# Research Papers — 2026-03 · bundle page 179 of 243 > Full-text markdown of papers #8901–8950 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/179 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/178.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/180.md) ### BuildMamba: A Visual State-Space Based Model for Multi-Task Building Segmentation and Height Estimation from Satellite Images Authors: Sinan U. Ulu, A. Enes Doruk, I. Can Yagmur, Bahadir K. Gunturk, Oguz Hanoglu, Hasan F. Ates Published: 2026-03-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.08523v1 Accurate building segmentation and height estimation from single-view RGB satellite imagery are fundamental for urban analytics, yet remain ill-posed due to structural variability and the high computational cost of global context modeling. While current approaches typically adapt monocular depth architectures, they often suffer from boundary bleeding and systematic underestimation of high-rise structures. To address these limitations, we propose BuildMamba, a unified multi-task framework designed to exploit the linear-time global modeling of visual state-space models. Motivated by the need for stronger structural coupling and computational efficiency, we introduce three modules: a Mamba Attention Module for dynamic spatial recalibration, a Spatial-Aware Mamba-FPN for multi-scale feature aggregation via gated state-space scans, and a Mask-Aware Height Refinement module using semantic priors to suppress height artifacts. Extensive experiments demonstrate that BuildMamba establishes a new performance upper bound across three benchmarks. Specifically, it achieves an IoU of 0.93 and RMSE of 1.77~m on DFC23 benchmark, surpassing state-of-the-art by 0.82~m in height estimation. Simulation results confirm the model's superior robustness and scalability for large-scale 3D urban reconstruction. --- ### OccTrack360: 4D Panoptic Occupancy Tracking from Surround-View Fisheye Cameras Authors: Yongzhi Lin, Kai Luo, Yuanfan Zheng, Hao Shi, Mengfei Duan, Yang Liu, Kailun Yang Published: 2026-03-09 Categories: cs.CV, cs.RO, eess.IV arXiv: https://arxiv.org/abs/2603.08521v3 Understanding dynamic 3D environments in a spatially continuous and temporally consistent manner is fundamental for robotics and autonomous driving. While recent advances in occupancy prediction provide a unified representation of scene geometry and semantics, progress in 4D panoptic occupancy tracking remains limited by the lack of benchmarks that support surround-view fisheye sensing, long temporal sequences, and instance-level voxel tracking. To address this gap, we present OccTrack360, a new benchmark for 4D panoptic occupancy tracking from surround-view fisheye cameras. OccTrack360 provides substantially longer and more diverse sequences (174~2234 frames) than prior benchmarks, together with principled voxel visibility annotations, including an all-direction occlusion mask and an MEI-based fisheye field-of-view mask. To establish a strong fisheye-oriented baseline, we further propose Focus on Sphere Occ (FoSOcc), a framework that addresses two core challenges in fisheye occupancy tracking: distorted spherical projection and inaccurate voxel-space localization. FoSOcc includes a Center Focusing Module (CFM) to enhance instance-aware spatial localization through supervised focus guidance, and a Fisheye-based Enhanced Lifting (FEL) that extends perspective lifting to fisheye imaging under the Unified Projection Model. Extensive experiments on Occ3D-Waymo and OccTrack360 show that our method improves occupancy tracking quality with notable gains on geometrically regular categories, and establishes a strong baseline for future research on surround-view fisheye 4D occupancy tracking. The benchmark and source code will be made publicly available at https://github.com/YouthZest-Lin/OccTrack360. --- ### Breaking the Bias Barrier in Concave Multi-Objective Reinforcement Learning Authors: Swetha Ganesh, Vaneet Aggarwal Published: 2026-03-09 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2603.08518v1 While standard reinforcement learning optimizes a single reward signal, many applications require optimizing a nonlinear utility $f(J_1^π,\dots,J_M^π)$ over multiple objectives, where each $J_m^π$ denotes the expected discounted return of a distinct reward function. A common approach is concave scalarization, which captures important trade-offs such as fairness and risk sensitivity. However, nonlinear scalarization introduces a fundamental challenge for policy gradient methods: the gradient depends on $\partial f(J^π)$, while in practice only empirical return estimates $\hat J$ are available. Because $f$ is nonlinear, the plug-in estimator is biased ($\mathbb{E}(\partial f(\hat J)) \neq \partial f(\mathbb{E}(\hat J))$), leading to persistent gradient bias that degrades sample complexity. In this work we identify and overcome this bias barrier in concave-scalarized multi-objective reinforcement learning. We show that existing policy-gradient methods suffer an intrinsic $\widetilde{\mathcal{O}}(ε^{-4})$ sample complexity due to this bias. To address this issue, we develop a Natural Policy Gradient (NPG) algorithm equipped with a multi-level Monte Carlo (MLMC) estimator that controls the bias of the scalarization gradient while maintaining low sampling cost. We prove that this approach achieves the optimal $\widetilde{\mathcal{O}}(ε^{-2})$ sample complexity for computing an $ε$-optimal policy. Furthermore, we show that when the scalarization function is second-order smooth, the first-order bias cancels automatically, allowing vanilla NPG to achieve the same $\widetilde{\mathcal{O}}(ε^{-2})$ rate without MLMC. Our results provide the first optimal sample complexity guarantees for concave multi-objective reinforcement learning under policy-gradient methods. --- ### Beyond Hungarian: Match-Free Supervision for End-to-End Object Detection Authors: Shoumeng Qiu, Xinrun Li, Yang Long Published: 2026-03-09 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.08514v1 Recent DEtection TRansformer (DETR) based frameworks have achieved remarkable success in end-to-end object detection. However, the reliance on the Hungarian algorithm for bipartite matching between queries and ground truths introduces computational overhead and complicates the training dynamics. In this paper, we propose a novel matching-free training scheme for DETR-based detectors that eliminates the need for explicit heuristic matching. At the core of our approach is a dedicated Cross-Attention-based Query Selection (CAQS) module. Instead of discrete assignment, we utilize encoded ground-truth information to probe the decoder queries through a cross-attention mechanism. By minimizing the weighted error between the queried results and the ground truths, the model autonomously learns the implicit correspondences between object queries and specific targets. This learned relationship further provides supervision signals for the learning of queries. Experimental results demonstrate that our proposed method bypasses the traditional matching process, significantly enhancing training efficiency, reducing the matching latency by over 50\%, effectively eliminating the discrete