# Research Papers — 2026-03 · bundle page 84 of 243 > Full-text markdown of papers #4151–4200 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/84 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/83.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/85.md) ### Cov2Pose: Leveraging Spatial Covariance for Direct Manifold-aware 6-DoF Object Pose Estimation Authors: Nassim Ali Ousalah, Peyman Rostami, Vincent Gaudillière, Emmanuel Koumandakis, Anis Kacem, Enjie Ghorbel, Djamila Aouada Published: 2026-03-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.19961v2 In this paper, we address the problem of 6-DoF object pose estimation from a single RGB image. Indirect methods that typically predict intermediate 2D keypoints, followed by a Perspective-n-Point solver, have shown great performance. Direct approaches, which regress the pose in an end-to-end manner, are usually computationally more efficient but less accurate. However, direct pose regression heads rely on globally pooled features, ignoring spatial second-order statistics despite their informativeness in pose prediction. They also predict, in most cases, discontinuous pose representations that lack robustness. Herein, we therefore propose a covariance-pooled representation that encodes convolutional feature distributions as a symmetric positive definite (SPD) matrix. Moreover, we propose a novel pose encoding in the form of an SPD matrix via its Cholesky decomposition. Pose is then regressed in an end-to-end manner with a manifold-aware network head, taking into account the Riemannian geometry of SPD matrices. Experiments and ablations consistently demonstrate the relevance of second-order pooling and continuous representations for direct pose regression, including under partial occlusion. --- ### HiPath: Hierarchical Vision-Language Alignment for Structured Pathology Report Prediction Authors: Ruicheng Yuan, Zhenxuan Zhang, Anbang Wang, Liwei Hu, Xiangqian Hua, Yaya Peng, Jiawei Luo, Guang Yang Published: 2026-03-20 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.19957v2 Pathology reports are structured, multi-granular documents encoding diagnostic conclusions, histological grades, and ancillary test results across one or more anatomical sites; yet existing pathology vision-language models (VLMs) reduce this output to a flat label or free-form text. We present HiPath, a lightweight VLM framework built on frozen UNI2 and Qwen3 backbones that treats structured report prediction as its primary training objective. Three trainable modules totalling 15M parameters address complementary aspects of the problem: a Hierarchical Patch Aggregator (HiPA) for multi-image visual encoding, Hierarchical Contrastive Learning (HiCL) for cross-modal alignment via optimal transport, and Slot-based Masked Diagnosis Prediction (Slot-MDP) for structured diagnosis generation. Trained on 749K real-world Chinese pathology cases from three hospitals, HiPath achieves 68.9% strict and 74.7% clinically acceptable accuracy with a 97.3% safety rate, outperforming all baselines under the same frozen backbone. Cross-hospital evaluation confirms generalisation with only a 3.4pp drop in strict accuracy while maintaining 97.1% safety. --- ### Structural Controllability of Large-Scale Hypergraphs Authors: Joshua Pickard, Xin Mao, Can Chen Published: 2026-03-20 Categories: math.OC, cs.LG, cs.SI, eess.SY arXiv: https://arxiv.org/abs/2603.19955v1 Controlling real-world networked systems, including ecological, biomedical, and engineered networks that exhibit higher-order interactions, remains challenging due to inherent nonlinearities and large system scales. Despite extensive studies on graph controllability, the controllability properties of hypergraphs remain largely underdeveloped. Existing results focus primarily on exact controllability, which is often impractical for large-scale hypergraphs. In this article, we develop a structural controllability framework for hypergraphs by modeling hypergraph dynamics as polynomial dynamical systems. In particular, we extend classical notions of accessibility and dilation from linear graph-based systems to polynomial hypergraph dynamics and establish a hypergraph-based criterion under which the topology guarantees satisfaction of classical Lie-algebraic and Kalman-type rank conditions for almost all parameter choices. We further derive a topology-based lower bound on the minimum number of driver nodes required for structural controllability and leverage this bound to design a scalable driver node selection algorithm combining dilation-aware initialization via maximum matching with greedy accessibility expansion. We demonstrate the effectiveness and scalability of the proposed framework through numerical experiments on hypergraphs with tens to thousands of nodes and higher-order interactions. --- ### On the Ability of Transformers to Verify Plans Authors: Yash Sarrof, Yupei Du, Katharina Stein, Alexander Koller, Sylvie Thiébaux, Michael Hahn Published: 2026-03-20 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.19954v2 Transformers have shown inconsistent success in AI planning tasks, and theoretical understanding of when generalization should be expected has been limited. We take important steps towards addressing this gap by analyzing the ability of decoder-only models to verify whether a given plan correctly solves a given planning instance. To analyse the general setting where the number of objects -- and thus the effective input alphabet -- grows at test time, we introduce C*-RASP, an extension of C-RASP designed to establish length generalization guarantees for transformers under the simultaneous growth in sequence length and vocabulary size. Our results identify a large class of classical planning domains for which transformers can provably learn to verify long plans, and structural properties that significantly affects the learnability of length generalizable solutions. Empirical experiments corroborate our theory. --- ### TAPAS: Efficient Two-Server Asymmetric Private Aggregation Beyond Prio(+) Authors: Harish Karthikeyan, Antigoni Polychroniadou Published: 2026-03-20 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2603.19949v1 Privacy-preserving aggregation is a cornerstone for AI systems that learn from distributed data without exposing individual records, especially in federated learning and telemetry. Existing two-server protocols (e.g., Prio and successors) set a practical baseline by validating inputs while preventing any single party from learning users' values, but they impose symmetric costs on both servers and communication that scales with the per-client input dimension $L$. Modern learning tasks routinely involve dimensionalities $L$ in the tens to hundreds of millions of model parameters. We present TAPAS, a two-server asymmetric private aggregation scheme that addresses these limitations along four dimensions: (i) no trusted setup or preprocessing, (ii) server-side communication that is independent of $L$ (iii) post-quantum security based solely on standard lattice assumptions (LWE, SIS), and (iv) stronger robustness with identifiable abort and full malicious security for the servers. A key design choice is intentional asymmetry: one server bears the $O(L)$ aggregation and verification work, while the other operates as a lightweight facilitator with computation independent of $L$. This reduces total cost, enables the secondary server to run on commodity hardware, and strengthens the non-collusion assumption of the servers. One of our main contributions is a suite of new and efficient lattice-based zero-knowledge proofs; to our knowledge, we are the first to establish privacy and correctness with identifiable abort in the two-server setting. --- ### Hybrid topic modelling for computational close reading: Mapping narrative themes in Pushkin's Evgenij Onegin Authors: Angelo Maria Sabatini Published: 2026-03-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.19940v1 This study presents a hybrid topic modelling framework for computational literary analysis that integrates Latent Dirichlet Allocation (LDA) with sparse Partial Least Squares Discriminant Analysis (sPLS-DA) to model thematic structure and longitudinal dynamics in narrative poetry. As a case study, we analyse Evgenij Onegin-Aleksandr S. Pushkin's novel in verse-using an Italian translation, testing whether unsupervised and supervised lexical structures converge in a small-corpus setting. The poetic text is segmented into thirty-five documents of lemmatised content words, from which five stable and interpretable topics emerge. To address small-corpus instability, a multi-seed consensus protocol is adopted. Using sPLS-DA as a supervised probe enhances interpretability by identifying lexical markers that refine each theme. Narrative hubs-groups of contiguous stanzas marking key episodes-extend the bag-of-words approach to the narrative level, revealing how thematic mixtures align with the poem's emotional and structural arc. Rather than replacing traditional literary interpretation, the proposed framework offers a computational form of close reading, illustrating how lightweight probabilistic models can yield reproducible thematic maps of complex poetic narratives, even when stylistic features such as metre, phonology, or native morphology are abstracted away. Despite relying on a single lemmatised translation, the approach provides a transparent methodological template applicable to other high-density literary texts in comparative studies. --- ### Timestep-Aware Block Masking for Efficient Diffusion Model Inference Authors: Haodong He, Yuan Gao, Weizhong Zhang, Gui-Song Xia Published: 2026-03-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.19939v1 Diffusion Probabilistic Models (DPMs) have achieved great success in image generation but suffer from high inference latency due to their iterative denoising nature. Motivated by the evolving feature dynamics across the denoising trajectory, we propose a novel framework to optimize the computational graph of pre-trained DPMs on a per-timestep