we study it through the theoretical lens of the language generation in the limit framework, introducing a replay adversary that augments the example stream with the generator's own past outputs. Our main contribution is a fine-grained learning-theoretic characterization of when replay fundamentally limits generation: while replay is benign for the strongest notion of uniform generation, it provably creates separations for the weaker notions of non-uniform generation and generation in the limit. Interestingly, our positive results mirror heuristics widely used in practice, such as data cleaning, watermarking, and output filtering, while our separations show when these ideas can fail. --- ### HELM: Hierarchical and Explicit Label Modeling with Graph Learning for Multi-Label Image Classification Authors: Marjan Stoimchev, Boshko Koloski, Jurica Levatić, Dragi Kocev, Sašo Džeroski Published: 2026-03-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.11783v1 Hierarchical multi-label classification (HMLC) is essential for modeling complex label dependencies in remote sensing. Existing methods, however, struggle with multi-path hierarchies where instances belong to multiple branches, and they rarely exploit unlabeled data. We introduce HELM (\textit{Hierarchical and Explicit Label Modeling}), a novel framework that overcomes these limitations. HELM: (i) uses hierarchy-specific class tokens within a Vision Transformer to capture nuanced label interactions; (ii) employs graph convolutional networks to explicitly encode the hierarchical structure and generate hierarchy-aware embeddings; and (iii) integrates a self-supervised branch to effectively leverage unlabeled imagery. We perform a comprehensive evaluation on four remote sensing image (RSI) datasets (UCM, AID, DFC-15, MLRSNet). HELM achieves state-of-the-art performance, consistently outperforming strong baselines in both supervised and semi-supervised settings, demonstrating particular strength in low-label scenarios. --- ### From Debate to Deliberation: Structured Collective Reasoning with Typed Epistemic Acts Authors: Sunil Prakash Published: 2026-03-12 Categories: cs.AI, cs.CL, cs.MA arXiv: https://arxiv.org/abs/2603.11781v1 Multi-agent LLM systems increasingly tackle complex reasoning, yet their interaction patterns remain limited to voting, unstructured debate, or pipeline orchestration. None model deliberation: a phased process where differentiated participants exchange typed reasoning moves, preserve disagreements, and converge on accountable outcomes. We introduce Deliberative Collective Intelligence (DCI), specifying four reasoning archetypes, 14 typed epistemic acts, a shared workspace, and DCI-CF, a convergent flow algorithm that guarantees termination with a structured decision packet containing the selected option, residual objections, minority report, and reopen conditions. We evaluate on 45 tasks across seven domains using Gemini 2.5 Flash. On non-routine tasks (n=40), DCI significantly improves over unstructured debate (+0.95, 95% CI (+0.41, +1.54)). DCI excels on hidden-profile tasks requiring perspective integration (9.56, highest of any system on any domain) while failing on routine decisions (5.39), confirming task-dependence. DCI produces 100% structured decision packets and 98% minority reports, artifacts absent from all baselines. However, DCI consumes ~62x single-agent tokens, and single-agent generation outperforms DCI on overall quality. DCI's contribution is not that more agents are better, but that consequential decisions benefit from deliberative structure when process accountability justifies the cost. --- ### Large Language Models for Biomedical Article Classification Authors: Jakub Proboszcz, Paweł Cichosz Published: 2026-03-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.11780v1 This work presents a systematic and in-depth investigation of the utility of large language models as text classifiers for biomedical article classification. The study uses several small and mid-size open source models, as well as selected closed source ones, and is more comprehensive than most prior work with respect to the scope of evaluated configurations: different types of prompts, output processing methods for generating both class and class probability predictions, as well as few-shot example counts and selection methods. The performance of the most successful configurations is compared to that of conventional classification algorithms. The obtained average PR AUC over 15 challenging datasets above 0.4 for zero-shot prompting and nearly 0.5 for few-shot prompting comes close to that of the naïve Bayes classifier (0.5), the random forest algorithm (0.5 with default settings or 0.55 with hyperparameter tuning) and fine-tuned transformer models (0.5). These results confirm the utility of large language models as text classifiers for non-trivial domains and provide practical recommendations of the most promising setups, including in particular using output token probabilities for class probability prediction. --- ### Trust Oriented Explainable AI for Fake News Detection Authors: Krzysztof Siwek, Daniel Stankowski, Maciej Stodolski Published: 2026-03-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.11778v1 This article examines the application of Explainable Artificial Intelligence (XAI) in NLP based fake news detection and compares selected interpretability methods. The work outlines key aspects of disinformation, neural network architectures, and XAI techniques, with a focus on SHAP, LIME, and Integrated Gradients. In the experimental study, classification models were implemented and interpreted using these methods. The results show that XAI enhances model transparency and interpretability while maintaining high detection accuracy. Each method provides distinct explanatory value: SHAP offers detailed local attributions, LIME provides simple and intuitive explanations, and Integrated Gradients performs efficiently with convolutional models. The study also highlights limitations such as computational cost and sensitivity to parameterization. Overall, the findings demonstrate that integrating XAI with NLP is an effective approach to improving the reliability and trustworthiness of fake news detection systems. --- ### Legal-DC: Benchmarking Retrieval-Augmented Generation for Legal Documents Authors: Yaocong Li, Qiang Lan, Leihan Zhang, Le Zhang Published: 2026-03-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.11772v1 Retrieval-Augmented Generation (RAG) has emerged as a promising technology for legal document consultation, yet its application in Chinese legal scenarios faces two key limitations: existing benchmarks lack specialized support for joint retriever-generator evaluation, and mainstream RAG systems often fail to accommodate the structured nature of legal provisions. To address these gaps, this study advances two core contributions: First, we constructed the Legal-DC benchmark dataset, comprising 480 legal documents (covering areas such as market regulation and contract management) and 2,475 refined question-answer pairs, each annotated with clause-level references, filling the gap for specialized evaluation resources in Chinese legal RAG. Second, we propose the LegRAG framework, which integrates legal adaptive indexing (clause-boundary segmentation) with a dual-path self-reflection mechanism to ensure clause integrity while enhancing answer accuracy. Third, we introduce automated evaluation methods for large language models to meet the high-reliability demands of legal retrieval scenarios. LegRAG outperforms existing state-of-the-art methods by 1.3% to 5.6% across key evaluation metrics. This research provides a specialized benchmark, practical framework, and empirical insights to advance the development of Chinese legal RAG systems. Our code and data are available at https://github.com/legal-dc/Legal-DC. ---