matching bottleneck through differentiable correspondence learning, and also achieving superior performance compared to existing state-of-the-art methods. --- ### Oracle-Guided Soft Shielding for Safe Move Prediction in Chess Authors: Prajit T Rajendran, Fabio Arnez, Huascar Espinoza, Agnes Delaborde, Chokri Mraidha Published: 2026-03-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.08506v1 In high stakes environments, agents relying purely on imitation learning or reinforcement learning often struggle to avoid safety-critical errors during exploration. Existing reinforcement learning approaches for environments such as chess require hundreds of thousands of episodes and substantial computational resources to converge. Imitation learning, on the other hand, is more sample efficient but is brittle under distributional shift and lacks mechanisms for proactive risk avoidance. In this work, we propose Oracle-Guided Soft Shielding (OGSS), a simple yet effective framework for safer decision-making, enabling safe exploration by learning a probabilistic safety model from oracle feedback in an imitation learning setting. Focusing on the domain of chess, we train a model to predict strong moves based on past games, and separately learn a blunder prediction model from Stockfish evaluations to estimate the tactical risk of each move. During inference, the agent first generates a set of candidate moves and then uses the blunder model to determine high-risk options, and uses a utility function combining the predicted move likelihood from the policy model and the blunder probability to select actions that strike a balance between performance and safety. This enables the agent to explore and play competitively while significantly reducing the chance of tactical mistakes. Across hundreds of games against a strong chess engine, we compare our approach with other methods in the literature, such as action pruning, SafeDAgger, and uncertainty-based sampling. Our results demonstrate that OGSS variants maintain a lower blunder rate even as the agent's exploration ratio is increased by several folds, highlighting its ability to support broader exploration without compromising tactical soundness. --- ### Echo2ECG: Enhancing ECG Representations with Cardiac Morphology from Multi-View Echos Authors: Michelle Espranita Liman, Özgün Turgut, Alexander Müller, Eimo Martens, Daniel Rueckert, Philip Müller Published: 2026-03-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.08505v2 Electrocardiography (ECG) is a low-cost, widely used modality for diagnosing electrical abnormalities like atrial fibrillation by capturing the heart's electrical activity. However, it cannot directly measure cardiac morphological phenotypes, such as left ventricular ejection fraction (LVEF), which typically require echocardiography (Echo). Predicting these phenotypes from ECG would enable early, accessible health screening. Existing self-supervised methods suffer from a representational mismatch by aligning ECGs to single-view Echos, which only capture local, spatially restricted anatomical snapshots. To address this, we propose Echo2ECG, a multimodal self-supervised learning framework that enriches ECG representations with the heart's morphological structure captured in multi-view Echos. We evaluate Echo2ECG as an ECG feature extractor on two clinically relevant tasks that fundamentally require morphological information: (1) classification of structural cardiac phenotypes across three datasets, and (2) retrieval of Echo studies with similar morphological characteristics using ECG queries. Our extracted ECG representations consistently outperform those of state-of-the-art unimodal and multimodal baselines across both tasks, despite being 18x smaller than the largest baseline. These results demonstrate that Echo2ECG is a robust, powerful ECG feature extractor. Our code is accessible at https://github.com/michelleespranita/Echo2ECG. --- ### Spherical-GOF: Geometry-Aware Panoramic Gaussian Opacity Fields for 3D Scene Reconstruction Authors: Zhe Yang, Guoqiang Zhao, Sheng Wu, Kai Luo, Kailun Yang Published: 2026-03-09 Categories: cs.CV, cs.GR, cs.RO, eess.IV arXiv: https://arxiv.org/abs/2603.08503v2 Omnidirectional images are increasingly used in robotics and vision due to their wide field of view. However, extending 3D Gaussian Splatting (3DGS) to panoramic camera models remains challenging, as existing formulations are designed for perspective projections and naive adaptations often introduce distortion and geometric inconsistencies. We present Spherical-GOF, an omnidirectional Gaussian rendering framework built upon Gaussian Opacity Fields (GOF). Unlike projection-based rasterization, Spherical-GOF performs GOF ray sampling directly on the unit sphere in spherical ray space, enabling consistent ray-Gaussian interactions for panoramic rendering. To make the spherical ray casting efficient and robust, we derive a conservative spherical bounding rule for fast ray-Gaussian culling and introduce a spherical filtering scheme that adapts Gaussian footprints to distortion-varying panoramic pixel sampling. Extensive experiments on standard panoramic benchmarks (OmniBlender and OmniPhotos) demonstrate competitive photometric quality and substantially improved geometric consistency. Compared with the strongest baseline, Spherical-GOF reduces depth reprojection error by 57% and improves cycle inlier ratio by 21%. Qualitative results show cleaner depth and more coherent normal maps, with strong robustness to global panorama rotations. We further validate generalization on OmniRob, a real-world robotic omnidirectional dataset introduced in this work, featuring UAV and quadruped platforms. The source code and the OmniRob dataset will be released at https://github.com/1170632760/Spherical-GOF. --- ### Fanar-Sadiq: A Multi-Agent Architecture for Grounded Islamic QA Authors: Ummar Abbas, Mourad Ouzzani, Mohamed Y. Eltabakh, Omar Sinan, Gagan Bhatia, Hamdy Mubarak, Majd Hawasly, Mohammed Qusay Hashim, Kareem Darwish, Firoj Alam Published: 2026-03-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.08501v3 Large language models (LLMs) can answer religious knowledge queries fluently, yet they often hallucinate and misattribute sources, which is especially consequential in Islamic settings where users expect grounding in canonical texts (Qur'an and Hadith) and jurisprudential (fiqh) nuance. Retrieval-augmented generation (RAG) improves grounding, however, a single retrieve-then-generate pipeline is insufficient for diverse Islamic queries, including verbatim scripture, citation-grounded guidance, and rule-constrained computations such as zakat and inheritance. To address these challenges, we present Fanar-Sadiq, a bilingual Arabic-English Islamic QA system built on a multi-agent, tool-augmented architecture. It is a core component of the Fanar AI platform. Fanar-Sadiq routes Islamic queries to specialized modules within an agentic tool architecture. It supports intent-aware routing, retrieval-grounded fiqh answers with normalized citations and verification traces, exact verse lookup with quotation validation, and deterministic Sunni zakat and inheritance calculators with madhhab-sensitive branching. We