basis. By learning timestep-specific masks, our method dynamically determines which blocks to execute or bypass through feature reuse at each inference stage. Unlike global optimization methods that incur prohibitive memory costs via full-chain backpropagation, our method optimizes masks for each timestep independently, ensuring a memory-efficient training process. To guide this process, we introduce a timestep-aware loss scaling mechanism that prioritizes feature fidelity during sensitive denoising phases, complemented by a knowledge-guided mask rectification strategy to prune redundant spatial-temporal dependencies. Our approach is architecture-agnostic and demonstrates significant efficiency gains across a broad spectrum of models, including DDPM, LDM, DiT, and PixArt. Experimental results show that by treating the denoising process as a sequence of optimized computational paths, our method achieves a superior balance between sampling speed and generative quality. Our code will be released. --- ### LIORNet: Self-Supervised LiDAR Snow Removal Framework for Autonomous Driving under Adverse Weather Conditions Authors: Ji-il Park, Inwook Shim Published: 2026-03-20 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2603.19936v1 LiDAR sensors provide high-resolution 3D perception and long-range detection, making them indispensable for autonomous driving and robotics. However, their performance significantly degrades under adverse weather conditions such as snow, rain, and fog, where spurious noise points dominate the point cloud and lead to false perception. To address this problem, various approaches have been proposed: distance-based filters exploiting spatial sparsity, intensity-based filters leveraging reflectance distributions, and learning-based methods that adapt to complex environments. Nevertheless, distance-based methods struggle to distinguish valid object points from noise, intensity-based methods often rely on fixed thresholds that lack adaptability to changing conditions, and learning-based methods suffer from the high cost of annotation, limited generalization, and computational overhead. In this study, we propose LIORNet, which eliminates these drawbacks and integrates the strengths of all three paradigms. LIORNet is built upon a U-Net++ backbone and employs a self-supervised learning strategy guided by pseudo-labels generated from multiple physical and statistical cues, including range-dependent intensity thresholds, snow reflectivity, point sparsity, and sensing range constraints. This design enables LIORNet to distinguish noise points from environmental structures without requiring manual annotations, thereby overcoming the difficulty of snow labeling and the limitations of single-principle approaches. Extensive experiments on the WADS and CADC datasets demonstrate that LIORNet outperforms state-of-the-art filtering algorithms in both accuracy and runtime while preserving critical environmental features. These results highlight LIORNet as a practical and robust solution for LiDAR perception in extreme weather, with strong potential for real-time deployment in autonomous driving systems. --- ### Memori: A Persistent Memory Layer for Efficient, Context-Aware LLM Agents Authors: Luiz C. Borro, Luiz A. B. Macarini, Gordon Tindall, Michael Montero, Adam B. Struck Published: 2026-03-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.19935v1 As large language models (LLMs) evolve into autonomous agents, persistent memory at the API layer is essential for enabling context-aware behavior across LLMs and multi-session interactions. Existing approaches force vendor lock-in and rely on injecting large volumes of raw conversation into prompts, leading to high token costs and degraded performance. We introduce Memori, an LLM-agnostic persistent memory layer that treats memory as a data structuring problem. Its Advanced Augmentation pipeline converts unstructured dialogue into compact semantic triples and conversation summaries, enabling precise retrieval and coherent reasoning. Evaluated on the LoCoMo benchmark, Memori achieves 81.95% accuracy, outperforming existing memory systems while using only 1,294 tokens per query (~5% of full context). This results in substantial cost reductions, including 67% fewer tokens than competing approaches and over 20x savings compared to full-context methods. These results show that effective memory in LLM agents depends on structured representations instead of larger context windows, enabling scalable and cost-efficient deployment. --- ### SAGE: Sustainable Agent-Guided Expert-tuning for Culturally Attuned Translation in Low-Resource Southeast Asia Authors: Zhixiang Lu, Chong Zhang, Yulong Li, Angelos Stefanidis, Anh Nguyen, Imran Razzak, Jionglong Su, Zhengyong Jiang Published: 2026-03-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.19931v1 The vision of an inclusive World Wide Web is impeded by a severe linguistic divide, particularly for communities in low-resource regions of Southeast Asia. While large language models (LLMs) offer a potential solution for translation, their deployment in data-poor contexts faces a dual challenge: the scarcity of high-quality, culturally relevant data and the prohibitive energy costs of training on massive, noisy web corpora. To resolve the tension between digital inclusion and environmental sustainability, we introduce Sustainable Agent-Guided Expert-tuning (SAGE). This framework pioneers an energy-aware paradigm that prioritizes the "right data" over "big data". Instead of carbon-intensive training on unfiltered datasets, SAGE employs a reinforcement learning (RL) agent, optimized via Group Relative Policy Optimization (GRPO), to autonomously curate a compact training set. The agent utilizes a semantic reward signal derived from a small, expert-constructed set of community dialogues to filter out noise and cultural misalignment. We then efficiently fine-tune open-source LLMs on this curated data using Low-Rank Adaptation (LoRA). We applied SAGE to translation tasks between English and seven low-resource languages (LRLs) in Southeast Asia. Our approach establishes new state-of-the-art performance on BLEU-4 and COMET-22 metrics, effectively capturing local linguistic nuances. Crucially, SAGE surpasses baselines trained on full datasets while reducing data usage by 97.1% and training energy consumption by 95.2%. By delivering high-performance models with a minimal environmental footprint, SAGE offers a scalable and responsible pathway to bridge the digital divide in the Global South. --- ### RAM: Recover Any 3D Human Motion in-the-Wild Authors: Sen Jia, Ning Zhu, Jinqin Zhong, Jiale Zhou, Huaping Zhang, Jenq-Neng Hwang, Lei Li Published: 2026-03-20 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.19929v2 RAM incorporates a motion-aware semantic tracker with adaptive Kalman filtering to achieve robust identity association under severe occlusions and dynamic interactions. A memory-augmented Temporal HMR module further enhances human motion reconstruction by injecting spatio-temporal priors for consistent and smooth motion estimation. Moreover, a lightweight Predictor module forecasts future poses to maintain reconstruction continuity, while a gated combiner adaptively fuses reconstructed and predicted features to ensure coherence and robustness. Experiments on in-the-wild multi-person benchmarks such as PoseTrack and 3DPW, demonstrate that RAM substantially outperforms previous state-of-the-art in both Zero-shot tracking stability and 3D accuracy, offering a generalizable paradigm for markerless 3D human motion capture in-the-wild. --- ### SegVGGT: Joint 3D Reconstruction and Instance Segmentation from Multi-View Images Authors: Jinyuan Qu, Hongyang Li, Lei Zhang Published: 2026-03-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.19926v1 3D instance segmentation methods typically rely on high-quality point clouds or posed RGB-D scans, requiring complex multi-stage processing pipelines, and are highly sensitive to reconstruction noise. While recent feed-forward transformers have revolutionized multi-view 3D reconstruction, they remain decoupled from high-level semantic understanding. In this work, we present SegVGGT, a unified end-to-end framework that simultaneously performs feed-forward 3D reconstruction and instance segmentation directly from multi-view RGB images. By introducing object queries that interact with multi-level geometric features, our method deeply integrates instance identification into the visual geometry grounded transformer. To address the severe attention dispersion problem caused by the massive number of global image tokens, we propose the Frame-level Attention Distribution Alignment (FADA) strategy. FADA explicitly guides object queries to attend to instance-relevant frames during training, providing structured supervision without extra inference overhead. Extensive experiments demonstrate that SegVGGT achieves the state-of-the-art performance on ScanNetv2 and ScanNet200, outperforming both recent joint models and RGB-D-based approaches, while exhibiting strong generalization capabilities on ScanNet++. --- ### ReconMIL: Synergizing Latent Space Reconstruction with Bi-Stream Mamba for Whole Slide Image Analysis Authors: Lubin Gan, Jing Zhang, Heng Zhang, Xin Di, Zhifeng Wang, Wenke Huang, Xiaoyan Sun Published: 2026-03-20 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2603.19925v2 Whole slide image (WSI) analysis heavily relies on multiple instance learning (MIL). While recent methods benefit from large-scale foundation models and advanced sequence modeling to capture long-range dependencies, they still struggle with two critical issues. First, directly applying frozen, task-agnostic features often leads to suboptimal separability due to the domain gap with specific histological tasks. Second, relying solely on global aggregators can cause over-smoothing, where sparse but critical diagnostic signals are overshadowed by the dominant background context. In this paper, we present ReconMIL, a novel framework designed to bridge this domain gap and