evaluate the end-to-end system on public Islamic QA benchmarks and show strong effectiveness and efficiency. It is publicly accessible through an API and Web application and has received over 1.9M accesses in less than a year (https://api.fanar.qa/docs). --- ### Improving Continual Learning for Gaussian Splatting based Environments Reconstruction on Commercial Off-the-Shelf Edge Devices Authors: Ivan Zaino, Matteo Risso, Daniele Jahier Pagliari, Miguel de Prado, Toon Van de Maele, Alessio Burrello Published: 2026-03-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.08499v1 Novel view synthesis (NVS) is increasingly relevant for edge robotics, where compact and incrementally updatable 3D scene models are needed for SLAM, navigation, and inspection under tight memory and latency budgets. Variational Bayesian Gaussian Splatting (VBGS) enables replay-free continual updates for the 3DGS algorithm by maintaining a probabilistic scene model, but its high-precision computations and large intermediate tensors make on-device training impractical. We present a precision-adaptive optimization framework that enables VBGS training on resource-constrained hardware without altering its variational formulation. We (i) profile VBGS to identify memory/latency hotspots, (ii) fuse memory-dominant kernels to reduce materialized intermediate tensors, and (iii) automatically assign operation-level precisions via a mixed-precision search with bounded relative error. Across the Blender, Habitat, and Replica datasets, our optimised pipeline reduces peak memory from 9.44 GB to 1.11 GB and training time from ~234 min to ~61 min on an A5000 GPU, while preserving (and in some cases improving) reconstruction quality of the state-of-the-art VBGS baseline. We also enable for the first time NVS training on a commercial embedded platform, the Jetson Orin Nano, reducing per-frame latency by 19x compared to 3DGS. --- ### All Vehicles Can Lie: Efficient Adversarial Defense in Fully Untrusted-Vehicle Collaborative Perception via Pseudo-Random Bayesian Inference Authors: Yi Yu, Libing Wu, Zhuangzhuang Zhang, Jing Qiu, Lijuan Huo, Jiaqi Feng Published: 2026-03-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.08498v1 Collaborative perception (CP) enables multiple vehicles to augment their individual perception capacities through the exchange of feature-level sensory data. However, this fusion mechanism is inherently vulnerable to adversarial attacks, especially in fully untrusted-vehicle environments. Existing defense approaches often assume a trusted ego vehicle as a reference or incorporate additional binary classifiers. These assumptions limit their practicality in real-world deployments due to the questionable trustworthiness of ego vehicles, the requirement for real-time detection, and the need for generalizability across diverse scenarios. To address these challenges, we propose a novel Pseudo-Random Bayesian Inference (PRBI) framework, a first efficient defense method tailored for fully untrusted-vehicle CP. PRBI detects adversarial behavior by leveraging temporal perceptual discrepancies, using the reliable perception from the preceding frame as a dynamic reference. Additionally, it employs a pseudo-random grouping strategy that requires only two verifications per frame, while applying Bayesian inference to estimate both the number and identities of malicious vehicles. Theoretical analysis has proven the convergence and stability of the proposed PRBI framework. Extensive experiments show that PRBI requires only 2.5 verifications per frame on average, outperforming existing methods significantly, and restores detection precision to between 79.4% and 86.9% of pre-attack levels. --- ### Reading $\neq$ Seeing: Diagnosing and Closing the Typography Gap in Vision-Language Models Authors: Heng Zhou, Ao Yu, Li Kang, Yuchen Fan, Yutao Fan, Xiufeng Song, Hejia Geng, Yiran Qin Published: 2026-03-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.08497v1 Vision-Language Models achieve near-perfect accuracy at reading text in images, yet prove largely typography-blind: capable of recognizing what text says, but not how it looks. We systematically investigate this gap by evaluating font family, size, style, and color recognition across 26 fonts, four scripts, and three difficulty levels. Our evaluation of 15 state-of-the-art VLMs reveals a striking perception hierarchy: color recognition is near-perfect, yet font style detection remains universally poor. We further find that model scale fails to predict performance and that accuracy is uniform across difficulty levels, together pointing to a training-data omission rather than a capacity ceiling. LoRA fine-tuning on a small set of synthetic samples substantially improves an open-source model, narrowing the gap to the best closed-source system and surpassing it on font size recognition. Font style alone remains resistant to fine-tuning, suggesting that relational visual reasoning may require architectural innovation beyond current patch-based encoders. We release our evaluation framework, data, and fine-tuning recipe to support progress in closing the typographic gap in vision-language understanding. --- ### Efficient Credal Prediction through Decalibration Authors: Paul Hofman, Timo Löhr, Maximilian Muschalik, Yusuf Sale, Eyke Hüllermeier Published: 2026-03-09 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2603.08495v1 A reliable representation of uncertainty is essential for the application of modern machine learning methods in safety-critical settings. In this regard, the use of credal sets (i.e., convex sets of probability distributions) has recently been proposed as a suitable approach to representing epistemic uncertainty. However, as with other approaches to epistemic uncertainty, training credal predictors is computationally complex and usually involves (re-)training an ensemble of models. The resulting computational complexity prevents their adoption for complex models such as foundation models and multi-modal systems. To address this problem, we propose an efficient method for credal prediction that is grounded in the notion of relative likelihood and inspired by techniques for the calibration of probabilistic classifiers. For each class label, our method predicts a range of plausible probabilities in the form of an interval. To produce the lower and upper bounds of these intervals, we propose a technique that we refer to as decalibration. Extensive experiments show that our method yields credal sets with strong performance across diverse tasks, including coverage-efficiency evaluation, out-of-distribution detection, and in-context learning. Notably, we demonstrate credal prediction on models such as TabPFN and CLIP -- architectures for which the construction of credal sets was previously infeasible. --- ### First-Order Geometry, Spectral Compression, and Structural Compatibility under Bounded Computation Authors: Changkai Li Published: 2026-03-09 Categories: math.OC, cs.AI arXiv: https://arxiv.org/abs/2603.08494v1 Optimization under structural constraints is typically analyzed through projection or penalty methods, obscuring the geometric mechanism by which constraints shape admissible dynamics. We propose an operator-theoretic formulation in which computational or feasibility limitations are encoded by self-adjoint operators defining locally reachable subspaces. In this setting, the optimal first-order improvement direction emerges as a pseudoinverse-weighted gradient, revealing how constraints induce a distorted ascent geometry. We further demonstrate that effective dynamics concentrate along dominant spectral modes, yielding a principled notion of spectral compression, and establish a compatibility principle that characterizes the existence of common admissible directions across multiple objectives. The resulting framework unifies gradient projection, spectral truncation, and multi-objective feasibility within a single geometric structure. --- ### Pareto-Optimal Anytime Algorithms via Bayesian Racing Authors: Jonathan Wurth, Helena Stegherr, Neele Kemper, Michael Heider, Jörg Hähner Published: 2026-03-09 Categories: cs.NE, cs.LG arXiv: https://arxiv.org/abs/2603.08493v1 Selecting an optimization algorithm requires comparing candidates across problem instances, but the computational budget for deployment is often unknown at benchmarking time. Current methods either collapse anytime performance into a scalar, require manual interpretation of plots, or produce conclusions that change when algorithms are added or removed. Moreover, methods based on raw objective values require normalization, which needs bounds or optima that are often unavailable and breaks coherent aggregation across instances. We propose a framework that formulates anytime algorithm comparison as Pareto optimization over time: an algorithm is non-dominated if no competitor beats it at every timepoint. By using rankings rather than objective values, our approach requires no bounds, no normalization, and aggregates coherently across arbitrary instance distributions without requiring known optima. We introduce PolarBear (Pareto-optimal anytime algorithms via Bayesian racing), a procedure that identifies the anytime Pareto set through adaptive sampling with calibrated uncertainty. Bayesian inference over a temporal Plackett-Luce ranking model provides posterior beliefs about pairwise dominance, enabling early elimination of confidently dominated algorithms. The output Pareto set together with the posterior supports downstream algorithm selection under arbitrary time preferences and risk profiles without additional experiments. --- ### Global Cross-Modal Geo-Localization: A Million-Scale Dataset and a Physical Consistency Learning Framework Authors: Yutong Hu, Jinhui Chen, Chaoqiang Xu, Yuan Kou, Sili Zhou, Shaocheng Yan, Pengcheng Shi, Qingwu Hu, Jiayuan Li Published: 2026-03-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.08491v2 Cross-modal Geo-localization (CMGL) matches ground-level text descriptions with geo-tagged aerial imagery, which is crucial for pedestrian navigation and emergency response. However, existing studies are constrained by narrow geographic coverage and simplistic scene diversity, failing to reflect the immense spatial heterogeneity of global architectural styles and topographic features. To bridge this gap and facilitate universal positioning, we introduce CORE, the first million-scale dataset dedicated to global CMGL. CORE comprises 1,034,786 cross-view images sampled from 225 distinct geographic regions across six continents, offering an unprecedented variety of perspectives in varying environmental conditions and urban layouts. We leverage the zero-shot reasoning of Large Vision-Language Models (LVLMs) to synthesize high-quality scene descriptions rich in discriminative cues. Furthermore, we propose a physical-law-aware network (PLANET) for cross-modal geo-localization. PLANET introduces a novel contrastive learning paradigm to guide textual representations in capturing the intrinsic physical signatures of satellite imagery. Extensive experiments across varied geographic regions demonstrate that PLANET significantly outperforms state-of-the-art methods, establishing a new benchmark for robust, global-scale geo-localization. The dataset and source code will be released at https://github.com/YtH0823/CORE. --- ### NN-OpInf: an operator inference approach using structure-preserving composable neural networks Authors: Eric Parish, Anthony Gruber, Patrick Blonigan, Irina Tezaur Published: 2026-03-09 Categories: cs.LG, math.DS arXiv: https://arxiv.org/abs/2603.08488v1 We propose neural network operator inference (NN-OpInf): a structure-preserving, composable, and minimally restrictive operator inference framework for the non-intrusive reduced-order modeling of dynamical systems. The approach learns latent dynamics from snapshot data, enforcing local operator structure such as skew-symmetry, (semi-)positive definiteness, and gradient preservation, while also reflecting complex dynamics by supporting additive compositions of heterogeneous operators. We present practical training strategies and analyze computational costs relative to linear and quadratic polynomial OpInf (P-OpInf). Numerical experiments across several nonlinear and parametric problems demonstrate improved accuracy, stability, and robustness over P-OpInf and prior NN-ROM formulations, particularly when the dynamics are not well represented by polynomial models. These results suggest that NN-OpInf can serve as an effective drop-in replacement for P-OpInf when the dynamics to be modeled contain non-polynomial nonlinearities, offering potential gains in accuracy and out-of-distribution performance at the expense of higher training computational costs and a more difficult, non-convex learning problem. --- ### Visual Self-Fulfilling Alignment: Shaping Safety-Oriented Personas via Threat-Related Images Authors: Qishun Yang, Shu Yang, Lijie Hu, Di Wang Published: 2026-03-09 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.08486v2 Multimodal large language models (MLLMs) face safety misalignment, where visual inputs enable harmful outputs. To address this, existing methods require explicit safety labels or contrastive data; yet, threat-related concepts are concrete and visually depictable, while safety concepts, like helpfulness, are abstract and lack visual referents. Inspired by the Self-Fulfilling mechanism underlying emergent misalignment, we propose Visual Self-Fulfilling Alignment (VSFA). VSFA fine-tunes vision-language models (VLMs) on neutral VQA tasks constructed around threat-related images, without any safety labels. Through repeated exposure to threat-related visual content, models internalize the implicit semantics of vigilance and caution, shaping safety-oriented personas. Experiments across multiple VLMs and safety benchmarks demonstrate that VSFA reduces the attack success rate, improves response quality, and mitigates over-refusal while preserving general capabilities. Our work extends the self-fulfilling mechanism from text to visual modalities, offering a label-free approach to VLMs alignment. --- ### X-AVDT: Audio-Visual Cross-Attention for Robust Deepfake Detection Authors: Youngseo Kim, Kwan Yun, Seokhyeon Hong, Sihun Cha, Colette Suhjung Koo, Junyong Noh Published: 2026-03-09 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.08483v1 The surge of highly realistic synthetic