balance global-local feature aggregation. Our approach introduces a Latent Space Reconstruction module that adaptively projects generic features into a compact, task-specific manifold, improving boundary delineation. To prevent information dilution, we develop a bi-stream architecture combining a Mamba-based global stream for contextual priors and a CNN-based local stream to preserve subtle morphological anomalies. A scale-adaptive selection mechanism dynamically fuses these two streams, determining when to rely on overall architecture versus local saliency. Evaluations across multiple diagnostic and survival prediction benchmarks show that ReconMIL consistently outperforms current state-of-the-art methods, effectively localizing fine-grained diagnostic regions while suppressing background noise. Visualization results confirm the models superior ability to localize diagnostic regions by effectively balancing global structure and local granularity. --- ### Translation from the Information Bottleneck Perspective: an Efficiency Analysis of Spatial Prepositions in Bitexts Authors: Antoine Taroni, Ludovic Moncla, Frederique Laforest Published: 2026-03-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.19924v2 Efficient communication requires balancing informativity and simplicity when encoding meanings. The Information Bottleneck (IB) framework captures this trade-off formally, predicting that natural language systems cluster near an optimal accuracy-complexity frontier. While supported in visual domains such as colour and motion, linguistic stimuli such as words in sentential context remain unexplored. We address this gap by framing translation as an IB optimisation problem, treating source sentences as stimuli and target sentences as compressed meanings. This allows IB analyses to be performed directly on bitexts rather than controlled naming experiments. We applied this to spatial prepositions across English, German and Serbian translations of a French novel. To estimate informativity, we conducted a pile-sorting pilot-study (N=35) and obtained similarity judgements of pairs of prepositions. We trained a low-rank projection model (D=5) that predicts these judgements (Spearman correlation: 0.78). Attested translations of prepositions lie closer to the IB optimal frontier than counterfactual alternatives, offering preliminary evidence that human translators exhibit communicative efficiency pressure in the spatial domain. More broadly, this work suggests that translation can serve as a window into the cognitive efficiency pressures shaping cross-linguistic semantic systems. --- ### Span-Level Machine Translation Meta-Evaluation Authors: Stefano Perrella, Eric Morales Agostinho, Hugo Zaragoza Published: 2026-03-20 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.19921v1 Machine Translation (MT) and automatic MT evaluation have improved dramatically in recent years, enabling numerous novel applications. Automatic evaluation techniques have evolved from producing scalar quality scores to precisely locating translation errors and assigning them error categories and severity levels. However, it remains unclear how to reliably measure the evaluation capabilities of auto-evaluators that do error detection, as no established technique exists in the literature. This work investigates different implementations of span-level precision, recall, and F-score, showing that seemingly similar approaches can yield substantially different rankings, and that certain widely-used techniques are unsuitable for evaluating MT error detection. We propose "match with partial overlap and partial credit" (MPP) with micro-averaging as a robust meta-evaluation strategy and release code for its use publicly. Finally, we use MPP to assess the state of the art in MT error detection. --- ### PanORama: Multiview Consistent Panoptic Segmentation in Operating Rooms Authors: Tuna Gürbüz, Ege Özsoy, Tony Danjun Wang, Nassir Navab Published: 2026-03-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.19920v1 Operating rooms (ORs) are cluttered, dynamic, highly occluded environments, where reliable spatial understanding is essential for situational awareness during complex surgical workflows. Achieving spatial understanding for panoptic segmentation from sparse multiview images poses a fundamental challenge, as limited visibility in a subset of views often leads to mispredictions across cameras. To this end, we introduce PanORama, the first panoptic segmentation for the operating room that is multiview-consistent by design. By modeling cross-view interactions at the feature level inside the backbone in a single forward pass, view consistency emerges directly rather than through post-hoc refinement. We evaluate on the MM-OR and 4D-OR datasets, achieving >70% Panoptic Quality (PQ) performance, and outperforming the previous state of the art. Importantly, PanORama is calibration-free, requiring no camera parameters, and generalizes to unseen camera viewpoints within any multiview configuration at inference time. By substantially enhancing multiview segmentation and, consequently, spatial understanding in the OR, we believe our approach opens new opportunities for surgical perception and assistance. Code will be released upon acceptance. --- ### Learning Like Humans: Analogical Concept Learning for Generalized Category Discovery Authors: Jizhou Han, Chenhao Ding, Yuhang He, Qiang Wang, Shaokun Wang, SongLin Dong, Yihong Gong Published: 2026-03-20 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.19918v1 Generalized Category Discovery (GCD) seeks to uncover novel categories in unlabeled data while preserving recognition of known categories, yet prevailing visual-only pipelines and the loose coupling between supervised learning and discovery often yield brittle boundaries on fine-grained, look-alike categories. We introduce the Analogical Textual Concept Generator (ATCG), a plug-and-play module that analogizes from labeled knowledge to new observations, forming textual concepts for unlabeled samples. Fusing these analogical textual concepts with visual features turns discovery into a visual-textual reasoning process, transferring prior knowledge to novel data and sharpening category separation. ATCG attaches to both parametric and clustering style GCD pipelines and requires no changes to their overall design. Across six benchmarks, ATCG consistently improves overall, known-class, and novel-class performance, with the largest gains on fine-grained data. Our code is available at: https://github.com/zhou-9527/AnaLogical-GCD. --- ### Infinite-dimensional spherical-radial decomposition for probabilistic functions, with application to constrained optimal control and Gaussian process regression Authors: Kewei Wang, Georg Stadler Published: 2026-03-20 Categories: math.OC, cs.LG, math.NA arXiv: https://arxiv.org/abs/2603.19907v1 The spherical-radial decomposition (SRD) is an efficient method for estimating probabilistic functions and their gradients defined over finite-dimensional elliptical distributions. In this work, we generalize the SRD to infinite stochastic dimensions by combining subspace SRD with standard Monte Carlo methods. The resulting method, which we call hybrid infinite-dimensional SRD (hiSRD) provides an unbiased, low-variance estimator for convex sets arising, for instance, in chance-constrained optimization. We provide a theoretical analysis of the variance of finite-dimensional SRD as the dimension increases, and show that the proposed hybrid method eliminates truncation-induced bias, reduces variance, and allows the computation of derivatives of probabilistic functions. We present comprehensive numerical studies for a risk-neutral stochastic PDE optimal control problem with joint chance state constraints, and for optimizing kernel parameters in Gaussian process regression under the constraint that the posterior process satisfies joint chance constraints. --- ### A Federated Many-to-One Hopfield model for associative Neural Networks Authors: Andrea Alessandrelli, Fabrizio Durante, Andrea Ladiana, Andrea Lepre Published: 2026-03-20 Categories: cond-mat.dis-nn, stat.ML arXiv: https://arxiv.org/abs/2603.19902v1 Federated learning enables collaborative training without sharing raw data, but struggles under client heterogeneity and streaming distribution shifts, where drift and novel data can impair convergence and cause forgetting. We propose a federated associative-memory framework that learns shared archetypes in heterogeneous, continual settings, where client data are independent but not necessarily balanced. Each client encodes its experience as a low-rank Hebbian operator, sent to a central server for aggregation and factorization into global archetypes. This approach preserves privacy, avoids centralized replay buffers, and is robust to small, noisy, or evolving datasets. We cast aggregation as a low-rank-plus-noise spectral inference problem, deriving theoretical thresholds for detectability and retrieval robustness. An entropy-based controller balances stability and plasticity in streaming regimes. Experiments with heterogeneous clients, drift, and novelty show improved global archetype reconstruction and associative retrieval, supporting the spectral view of federated consolidation. --- ### Deep Autocorrelation Modeling for Time-Series Forecasting: Progress and Prospects Authors: Hao Wang, Licheng Pan, Qingsong Wen, Jialin Yu, Zhichao Chen, Chunyuan Zheng, Xiaoxi Li, Zhixuan Chu, Chao Xu, Mingming Gong, Haoxuan Li, Yuan Lu et al. Published: 2026-03-20 Categories: stat.ML, cs.LG, stat.AP arXiv: https://arxiv.org/abs/2603.19899v1 Autocorrelation is a defining characteristic of time-series data, where each observation is statistically dependent on its predecessors. In the context of deep time-series forecasting, autocorrelation arises in both the input history and the label sequences, presenting two central research challenges: (1) designing neural architectures that model autocorrelation in history sequences, and (2) devising learning objectives that model autocorrelation in label sequences. Recent studies have made strides in tackling these challenges, but a systematic survey examining both aspects remains lacking. To bridge this gap, this paper provides a comprehensive review of deep time-series forecasting from the perspective of autocorrelation modeling. In contrast to existing surveys, this work makes two distinctive contributions. First, it proposes a novel taxonomy that encompasses recent literature on both model architectures and learning objectives -- whereas prior surveys neglect or inadequately discuss the latter aspect. Second, it offers a thorough analysis of the motivations, insights, and progression of the surveyed literature from a unified, autocorrelation-centric perspective, providing a holistic overview of the evolution of deep time-series forecasting. The full list of papers and resources is available at https://github.com/Master-PLC/Awesome-TSF-Papers. --- ### Revealing Domain-Spatiality Patterns for Configuration Tuning: Domain Knowledge Meets Fitness Landscapes Authors: Yulong Ye, Hongyuan Liang, Chao Jiang, Miqing Li, Tao Chen Published: 2026-03-20 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2603.19897v2 Configuration tuning for better performance is crucial in quality assurance. Yet, there has long been a mystery on tuners' effectiveness, due to the black-box nature of configurable systems. Prior efforts predominantly adopt static domain analysis (e.g., static taint analysis), which often lacks generalizability, or dynamic data analysis (e.g., benchmarking performance analysis), limiting explainability. In this work, we embrace Fitness Landscape Analysis (FLA) as a bridge between domain knowledge and difficulty of the tuning. We propose Domland, a two-pronged methodology that synergizes the spatial information obtained from FLA and domain-driven analysis to systematically capture the hidden characteristics of configuration tuning cases, explaining how and why a tuner might succeed or fail. This helps to better interpret and contextualize the behavior of tuners and inform tuner design. To evaluate Domland, we conduct a case study of nine software systems and 93 workloads, from which we reveal several key findings: (1) configuration landscapes are inherently system-specific, with no single domain factor (e.g., system area, programming language, or resource intensity) consistently shaping their structure; (2) the core options (e.g., pic-struct of x264), which control the main functional flows, exert a stronger influence on landscape ruggedness (i.e. the difficulty of tuning) compared to resource options (e.g., cpu-independent of x264); (3) Workload effects on landscape structure are not uniformly tied to type or scale. Both contribute to landscape variations, but their impact is system-dependent. --- ### Utility-Guided Agent Orchestration for Efficient LLM Tool Use Authors: Boyan Liu, Gongming Zhao, Hongli Xu Published: 2026-03-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.19896v2 Tool-using large language model (LLM) agents often face a fundamental tension between answer quality and execution cost. Fixed workflows are stable but inflexible, while free-form multi-step reasoning methods such as ReAct may improve task performance at the expense of excessive tool calls, longer trajectories, higher token consumption, and increased latency. In this paper, we study agent orchestration as an explicit decision problem rather than leaving it entirely to prompt-level behavior. We propose a utility-guided orchestration policy that selects among actions such as respond, retrieve, tool call, verify, and stop by balancing estimated gain, step cost, uncertainty, and redundancy. Our goal is not to claim universally best task performance, but to provide a controllable and analyzable policy framework for studying quality-cost trade-offs in tool-using LLM agents. Experiments across direct answering, threshold control, fixed workflows, ReAct, and several policy variants show that explicit orchestration signals substantially affect agent behavior. Additional analyses on cost definitions, workflow fairness, and redundancy control further demonstrate that lightweight utility design can provide a defensible and practical mechanism for agent control. --- ### Utility-Guided Agent Orchestration for Efficient LLM Tool Use Authors: Boyan Liu, Gongming Zhao, Hongli Xu Published: 2026-03-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.19896v1 Tool-using large language model (LLM) agents often face a fundamental tension between answer quality and execution cost. Fixed workflows are stable but inflexible, while free-form multi-step reasoning methods such as ReAct may improve task performance at the expense of excessive tool calls, longer trajectories, higher token consumption, and increased latency. In this paper, we study agent orchestration as an explicit decision problem rather than leaving it entirely to prompt-level behavior. We propose a utility-guided orchestration policy that selects among actions such as respond, retrieve, tool call, verify, and stop by balancing estimated gain, step cost, uncertainty, and redundancy. Our goal is not to claim universally best task performance, but to provide a controllable and analyzable policy framework for studying quality-cost trade-offs in tool-using LLM agents. Experiments across direct answering, threshold control, fixed workflows, ReAct, and several policy variants show that explicit orchestration signals substantially affect agent behavior. Additional analyses on cost definitions, workflow fairness, and redundancy control further demonstrate that lightweight utility design can provide a defensible and practical mechanism for agent control. --- ### Integrating Meta-Features with Knowledge Graph Embeddings for Meta-Learning Authors: Antonis Klironomos, Ioannis Dasoulas, Francesco Periti, Mohamed Gad-Elrab, Heiko Paulheim, Anastasia Dimou, Evgeny Kharlamov Published: 2026-03-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.19888v1 The vast collection of machine learning records available on the web presents a significant opportunity for meta-learning, where past experiments are leveraged to improve performance. Two crucial meta-learning tasks are pipeline performance estimation (PPE), which predicts pipeline performance on target datasets, and dataset performance-based similarity estimation (DPSE), which identifies datasets with similar performance patterns. Existing approaches primarily rely on dataset meta-features (e.g., number of instances, class entropy, etc.) to represent datasets numerically and approximate these meta-learning tasks. However, these approaches often overlook the wealth of past experimental results and pipeline metadata available. This limits their ability to capture dataset - pipeline interactions that reveal performance similarity patterns. In this work, we propose KGmetaSP, a knowledge-graph-embeddings approach that leverages existing experiment data to capture these interactions and improve both PPE and DPSE. We represent datasets and pipelines within a unified knowledge graph (KG) and derive embeddings that support pipeline-agnostic meta-models for PPE and distance-based retrieval for DPSE. To validate our approach, we construct a large-scale benchmark comprising 144,177 OpenML experiments, enabling a rich cross-dataset evaluation. KGmetaSP enables accurate PPE using a single pipeline-agnostic meta-model and improves DPSE over baselines. The proposed KGmetaSP, KG, and benchmark are released, establishing a new reference point for meta-learning and demonstrating how consolidating open experiment data into a unified KG advances the field. --- ### What If Consensus Lies? Selective-Complementary Reinforcement Learning at Test Time Authors: Dong Yan, Jian Liang, Yanbo Wang, Shuo Lu, Ran He, Tieniu Tan Published: 2026-03-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.19880v2 Test-Time Reinforcement Learning (TTRL) enables Large Language Models (LLMs) to enhance reasoning capabilities on unlabeled test streams by deriving pseudo-rewards from majority voting consensus. However, existing TTRL methods rely exclusively on positive pseudo-labeling strategies. Such reliance becomes vulnerable under challenging scenarios where answer distributions are highly dispersed, resulting in weak consensus that inadvertently reinforces incorrect trajectories as supervision signals. In this paper, we propose SCRL (Selective-Complementary Reinforcement Learning), a robust test-time reinforcement learning framework that effectively mitigates label noise amplification. SCRL develops Selective Positive Pseudo-Labeling, which enforces strict consensus criteria to filter unreliable majorities. Complementarily, SCRL introduces Entropy-Gated Negative Pseudo-Labeling, the first negative supervision mechanism in TTRL, to reliably prune incorrect trajectories based on generation uncertainty. Extensive experiments on multiple reasoning benchmarks demonstrate that SCRL achieves substantial improvements over baselines, while maintaining robust generalization and training stability under constrained rollout budgets. Our code is available at https://github.com/Jasper-Yan/SCRL. --- ### Discovery of Decision Synchronization Patterns from Event Logs Authors: Tijmen Kuijpers, Karolin Winter, Remco Dijkman Published: 2026-03-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.19879v1 Synchronizing decisions between running cases in business processes facilitates fair and efficient use of resources, helps prioritize the most valuable cases, and prevents unnecessary waiting. Consequently, decision synchronization patterns are regularly built into processes, in the form of mechanisms that temporarily delay one case to favor another. These decision mechanisms therefore consider properties of multiple cases at once, rather than just the properties of a single case; an aspect that is rarely addressed by current process discovery techniques. To address this gap, this paper proposes an approach for discovering decision synchronization patterns inspired by supply chain processes. These decision