videos produced by contemporary generative systems has significantly increased the risk of malicious use, challenging both humans and existing detectors. Against this backdrop, we take a generator-side view and observe that internal cross-attention mechanisms in these models encode fine-grained speech-motion alignment, offering useful correspondence cues for forgery detection. Building on this insight, we propose X-AVDT, a robust and generalizable deepfake detector that probes generator-internal audio-visual signals accessed via DDIM inversion to expose these cues. X-AVDT extracts two complementary signals: (i) a video composite capturing inversion-induced discrepancies, and (ii) an audio-visual cross-attention feature reflecting modality alignment enforced during generation. To enable faithful cross-generator evaluation, we further introduce MMDF, a new multimodal deepfake dataset spanning diverse manipulation types and rapidly evolving synthesis paradigms, including GANs, diffusion, and flow-matching. Extensive experiments demonstrate that X-AVDT achieves leading performance on MMDF and generalizes strongly to external benchmarks and unseen generators, outperforming existing methods with accuracy improved by 13.1%. Our findings highlight the importance of leveraging internal audio-visual consistency cues for robustness to future generators in deepfake detection. --- ### STRIDE: Structured Lagrangian and Stochastic Residual Dynamics via Flow Matching Authors: Prakrut Kotecha, Ganga Nair B, Shishir Kolathaya Published: 2026-03-09 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2603.08478v2 Robotic systems operating in unstructured environments must operate under significant uncertainty arising from intermittent contacts, frictional variability, and unmodeled compliance. While recent model-free approaches have demonstrated impressive performance, many deployment settings still require predictive models that support planning, constraint handling, and online adaptation. Analytical rigid-body models provide strong physical structure but often fail to capture complex interaction effects, whereas purely data-driven models may violate physical consistency, exhibit data bias, and accumulate long-horizon drift. In this work, we propose STRIDE, a dynamics learning framework that explicitly separates conservative rigid-body mechanics from uncertain, effectively stochastic non-conservative interaction effects. The structured component is modeled using a Lagrangian Neural Network (LNN) to preserve energy-consistent inertial dynamics, while residual interaction forces are represented using Conditional Flow Matching (CFM) to capture multi-modal interaction phenomena. The two components are trained jointly end-to-end, enabling the model to retain physical structure while representing complex stochastic behavior. We evaluate STRIDE on systems of increasing complexity, including a pendulum, the Unitree Go1 quadruped, and the Unitree G1 humanoid. Results show 20% reduction in long-horizon prediction error and 30% reduction in contact force prediction error compared to deterministic residual baselines, supporting more reliable model-based control in uncertain robotic environments. --- ### R2F: Repurposing Ray Frontiers for LLM-free Object Navigation Authors: Francesco Argenziano, John Mark Alexis Marcelo, Michele Brienza, Abdel Hakim Drid, Emanuele Musumeci, Daniele Nardi, Domenico D. Bloisi, Vincenzo Suriani Published: 2026-03-09 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2603.08475v1 Zero-shot open-vocabulary object navigation has progressed rapidly with the emergence of large Vision-Language Models (VLMs) and Large Language Models (LLMs), now widely used as high-level decision-makers instead of end-to-end policies. Although effective, such systems often rely on iterative large-model queries at inference time, introducing latency and computational overhead that limit real-time deployment. To address this problem, we repurpose ray frontiers (R2F), a recently proposed frontier-based exploration paradigm, to develop an LLM-free framework for indoor open-vocabulary object navigation. While ray frontiers were originally used to bias exploration using semantic cues carried along rays, we reinterpret frontier regions as explicit, direction-conditioned semantic hypotheses that serve as navigation goals. Language-aligned features accumulated along out-of-range rays are stored sparsely at frontiers, where each region maintains multiple directional embeddings encoding plausible unseen content. In this way, navigation then reduces to embedding-based frontier scoring and goal tracking within a classical mapping and planning pipeline, eliminating iterative large-model reasoning. We further introduce R2F-VLN, a lightweight extension for free-form language instructions using syntactic parsing and relational verification without additional VLM or LLM components. Experiments in Habitat-sim and on a real robotic platform demonstrate competitive state-of-the-art zero-shot performance with real-time execution, achieving up to 6 times faster runtime than VLM-based alternatives. --- ### Integrating Lagrangian Neural Networks into the Dyna Framework for Reinforcement Learning Authors: Shreya Das, Kundan Kumar, Muhammad Iqbal, Outi Savolainen, Dominik Baumann, Laura Ruotsalainen, Simo Särkkä Published: 2026-03-09 Categories: eess.SY, cs.LG arXiv: https://arxiv.org/abs/2603.08468v1 Model-based reinforcement learning (MBRL) is sample-efficient but depends on the accuracy of the learned dynamics, which are often modeled using black-box methods that do not adhere to physical laws. Those methods tend to produce inaccurate predictions when presented with data that differ from the original training set. In this work, we employ Lagrangian neural networks (LNNs), which enforce an underlying Lagrangian structure to train the model within a Dyna-based MBRL framework. Furthermore, we train the LNN using stochastic gradient-based and state-estimation-based optimizers to learn the network's weights. The state-estimation-based method converges faster than the stochastic gradient-based method during neural network training. Simulation results are provided to illustrate the effectiveness of the proposed LNN-based Dyna framework for MBRL. --- ### MUSA-PINN: Multi-scale Weak-form Physics-Informed Neural Networks for Fluid Flow in Complex Geometries Authors: Weizheng Zhang, Xunjie Xie, Hao Pan, Xiaowei Duan, Bingteng Sun, Qiang Du, Lin Lu Published: 2026-03-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.08465v3 While Physics-Informed Neural Networks (PINNs) offer a mesh-free approach to solving fluid-flow PDEs, standard point-wise residual minimization suffers from convergence pathologies in topologically complex domains like Triply Periodic Minimal Surfaces (TPMS). The locality bias of point-wise constraints fails to propagate global information through tortuous channels, causing unstable gradients and conservation violations. To address this, we propose the Multi-scale Weak-form PINN (MUSA-PINN), which reformulates Navier-Stokes equation constraints as integral conservation laws over hierarchical spherical control volumes. We enforce continuity and momentum conservation via