synchronization patterns take the form of specific process constructs combined with a constraint that determines which particular case to execute. We describe, formalize and demonstrate how the constraint for four such patterns can be discovered. We evaluate our approach in two artificial scenarios. First, with four separate process models each containing a single decision synchronization pattern, i.e., we demonstrate that our approach can discover every type of pattern when only this one type is present. Second, we consider a process model containing all four decision synchronization patterns to show generalizability of the approach to more complex problems. For both scenarios, we could reliably retrieve the expected patterns. --- ### Minimax Generalized Cross-Entropy Authors: Kartheek Bondugula, Santiago Mazuelas, Aritz Pérez, Anqi Liu Published: 2026-03-20 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2603.19874v3 Loss functions play a central role in supervised classification. Cross-entropy (CE) is widely used, whereas the mean absolute error (MAE) loss can offer robustness but is difficult to optimize. Interpolating between the CE and MAE losses, generalized cross-entropy (GCE) has recently been introduced to provide a trade-off between optimization difficulty and robustness. Existing formulations of GCE result in a non-convex optimization over classification margins that is prone to underfitting, leading to poor performances with complex datasets. In this paper, we propose a minimax formulation of generalized cross-entropy (MGCE) that results in a convex optimization over classification margins. Moreover, we show that MGCEs can provide an upper bound on the classification error. The proposed bilevel convex optimization can be efficiently implemented using stochastic gradient computed via implicit differentiation. Using benchmark datasets, we show that MGCE achieves strong accuracy, faster convergence, and better calibration, especially in the presence of label noise. --- ### SIMPLER: Efficient Foundation Model Adaptation via Similarity-Guided Layer Pruning for Earth Observation Authors: Víctor Barreiro, Johannes Jakubik, Francisco Argüello, Dora B. Heras Published: 2026-03-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.19873v3 Fine-tuning foundation models for Earth Observation is computationally expensive, with high training time and memory demands for both training and deployment. Parameter-efficient methods reduce training cost but retain full inference complexity, while post-hoc compression optimizes inference only after costly full fine-tuning. We introduce SIMPLER, a pre-fine-tuning architecture selection method that reduces inference and deployment costs by identifying an effective model depth before adaptation. SIMPLER exploits stabilization of representations in deeper layers of pre-trained vision transformers: it computes layer-wise representation similarity on unlabeled task data and applies an automated scoring function to select redundant layers, with no gradients, magnitude heuristics, or hyperparameter tuning required. On Prithvi-EO-2, SIMPLER prunes up to 79% of parameters while retaining 94% of baseline performance, yielding a 2.1x training speedup and 2.6x inference speedup. The method generalizes to TerraMind (a multimodal EO foundation model) and ImageNet-pretrained ViT-MAE, demonstrating applicability across tasks, architectures, and spectral modalities. Code is available at https://gitlab.citius.gal/hpc4rs/simpler. --- ### SIMPLER: Efficient Foundation Model Adaptation via Similarity-Guided Layer Pruning for Earth Observation Authors: Víctor Barreiro, Johannes Jakubik, Francisco Argüello, Dora B. Heras Published: 2026-03-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.19873v2 Fine-tuning foundation models for Earth Observation is computationally expensive, with high training time and memory demands for both training and deployment. Parameter-efficient methods reduce training cost but retain full inference complexity, while post-hoc compression optimizes inference only after costly full fine-tuning. We introduce SIMPLER, a pre-fine-tuning architecture selection method that reduces inference and deployment costs by identifying an effective model depth before adaptation. SIMPLER exploits stabilization of representations in deeper layers of pre-trained vision transformers: it computes layer-wise representation similarity on unlabeled task data and applies an automated scoring function to select redundant layers, with no gradients, magnitude heuristics, or hyperparameter tuning required. On Prithvi-EO-2, SIMPLER prunes up to 79% of parameters while retaining 94% of baseline performance, yielding a 2.1x training speedup and 2.6x inference speedup. The method generalizes to TerraMind (a multimodal EO foundation model) and ImageNet-pretrained ViT-MAE, demonstrating applicability across tasks, architectures, and spectral modalities. Code is available at https://gitlab.citius.gal/hpc4rs/simpler. --- ### On the Dynamics & Transferability of Latent Generalization during Memorization Authors: Simran Ketha, Venkatakrishnan Ramaswamy Published: 2026-03-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.19865v1 Deep networks have been known to have extraordinary generalization abilities, via mechanisms that aren't yet well understood. It is also known that upon shuffling labels in the training data to varying degrees, deep networks, trained with standard methods, can still achieve perfect or high accuracy on this corrupted training data. This phenomenon is called memorization, and typically comes at the cost of poorer generalization to true labels. Our recent work has demonstrated, that the internal representations of such models retain significantly better latent generalization abilities than is directly apparent from the model. In particular, it has been shown that such latent generalization can be recovered via simple probes (called MASC probes) on the layer-wise representations of the model. However, the origin and dynamics over training of this latent generalization during memorization is not well understood. Here, we track the training dynamics, empirically, and find that latent generalization abilities largely peak early in training, with model generalization. Next, we investigate to what extent the specific nature of the MASC probe is critical for our ability to extract latent generalization from the model's layerwise outputs. To this end, we first examine the mathematical structure of the MASC probe and show that it is a quadratic classifier, i.e. is non-linear. This brings up the question of the extent to which this latent generalization might be linearly decodable from layerwise outputs. To investigate this, we designed a new linear probe for this setting. Next, we consider the question of whether it is possible to transfer latent generalization to model generalization by directly editing model weights. To this end, we devise a way to transfer the latent generalization present in last-layer representations to the model using the new linear probe. --- ### NASimJax: A GPU-Accelerated Policy Learning Framework for Penetration Testing Authors: Raphael Simon, José Carrasquel, Wim Mees, Pieter Libin Published: 2026-03-20 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2603.19864v2 Penetration testing, the practice of simulating cyberattacks to identify vulnerabilities, is a complex sequential decision-making task that is inherently partially observable and features large action spaces. Training reinforcement learning (RL) policies for this domain faces a fundamental bottleneck: existing simulators are too slow to train on realistic network scenarios at scale, resulting in policies that fail to generalize. We present NASimJax, a complete JAX-based reimplementation of the Network Attack Simulator (NASim), achieving up to 100x higher environment throughput than the original simulator. By running the entire training pipeline on hardware accelerators, NASimJax enables experimentation on larger networks under fixed compute budgets that were previously infeasible. We formulate automated penetration testing as a Contextual POMDP and introduce a network generation pipeline that produces structurally diverse and guaranteed-solvable scenarios. Together, these provide a principled basis for studying zero-shot policy generalization. We use the framework to investigate action-space scaling and generalization across networks of up to 40 hosts. We find that Prioritized Level Replay better handles dense training distributions than Domain Randomization, particularly at larger scales, and that training on sparser topologies yields an implicit curriculum that improves out-of-distribution generalization, even on topologies denser than those seen during training. To handle linearly growing action spaces, we propose a two-stage action decomposition (2SAS) that substantially outperforms flat action masking at scale. Finally, we identify a failure mode arising from the interaction between Prioritized Level Replay's episode-reset behaviour and 2SAS's credit assignment structure. NASimJax thus provides a fast, flexible, and realistic platform for advancing RL-based penetration testing. --- ### MedQ-Engine: A Closed-Loop Data Engine for Evolving MLLMs in Medical Image Quality Assessment Authors: Jiyao Liu, Junzhi Ning, Wanying Qu, Lihao Liu, Chenglong Ma, Junjun He, Ningsheng Xu Published: 2026-03-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.19863v1 Medical image quality assessment (Med-IQA) is a prerequisite for clinical AI deployment, yet multimodal large language models (MLLMs) still fall substantially short of human experts, particularly when required to provide descriptive assessments with clinical reasoning beyond simple quality scores. However, improving them is hindered by the high cost of acquiring descriptive annotations and by the inability of one-time data collection to adapt to the model's evolving weaknesses. To address these challenges, we propose MedQ-Engine, a closed-loop data engine that iteratively evaluates the model to discover failure prototypes via data-driven clustering, explores a million-scale image pool using these prototypes as retrieval anchors with progressive human-in-the-loop annotation, and evolves through quality-assured fine-tuning, forming a self-improving cycle. Models are evaluated on complementary perception and description tasks. An entropy-guided routing mechanism triages annotations to minimize labeling cost. Experiments across five medical imaging modalities show that MedQ-Engine elevates an 8B-parameter model to surpass GPT-4o by over 13% and narrow the gap with human experts to only 4.34%, using only 10K annotations with more than 4x sample efficiency over random sampling. --- ### IsoCLIP: Decomposing CLIP Projectors for Efficient Intra-modal Alignment Authors: Simone Magistri, Dipam Goswami, Marco Mistretta, Bartłomiej Twardowski, Joost van de Weijer, Andrew D. Bagdanov Published: 2026-03-20 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.19862v2 Vision-Language Models like CLIP are extensively used for inter-modal tasks which involve both visual and text modalities. However, when the individual modality encoders are applied to inherently intra-modal tasks like image-to-image retrieval, their performance suffers from the intra-modal misalignment. In this paper we study intra-modal misalignment in CLIP with a focus on the role of the projectors that map pre-projection image and text embeddings into the shared embedding space. By analyzing the form of the cosine similarity applied to projected features, and its interaction with the contrastive CLIP loss, we show that there is an inter-modal operator responsible for aligning the two modalities during training, and a second, intra-modal operator that only enforces intra-modal normalization but does nothing to promote intra-modal alignment. Via spectral analysis of the inter-modal operator, we identify an approximately isotropic subspace in which the two modalities are well-aligned, as well as anisotropic directions specific to each modality. We demonstrate that this aligned subspace can be directly obtained from the projector weights and that removing the anisotropic directions improves intra-modal alignment. Our experiments on intra-modal retrieval and classification benchmarks show that our training-free method reduces intra-modal misalignment, greatly lowers latency, and outperforms existing approaches across multiple pre-trained CLIP-like models. The code is publicly available at: https://github.com/simomagi/IsoCLIP. --- ### FoleyDirector: Fine-Grained Temporal Steering for Video-to-Audio Generation via Structured Scripts Authors: You Li, Dewei Zhou, Fan Ma, Fu Li, Dongliang He, Yi Yang Published: 2026-03-20 Categories: cs.SD, cs.CV arXiv: https://arxiv.org/abs/2603.19857v2 Recent Video-to-Audio (V2A) methods have achieved remarkable progress, enabling the synthesis of realistic, high-quality audio. However, they struggle with fine-grained temporal control in multi-event scenarios or when visual cues are insufficient, such as small regions, off-screen sounds, or occluded or partially visible objects. In this paper, we propose FoleyDirector, a framework that, for the first time, enables precise temporal guidance in DiT-based V2A generation while preserving the base model's audio quality and allowing seamless switching between V2A generation and temporally controlled synthesis. FoleyDirector introduces Structured Temporal Scripts (STS), a set of captions corresponding to short temporal segments, to provide richer temporal information. These features are integrated via the Script-Guided Temporal Fusion Module, which employs Temporal Script Attention to fuse STS features coherently. To handle complex multi-event scenarios, we further propose Bi-Frame Sound Synthesis, enabling parallel in-frame and out-of-frame audio generation and improving controllability. To support training and evaluation, we construct the DirectorSound dataset and introduce VGGSoundDirector and DirectorBench. Experiments demonstrate that FoleyDirector substantially enhances temporal controllability while maintaining high audio fidelity, empowering users to act as Foley directors and advancing V2A toward more expressive and controllable generation. --- ### Failure Modes for Deep Learning-Based Online Mapping: How to Measure and Address Them Authors: Michael Hubbertz, Qi Han, Tobias Meisen Published: 2026-03-20 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.19852v1 Deep learning-based online mapping has emerged as a cornerstone of autonomous driving, yet these models frequently fail to generalize beyond familiar environments. We propose a framework to identify and measure the underlying failure modes by disentangling two effects: Memorization of input features and overfitting to known map geometries. We propose measures based on evaluation subsets that control for geographical proximity and geometric similarity between training and validation scenes. We introduce Fréchet distance-based reconstruction statistics that capture per-element shape fidelity without threshold tuning, and define complementary failure-mode scores: a localization overfitting score quantifying the performance drop when geographic cues disappear, and a map geometry overfitting score measuring degradation as scenes become geometrically novel. Beyond models, we analyze dataset biases and contribute map geometry-aware diagnostics: A minimum-spanning-tree (MST) diversity measure for training sets and a symmetric coverage measure to quantify geometric similarity between splits. Leveraging these, we formulate an MST-based sparsification strategy that reduces redundancy and improves balancing and performance while shrinking training size. Experiments on nuScenes and Argoverse 2 across multiple state-of-the-art models yield more trustworthy assessment of generalization and show that map geometry-diverse and balanced training sets lead to improved performance. Our results motivate failure-mode-aware protocols and map geometry-centric dataset design for deployable online mapping. --- ### Semantic Delta: An Interpretable Signal Differentiating Human and LLMs Dialogue Authors: Riccardo Scantamburlo, Mauro Mezzanzana, Giacomo Buonanno, Francesco Bertolotti Published: 2026-03-20 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.19849v1 Do LLMs talk like us? This question intrigues a multitude of scholar and it is relevant in many fields, from education to academia. This work presents an interpretable statistical feature for distinguishing human written and LLMs generated dialogue. We introduce a lightweight metric derived from semantic categories distribution. Using the Empath lexical analysis framework, each text is mapped to a set of thematic intensity scores. We define semantic delta as the difference between the two most dominant category intensities within a dialogue, hypothesizing that LLM outputs exhibit stronger thematic concentration than human discourse. To evaluate this hypothesis, conversational data were generated from multiple LLM configurations and compared against heterogeneous human corpora, including scripted dialogue, literary works, and online discussions. A Welch t-test was applied to the resulting distributions of semantic delta values. Results show that AI-generated texts consistently produce higher deltas than human texts, indicating a more rigid topics structure, whereas human dialogue displays a broader and more balanced semantic spread. Rather than replacing existing detection techniques, the proposed zero-shot metric provides a computationally inexpensive complementary signal that can be integrated into ensemble detection systems. These finding also contribute to the broader empirical understanding of LLM behavioural mimicry and suggest that thematic distribution constitutes a quantifiable dimension along which current models fall short of human conversational dynamics. --- ### Hyper-Connections for Adaptive Multi-Modal MRI Brain Tumor Segmentation Authors: Lokendra Kumar, Shubham Aggarwal Published: 2026-03-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.19844v2 We present the first study of Hyper-Connections (HC) for volumetric multi-modal brain tumor segmentation, integrating them as a drop-in replacement for fixed residual connections across five architectures: nnU-Net, SwinUNETR, VT-UNet, U-Net, and U-Netpp. Dynamic HC consistently improves all 3D models on the BraTS 2021 dataset, yielding up to +1.03 percent mean Dice gain with negligible parameter overhead. Gains are most pronounced in the Enhancing Tumor sub-region, reflecting improved fine-grained boundary delineation. Modality ablation further reveals that HC-equipped models develop sharper sensitivity toward clinically dominant sequences, specifically T1ce for Tumor Core and Enhancing Tumor, and FLAIR for Whole Tumor, a behavior absent in fixed-connection baselines and consistent across all architectures. In 2D settings, improvements are smaller and configuration-sensitive, suggesting that volumetric spatial context amplifies the benefit of adaptive aggregation. These results establish HC as a simple, efficient, and broadly applicable mechanism for multi-modal feature fusion in medical image segmentation. --- ### Overreliance on AI in Information-seeking from Video Content Authors: Anders Giovanni Møller, Elisa Bassignana, Francesco Pierri, Luca Maria Aiello Published: 2026-03-20 Categories: cs.CY, cs.CL, cs.HC arXiv: https://arxiv.org/abs/2603.19843v2 The ubiquity of multimedia content is reshaping online information spaces, particularly in social media environments. At the same time, search is being rapidly transformed by generative AI, with large language models (LLMs) routinely deployed as intermediaries between users and multimedia content to retrieve and summarize information. Despite their growing influence, the impact of LLM inaccuracies and potential vulnerabilities on multimedia information-seeking tasks remains largely unexplored. We investigate how generative AI affects accuracy, efficiency, and confidence in information retrieval from videos. We