flux-balance residuals on control surfaces. Our method utilizes a three-scale subdomain strategy-comprising large volumes for long-range coupling, skeleton-aware meso-scale volumes aligned with transport pathways, and small volumes for local refinement-alongside a two-stage training schedule prioritizing continuity. Experiments on steady incompressible flow in TPMS geometries show MUSA-PINN outperforms state-of-the-art baselines, reducing relative errors by up to 93% and preserving mass conservation. --- ### Evolving Symbiosis, from Barricelli's Legacy to Collective Intelligence: a simulated and conceptual approach Authors: James Ashford, Marko Cvjetko, Richard Löffler, Berfin Sakallioglu, Alessandro Valerio, Marta Tataryn, Benedikt Hartl, Léo Pio-Lopez, Stefano Nichele Published: 2026-03-09 Categories: cs.NE arXiv: https://arxiv.org/abs/2603.08463v1 This report documents the work of our group (named SymBa) at the ALICE 2026 workshop in Copenhagen. Inspired by the pioneering work by Nils Aall Barricelli on symbiogenesis of numerical organisms (i.e., 1D cellular automata) in 1953 (70+ years ago!!), we discussed the role of symbiogenesis as mechanism contributing to the origins of life, open-endedness, and collective intelligence. We report replications of Barricelli's original work in 1D worlds, an extension to 2D symbioorganisms, and preliminary experimentation with DNA-norms. We discuss the implications of symbiogenesis for artifical life and artificial intelligence, and outline several opportunities for future works, both at the conceptual level as well as using different substrates (neural networks, neural cellular automata, etc.) --- ### Reasoning as Compression: Unifying Budget Forcing via the Conditional Information Bottleneck Authors: Fabio Valerio Massoli, Andrey Kuzmin, Arash Behboodi Published: 2026-03-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.08462v2 \ac{CoT} prompting improves LLM accuracy on complex tasks but often increases token usage and inference cost. Existing ``Budget Forcing'' methods reduce cost via fine-tuning with heuristic length penalties, suppressing both essential reasoning and redundant filler. We recast efficient reasoning as a lossy compression problem under the \ac{IB} principle, and identify a key theoretical gap when applying naive \ac{IB} to transformers: attention violates the Markov property between prompt, reasoning trace, and response. To resolve this issue, we model \ac{CoT} generation under the \ac{CIB} principle, where the reasoning trace $Z$ acts as a computational bridge that contains only the information about the response $Y$ that is not directly accessible from the prompt $X$. This yields a general Reinforcement Learning objective: maximize task reward while compressing completions under a prior over reasoning traces, subsuming common heuristics (e.g., length penalties) as special cases (e.g., uniform priors). In contrast to naive token-counting approaches, we introduce a semantic prior that measures token cost by surprisal under a language model. Crucially, the prior is queried only for token-level log-probabilities, adding negligible overhead to the training loop. Empirically, our \ac{CIB} objective prunes reasoning redundancy while preserving fluency and logic, improving accuracy at moderate compression and enabling aggressive compression with minimal accuracy drop. These gains generalize across model families and task domains, confirming \ac{CIB} as a domain-agnostic CoT compression framework. --- ### Data-Driven Priors for Uncertainty-Aware Deterioration Risk Prediction with Multimodal Data Authors: L. Julián Lechuga López, Tim G. J. Rudner, Farah E. Shamout Published: 2026-03-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.08459v1 Safe predictions are a crucial requirement for integrating predictive models into clinical decision support systems. One approach for ensuring trustworthiness is to enable models' ability to express their uncertainty about individual predictions. However, current machine learning models frequently lack reliable uncertainty estimation, hindering real-world deployment. This is further observed in multimodal settings, where the goal is to enable effective information fusion. In this work, we propose $\texttt{MedCertAIn}$, a predictive uncertainty framework that leverages multimodal clinical data for in-hospital risk prediction to improve model performance and reliability. We design data-driven priors over neural network parameters using a hybrid strategy that considers cross-modal similarity in self-supervised latent representations and modality-specific data corruptions. We train and evaluate the models with such priors using clinical time-series and chest X-ray images from the publicly-available datasets MIMIC-IV and MIMIC-CXR. Our results show that $\texttt{MedCertAIn}$ significantly improves predictive performance and uncertainty quantification compared to state-of-the-art deterministic baselines and alternative Bayesian methods. These findings highlight the promise of data-driven priors in advancing robust, uncertainty-aware AI tools for high-stakes clinical applications. --- ### Adaptive Entropy-Driven Sensor Selection in a Camera-LiDAR Particle Filter for Single-Vessel Tracking Authors: Andrei Starodubov, Yaqub Aris Prabowo, Andreas Hadjipieris, Ioannis Kyriakides, Roberto Galeazzi Published: 2026-03-09 Categories: cs.RO, cs.LG, eess.SP, eess.SY, physics.data-an arXiv: https://arxiv.org/abs/2603.08457v2 Robust single-vessel tracking from fixed coastal platforms is hindered by modality-specific degradations: cameras suffer from illumination and visual clutter, while LiDAR performance drops with range and intermittent returns. We present a particle-filter tracker that supports sequential measurement-level camera-LiDAR fusion and an information-gain (entropy-reduction) adaptive sensing policy that selects the most informative sensing modality at each fusion time bin. The approach is validated in a real maritime deployment at the Cyprus Marine and Maritime Institute Smart Marina Testbed (Ayia Napa Marina, Cyprus), using a shore-mounted 3D LiDAR and an elevated fixed camera to track a rigid inflatable boat with onboard GNSS ground truth. We compare LiDAR-only, camera-only, All sensors, and adaptive configurations. Results show LiDAR dominates near-field accuracy, the camera sustains longer-range coverage when LiDAR becomes unavailable, and the adaptive policy achieves a favorable accuracy-continuity trade-off by switching modalities based on information gain. The adaptive configuration therefore provides a practical sensor-selection baseline for resilient and resource-aware maritime surveillance. --- ### The Boiling Frog Threshold: Criticality and Blindness in World Model-Based Anomaly Detection Under Gradual Drift Authors: Zhe Hong Published: 2026-03-09 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.08455v1 When an RL agent's observations are gradually corrupted, at what drift rate does it "wake up" -- and what determines this boundary? We study world model-based self-monitoring under continuous observation drift across four MuJoCo environments, three detector families (z-score, variance, percentile), and three model capacities. We find