conduct an experiment with around 900 participants on 8,000+ video-based information-seeking tasks, comparing behavior across three conditions: (1) access to videos only, (2) access to videos with LLM-based AI assistance, and (3) access to videos with a deceiving AI assistant designed to provide false answers. We find that AI assistance increases accuracy by 3-7% when participants viewed the relevant video segment, and by 27-35% when they did not. Efficiency increases by 10% for short videos and 25% for longer ones. However, participants tend to over-rely on AI outputs, resulting in accuracy drops of up to 32% when interacting with the deceiving AI. Alarmingly, self-reported confidence in answers remains stable across all three conditions. Our findings expose fundamental safety risks in AI-mediated video information retrieval. --- ### Overreliance on AI in Information-seeking from Video Content Authors: Anders Giovanni Møller, Elisa Bassignana, Francesco Pierri, Luca Maria Aiello Published: 2026-03-20 Categories: cs.CY, cs.CL, cs.HC arXiv: https://arxiv.org/abs/2603.19843v1 The ubiquity of multimedia content is reshaping online information spaces, particularly in social media environments. At the same time, search is being rapidly transformed by generative AI, with large language models (LLMs) routinely deployed as intermediaries between users and multimedia content to retrieve and summarize information. Despite their growing influence, the impact of LLM inaccuracies and potential vulnerabilities on multimedia information-seeking tasks remains largely unexplored. We investigate how generative AI affects accuracy, efficiency, and confidence in information retrieval from videos. We conduct an experiment with around 900 participants on 8,000+ video-based information-seeking tasks, comparing behavior across three conditions: (1) access to videos only, (2) access to videos with LLM-based AI assistance, and (3) access to videos with a deceiving AI assistant designed to provide false answers. We find that AI assistance increases accuracy by 3-7% when participants viewed the relevant video segment, and by 27-35% when they did not. Efficiency increases by 10% for short videos and 25% for longer ones. However, participants tend to over-rely on AI outputs, resulting in accuracy drops of up to 32% when interacting with the deceiving AI. Alarmingly, self-reported confidence in answers remains stable across all three conditions. Our findings expose fundamental safety risks in AI-mediated video information retrieval. --- ### Modeling subgrid scale production rates on complex meshes using graph neural networks Authors: Priyabrat Dash, Mathis Bode, Konduri Aditya Published: 2026-03-20 Categories: physics.flu-dyn, cs.LG arXiv: https://arxiv.org/abs/2603.19841v1 Large-eddy simulations (LES) require closures for filtered production rates because the resolved fields do not contain all correlations that govern chemical source terms. We develop a graph neural network (GNN) that predicts filtered species production rates on non-uniform meshes from inputs of filtered mass fractions and temperature. Direct numerical simulations of turbulent premixed hydrogen-methane jet flames with hydrogen fractions of 10%, 50%, and 80% provide the dataset. All fields are Favre filtered with the filter width matched to the operating mesh, and learning is performed on subdomain graphs constructed from mesh-point connectivity. A compact set of reactants, intermediates, and products is used, and their filtered production rates form the targets. The model is trained on 10% and 80% blends and evaluated on the unseen 50% blend to test cross-composition generalization. The GNN is compared against an unclosed reference that evaluates rates at the filtered state, and a convolutional neural network baseline that requires remeshing. Across in-distribution and out-of-distribution cases, the GNN yields lower errors and closer statistical agreement with the reference data. Furthermore, the model demonstrates robust generalization across varying filter widths without retraining, maintaining bounded errors at coarser spatial resolutions. A backward facing step configuration further confirms prediction efficacy on a practically relevant geometry. These results highlight the capability of GNNs as robust data-driven closure models for LES on complex meshes. --- ### Explainable cluster analysis: a bagging approach Authors: Federico Maria Quetti, Elena Ballante, Silvia Figini, Paolo Giudici Published: 2026-03-20 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2603.19840v1 A major limitation of clustering approaches is their lack of explainability: methods rarely provide insight into which features drive the grouping of similar observations. To address this limitation, we propose an ensemble-based clustering framework that integrates bagging and feature dropout to generate feature importance scores, in analogy with feature importance mechanisms in supervised random forests. By leveraging multiple bootstrap resampling schemes and aggregating the resulting partitions, the method improves stability and robustness of the cluster definition, particularly in small-sample or noisy settings. Feature importance is assessed through an information-theoretic approach: at each step, the mutual information between each feature and the estimated cluster labels is computed and weighted by a measure of clustering validity to emphasize well-formed partitions, before being aggregated into a final score. The method outputs both a consensus partition and a corresponding measure of feature importance, enabling a unified interpretation of clustering structure and variable relevance. Its effectiveness is demonstrated on multiple simulated and real-world datasets. --- ### FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization Authors: Chiyu Ma, Shuo Yang, Kexin Huang, Jinda Lu, Haoming Meng, Shangshang Wang, Bolin Ding, Soroush Vosoughi, Guoyin Wang, Jingren Zhou Published: 2026-03-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.19835v3 We present Future-KL Influenced Policy Optimization (FIPO), a reinforcement learning algorithm designed to overcome reasoning bottlenecks in large language models. While GRPO style training scales effectively, it typically relies on outcome-based rewards (ORM) that distribute a global advantage uniformly across every token in a trajectory. We argue that this coarse-grained credit assignment imposes a performance ceiling by failing to distinguish critical logical pivots from trivial tokens. FIPO addresses this by incorporating discounted future-KL divergence into the policy update, creating a dense advantage formulation that re-weights tokens based on their influence on subsequent trajectory behavior. Empirically, FIPO enables models to break through the length stagnation seen in standard baselines. Evaluated on Qwen2.5-32B, FIPO extends the average chain-of-thought length from roughly 4,000 to over 10,000 tokens and increases AIME 2024 Pass@1 accuracy from 50.0% to a peak of 58.0% (converging at approximately 56.0\%). This outperforms both DeepSeek-R1-Zero-Math-32B (around 47.0%) and o1-mini (approximately 56.0%). Our results suggest that establishing dense advantage formulations is a vital path for evolving ORM-based algorithms to unlock the full reasoning potential of base models. We open-source our training system, built on the verl framework. --- ### Fourier Splatting: Generalized Fourier encoded primitives for scalable radiance fields Authors: Mihnea-Bogdan Jurca, Bert Van hauwermeiren, Adrian Munteanu Published: 2026-03-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.19834v3 Novel view synthesis has recently been revolutionized by 3D Gaussian Splatting (3DGS), which enables real-time rendering through explicit primitive rasterization. However, existing methods tie visual fidelity strictly to the number of primitives: quality downscaling is achieved only through pruning primitives. We propose the first inherently scalable primitive for radiance field rendering. Fourier Splatting employs scalable primitives with arbitrary closed shapes obtained by parameterizing planar surfels with Fourier encoded descriptors. This formulation allows a single trained model to be rendered at varying levels of detail simply by truncating Fourier coefficients at runtime. To facilitate stable optimization, we employ a straight-through estimator for gradient extension beyond the primitive boundary, and introduce HYDRA, a densification strategy that decomposes complex primitives into simpler constituents within the MCMC framework. Our method achieves state-of-the-art rendering quality among planar-primitive frameworks and comparable perceptual metrics compared to leading volumetric representations on standard benchmarks, providing a versatile solution for bandwidth-constrained high-fidelity rendering. --- ### Gesture2Speech: How Far Can Hand Movements Shape Expressive Speech? Authors: Lokesh Kumar, Nirmesh Shah, Ashishkumar P. Gudmalwar, Pankaj Wasnik Published: 2026-03-20 Categories: eess.AS, cs.AI, cs.MM arXiv: https://arxiv.org/abs/2603.19831v1 Human communication seamlessly integrates speech and bodily motion, where hand gestures naturally complement vocal prosody to express intent, emotion, and emphasis. While recent text-to-speech (TTS) systems have begun incorporating multimodal cues such as facial expressions or lip movements, the role of hand gestures in shaping prosody remains largely underexplored. We propose a novel multimodal TTS framework, Gesture2Speech, that leverages visual gesture cues to modulate prosody in synthesized speech. Motivated by the observation that confident and expressive speakers coordinate gestures with vocal prosody, we introduce a multimodal Mixture-of-Experts (MoE) architecture that dynamically fuses linguistic content and gesture features within a dedicated style extraction module. The fused representation conditions an LLM-based speech decoder, enabling prosodic modulation that is temporally aligned with hand movements. We further design a gesture-speech alignment loss that explicitly models their temporal correspondence to ensure fine-grained synchrony between gestures and prosodic contours. Evaluations on the PATS dataset show that Gesture2Speech outperforms state-of-the-art baselines in both speech naturalness and gesture-speech synchrony. To the best of our knowledge, this is the first work to utilize hand gesture cues for prosody control in neural speech synthesis. Demo samples are available at https://research.sri-media-analysis.com/aaai26-beeu-gesture2speech/ --- ### FormalEvolve: Neuro-Symbolic Evolutionary Search for Diverse Autoformalization Authors: Haijian Lu, Wei Wang, Jing Liu Published: 2026-03-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.19828v4 Autoformalization aims to produce formal statements that compile and faithfully preserve the intended meaning of informal mathematics. Yet standard single-output evaluation collapses this many-to-many structure into a single prediction. For downstream proving, this granularity is too coarse: a formal statement is not merely a faithful translation endpoint, but also a prover-facing interface whose structure can alter proof search under a fixed budget. We therefore recast autoformalization as budgeted test-time search: FormalEvolve maintains a compilation-feasible archive for reuse and returns a deduplicated, semantically accepted repertoire for evaluation and downstream proving. It expands the archive with LLM-driven mutation, crossover, bounded patch repair, and symbolic abstract syntax tree (AST) rewrites for structural diversity. Under a generator-call budget of T=100 with a fixed LLM semantic judge, FormalEvolve reaches SH@100 of 58.0% on CombiBench and 84.9% on ProofNet, improving over all no-archive controls while reducing the cross-problem concentration of semantic successes. Under a fixed B=64 prover budget, these repertoires improve theorem-complete proving over the matched no-archive control. Additional stronger-base statement-generation experiments show that archive-search gains persist with stronger seed and repair models. --- ### FormalEvolve: Neuro-Symbolic Evolutionary Search for Diverse Autoformalization Authors: Haijian Lu, Wei Wang, Jing Liu Published: 2026-03-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.19828v3 Autoformalization aims to produce formal statements that compile and faithfully preserve the intended meaning of informal mathematics. Yet standard single-output evaluation protocols collapse a many-to-many problem into a single-output prediction task. For downstream proving, this granularity is too coarse: a formal statement is not merely a faithful translation endpoint, but also a prover-facing interface whose structure can alter proof search under a fixed budget. We therefore recast autoformalization as budgeted test-time search: FormalEvolve maintains a compilation-feasible archive for reuse, while reporting the deduplicated semantically accepted repertoire for evaluation and downstream proving. It expands the archive with LLM-driven mutation, crossover, bounded patch repair, and symbolic Abstract Syntax Tree (AST) rewrites for structural diversity. Under a generator-call budget of T=100 with a fixed LLM semantic judge, FormalEvolve reaches SH@100 of 58.0% on CombiBench and 84.9% on ProofNet, improving over all no-archive controls while reducing the cross-problem concentration of semantic successes. To assess downstream value, we evaluate the resulting repertoires under a fixed B=64 prover budget, where they improve theorem-complete proving over the matched no-archive control; additional stronger-base statement-generation experiments show that archive-search gains hold with stronger seed and repair models. Manual faithfulness audits calibrate these judge-positive outputs. --- ### FrameNet Semantic Role Classification by Analogy Authors: Van-Duy Ngo, Stergos Afantenos, Emiliano Lorini, Miguel Couceiro Published: 2026-03-20 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.19825v1 In this paper, we adopt a relational view of analogies applied to Semantic Role Classification in FrameNet. We define analogies as formal relations over the Cartesian product of frame evoking lexical units (LUs) and frame element (FEs) pairs, which we use to construct a new dataset. Each element of this binary relation is labelled as a valid analogical instance if the frame elements share the same semantic role, or as invalid otherwise. This formulation allows us to transform Semantic Role Classification into binary classification and train a lightweight Artificial Neural Network (ANN) that exhibits rapid convergence with minimal parameters. Unconventionally, no Semantic Role information is introduced to the neural network during training. We recover semantic roles during inference by computing probability distributions over candidates of all semantic roles within a given frame through random sampling and analogical transfer. This approach allows us to surpass previous state-of-the-art results while maintaining computational efficiency and frugality. --- ### HUGE-Bench: A Benchmark for High-Level UAV Vision-Language-Action Tasks Authors: Jingyu Guo, Ziye Chen, Ziwen Li, Zhengqing Gao, Jiaxin Huang, Hanlue Zhang, Fengming Huang, Yu Yao, Tongliang Liu, Mingming Gong Published: 2026-03-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.19822v4 Existing UAV vision-language navigation (VLN) benchmarks have enabled language-guided flight, but they largely focus on long, step-wise route descriptions with goal-centric evaluation, making them less diagnostic for real operations where brief, high-level commands must be grounded into safe multi-stage behaviors. We present HUGE-Bench, a benchmark for High-Level UAV Vision-Language-Action (HL-VLA) tasks that tests whether an agent can interpret concise language and execute complex, process-oriented trajectories with safety awareness. HUGE-Bench comprises 4 real-world digital twin scenes, 8 high-level tasks, and 2.56M meters of trajectories, and is built on an aligned 3D Gaussian Splatting (3DGS)-Mesh representation that combines photorealistic rendering with collision-capable geometry for scalable generation and collision-aware evaluation. We introduce process-oriented and collision-aware metrics to assess process fidelity, terminal accuracy, and safety. Experiments on representative state-of-the-art VLA models reveal significant gaps in high-level semantic completion and safe execution, highlighting HUGE-Bench as a diagnostic testbed for high-level UAV autonomy. --- ### GDEGAN: Gaussian Dynamic Equivariant Graph Attention Network for Ligand Binding Site Prediction Authors: Animesh, Plaban Kumar Bhowmick, Pralay Mitra Published: 2026-03-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.19817v1 Accurate prediction of binding sites of a given protein, to which ligands can bind, is a critical step in structure-based computational drug discovery. Recently, Equivariant Graph Neural Networks (GNNs) have emerged as a powerful paradigm for binding site identification methods due to the large-scale availability of 3D structures of proteins via protein databases and AlphaFold predictions. The state-of-the-art equivariant GNN methods implement dot product attention, disregarding the variation in the chemical and geometric properties of the neighboring residues. To capture this variation, we propose GDEGAN (Gaussian Dynamic Equivariant Graph Attention Network), which replaces dot-product attention with adaptive kernels that recognize binding sites. The proposed attention mechanism captures variation in neighboring residues using statistics of their characteristic local feature distributions. Our mechanism dynamically computes neighborhood statistics at each layer, using local variance as an adaptive bandwidth parameter with learnable per-head temperatures, enabling each protein region to determine its own context-specific importance. GDEGAN outperforms existing methods with relative improvements of 37-66% in DCC and 7-19% DCA success rates across COACH420, HOLO4k, and PDBBind2020 datasets. These advances have direct application in accelerating protein-ligand docking by identifying potential binding sites for therapeutic target identification. --- ### Eye Gaze-Informed and Context-Aware Pedestrian Trajectory Prediction in Shared Spaces with Automated Shuttles: A Virtual Reality Study Authors: Danya Li, Yan Feng, Rico Krueger Published: 2026-03-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.19812v2 To address this gap, we conduct a Virtual Reality experiment in which pedestrians interact with automated shuttles under varying approach angles (45°, 90°, 135°) and continuous-traffic conditions (single shuttle, two shuttles with 3 or 5-second gaps), collecting synchronized motion, eye gaze, and head orientation data. To investigate to what extent, under what conditions, and in what form fine-grained eye gaze is informative for pedestrian motion prediction, we develop a multi-modal prediction model that fuses these signals through modality-specific encoders, and systematically ablate gaze representations against head orientation and situational context. We report three main results. First, the predictive value of eye gaze is angle-dependent and tightly coupled with eye-head-body coordination: at acute angles where pedestrians actively redirect gaze to acquire the shuttle, eye gaze carries information that head orientation alone misses. Second, continuous gaze orientation outperforms categorical semantic fixation labels, with the optimal encoding frame (global or body-relative) depending on whether gaze is used alone or jointly with context. Third, eye gaze and situational context provide complementary predictive information: their combination reduces final displacement error (FDE) by 8.47%, close to the sum of their individual contributions. Together, these findings highlight the value of incorporating human perceptual signals into pedestrian behavior prediction and motivate a human-centered complement to vehicle-centric modeling approaches. Our code is available at https://github.com/danyayay/GazeX.git. ---