that (1) a sharp detection threshold $\varepsilon^*$ exists universally: below it, drift is absorbed as normal variation; above it, detection occurs rapidly. The threshold's existence and sigmoid shape are invariant across all detector families and model capacities, though its position depends on the interaction between detector sensitivity, noise floor structure, and environment dynamics. (2) Sinusoidal drift is completely undetectable by all detector families -- including variance and percentile detectors with no temporal smoothing -- establishing this as a world model property rather than a detector artifact. (3) Within each environment, $\varepsilon^*$ follows a power law in detector parameters ($R^2 = 0.89$-$0.97$), but cross-environment prediction fails ($R^2 = 0.45$), revealing that the missing variable is environment-specific dynamics structure $\partial \mathrm{PE}/\partial\varepsilon$. (4) In fragile environments, agents collapse before any detector can fire ("collapse before awareness"), creating a fundamentally unmonitorable failure mode. Our results reframe $\varepsilon^*$ from an emergent world model property to a three-way interaction between noise floor, detector, and environment dynamics, providing a more defensible and empirically grounded account of self-monitoring boundaries in RL agents. --- ### LycheeCluster: Efficient Long-Context Inference with Structure-Aware Chunking and Hierarchical KV Indexing Authors: Dongfang Li, Zixuan Liu, Gang Lin, Baotian Hu, Min Zhang Published: 2026-03-09 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.08453v1 The quadratic complexity of the attention mechanism and the substantial memory footprint of the Key-Value (KV) cache present severe computational and memory challenges for Large Language Models (LLMs) processing long contexts. Existing retrieval-based methods often compromise semantic integrity through fixed-size chunking and suffer from inefficient linear scanning. In this paper, we propose LycheeCluster, a novel method for efficient KV cache management. LycheeCluster preserves local semantic coherence via boundary-aware chunking and constructs a recursive hierarchical index rooted in the triangle inequality. This design transforms cache retrieval from a linear scan into a theoretically bounded, logarithmic-time pruning process, while a lazy update strategy supports efficient streaming generation. Experiments demonstrate that LycheeCluster achieves up to a 3.6x end-to-end inference speedup with negligible degradation in model performance, outperforming state-of-the-art KV cache management methods (e.g., Quest, ClusterKV). We will release our code and kernels after publication. --- ### A Dataset for Probing Translationese Preferences in English-to-Swedish Translation Authors: Jenny Kunz, Anja Jarochenko, Marcel Bollmann Published: 2026-03-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.08450v1 Translations often carry traces of the source language, a phenomenon known as translationese. We introduce the first freely available English-to-Swedish dataset contrasting translationese sentences with idiomatic alternatives, designed to probe intrinsic preferences of language models. It includes error tags and descriptions of the problems in the original translations. In experiments evaluating smaller Swedish and multilingual LLMs with our dataset, we find that they often favor the translationese phrasing. Human alternatives are chosen more often when the English source sentence is omitted, indicating that exposure to the source biases models toward literal translations, although even without context models often prefer the translationese variant. Our dataset and findings provide a resource and benchmark for developing models that produce more natural, idiomatic output in non-English languages. --- ### A prospective clinical feasibility study of a conversational diagnostic AI in an ambulatory primary care clinic Authors: Peter Brodeur, Jacob M. Koshy, Anil Palepu, Khaled Saab, Ava Homiar, Roma Ruparel, Charles Wu, Ryutaro Tanno, Joseph Xu, Amy Wang, David Stutz, Wei-Hung Weng et al. Published: 2026-03-09 Categories: cs.HC, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.08448v3 Large language model (LLM)-based AI systems have shown promise for patient-facing diagnostic and management conversations in simulated settings. Translating these systems into clinical practice requires assessment in real-world workflows with rigorous safety oversight. We report a prospective, single-arm feasibility study of an LLM-based conversational AI, the Articulate Medical Intelligence Explorer (AMIE), conducting clinical history taking and presentation of potential diagnoses for patients to discuss with their provider at urgent care appointments at a leading academic medical center. 100 adult patients completed an AMIE text-chat interaction up to 5 days before their appointment. We sought to assess the conversational safety and quality, patient and clinician experience, and clinical reasoning capabilities compared to primary care providers (PCPs). Human safety supervisors monitored all patient-AMIE interactions in real time and did not need to intervene to stop any consultations based on pre-defined criteria. Patients reported high satisfaction and their attitudes towards AI improved after interacting with AMIE (p < 0.001). PCPs found AMIE's output useful with a positive impact on preparedness. AMIE's differential diagnosis (DDx) included the final diagnosis, per chart review 8 weeks post-encounter, in 90% of cases, with 75% top-3 accuracy. Blinded assessment of AMIE and PCP DDx and management (Mx) plans suggested similar overall DDx and Mx plan quality, without significant differences for DDx (p = 0.6) and appropriateness and safety of Mx (p = 0.1 and 1.0, respectively). PCPs outperformed AMIE in the practicality (p = 0.003) and cost effectiveness (p = 0.004) of Mx. While further research is needed, this study demonstrates the initial feasibility, safety, and user acceptance of conversational AI in a real-world setting, representing crucial steps towards clinical translation. --- ### Efficient Policy Learning with Hybrid Evaluation-Based Genetic Programming for Uncertain Agile Earth Observation Satellite Scheduling Authors: Junhua Xue, Yuning Chen, Mingyan Shao, Yangming Zhou, Qinghua Wu, Yingwu Chen Published: 2026-03-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.08447v2 The Uncertain Agile Earth Observation Satellite Scheduling Problem (UAEOSSP) is a novel combinatorial optimization problem and a practical engineering challenge that aligns with the current demands of space technology development. It incorporates uncertainties in profit, resource consumption, and visibility, which may render pre-planned schedules suboptimal or even infeasible. Genetic Programming Hyper-Heuristic (GPHH) shows promise for evolving interpretable scheduling policies; however, their simulation-based evaluation incurs high computational costs. Moreover, the design of the constructive method, denoted as Online Scheduling Algorithm (OSA), directly affects fitness assessment, resulting in evaluation-dependent local optima within the policy space. To address these issues, this paper proposes a Hybrid Evaluation-based Genetic Programming (HE-GP) for effectively solving UAEOSSP. A Hybrid Evaluation (HE) mechanism is integrated into the policy-driven OSA, combining exact and approximate filtering modes: exact mode ensures evaluation accuracy through elaborately designed constraint verification modules, while approximate mode reduces computational overhead via simplified logic. HE-GP dynamically switches between evaluation models based on real-time evolutionary state information. Experiments on 16 simulated instance sets demonstrate that HE-GP significantly outperforms handcrafted heuristics and single-evaluation based GPHH, achieving substantial reductions in computational cost while maintaining excellent scheduling performance across diverse scenarios. Specifically, the average training time of HE-GP was reduced by 17.77\% compared to GP employing exclusively exact evaluation, while the optimal policy generated by HE-GP achieved the highest average ranks across all scenarios. --- ### Alfa: Attentive Low-Rank Filter Adaptation for Structure-Aware Cross-Domain Personalized Gaze Estimation Authors: He-Yen Hsieh, Wei-Te Mark Ting, H. T. Kung Published: 2026-03-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.08445v1 Pre-trained gaze models learn to identify useful patterns commonly found across users, but subtle user-specific variations (i.e., eyelid shape or facial structure) can degrade model performance. Test-time personalization (TTP) adapts pre-trained models to these user-specific domain shifts using only a few unlabeled samples. Efficient fine-tuning is critical in performing this domain adaptation: data and computation resources can be limited-especially for on-device customization. While popular parameter-efficient fine-tuning (PEFT) methods address adaptation costs by updating only a small set of weights, they may not be taking full advantage of structures encoded in pre-trained filters. To more effectively leverage existing structures learned during pre-training, we reframe personalization as a process to reweight existing features rather than learning entirely new ones. We present Attentive Low-Rank Filter Adaptation (Alfa) to adapt gaze models by reweighting semantic patterns in pre-trained filters. With Alfa, singular value decomposition (SVD) extracts dominant spatial components that capture eye and facial characteristics across users. Via an attention mechanism, we need only a few unlabeled samples to adjust and reweight pre-trained structures, selectively amplifying those relevant to a target user. Alfa achieves the lowest average gaze errors across four cross-dataset gaze benchmarks, outperforming existing TTP methods and low-rank adaptation (LoRA)-based variants. We also show that Alfa's attentive low-rank methods can be applied to applications beyond vision, such as diffusion-based language models. --- ### Can Vision-Language Models Solve the Shell Game? Authors: Tiedong Liu, Wee Sun Lee Published: 2026-03-09 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2603.08436v1 Visual entity tracking is an innate cognitive ability in humans, yet it remains a critical bottleneck for Vision-Language Models (VLMs). This deficit is often obscured in existing video benchmarks by visual shortcuts. We introduce VET-Bench, a synthetic diagnostic testbed featuring visually identical objects that necessitate tracking exclusively through spatiotemporal continuity. Our experiments reveal that current state-of-the-art VLMs perform at or near chance level on VET-Bench, exposing a fundamental limitation: an over-reliance on static frame-level features and a failure to maintain entity representations over time. We provide a theoretical analysis drawing connections to the state-tracking problem, proving that fixed-depth transformer-based VLMs are fundamentally limited in tracking indistinguishable objects without intermediate supervision due to expressivity constraints. To address this, we propose Spatiotemporal Grounded Chain-of-Thought (SGCoT): generating object trajectories as explicit intermediate states. Leveraging Molmo2's object tracking ability, we elicit SGCoT reasoning by fine-tuning on synthesized text-only data for alignment. Our method achieves state-of-the-art accuracy exceeding 90% on VET-Bench, demonstrating that VLMs can reliably solve the video shell-game task end-to-end without external tools. Our code and data are available at https://vetbench.github.io . --- ### Information Maximization for Long-Tailed Semi-Supervised Domain Generalization Authors: Leo Fillioux, Omprakash Chakraborty, Quentin Gopée, Pierre Marza, Paul-Henry Cournède, Stergios Christodoulidis, Maria Vakalopoulou, Ismail Ben Ayed, Jose Dolz Published: 2026-03-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.08434v1 Semi-supervised domain generalization (SSDG) has recently emerged as an appealing alternative to tackle domain generalization when labeled data is scarce but unlabeled samples across domains are abundant. In this work, we identify an important limitation that hampers the deployment of state-of-the-art methods on more challenging but practical scenarios. In particular, state-of-the-art SSDG severely suffers in the presence of long-tailed class distributions, an arguably common situation in real-world settings. To alleviate this limitation, we propose IMaX, a simple yet effective objective based on the well-known InfoMax principle adapted to the SSDG scenario, where the Mutual Information (MI) between the learned features and latent labels is maximized, constrained by the supervision from the labeled samples. Our formulation integrates an α-entropic objective, which mitigates the class-balance bias encoded in the standard marginal entropy term of the MI, thereby better handling arbitrary class distributions. IMaX can be seamlessly plugged into recent state-of-the-art SSDG, consistently enhancing their performance, as demonstrated empirically across two different image modalities. --- ### One Model Is Enough: Native Retrieval Embeddings from LLM Agent Hidden States Authors: Bo Jiang Published: 2026-03-09 Categories: cs.CL, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2603.08429v1 LLM agents that retrieve external knowledge typically generate a search query as text, then run a separate embedding model to encode it into a vector. This two-model pipeline adds infrastructure complexity and latency, yet is redundant: the LLM already encodes the full conversational context in its hidden states. We propose equipping LLM agents with native retrieval capability by adding a lightweight projection head that maps hidden states directly into the embedding space, eliminating the need for a separate embedding model. Trained with a combination of alignment, contrastive, and rank distillation losses, our method retains 97\% of baseline retrieval quality while enabling the LLM agent to search with its own representations. Experiments on the QReCC conversational search benchmark show competitive Recall@10 and MRR@10 compared to the standard generate-then-encode pipeline, with systematic ablations confirming the contribution of each loss component. --- ### Grow, Assess, Compress: Adaptive Backbone Scaling for Memory-Efficient Class Incremental Learning Authors: Adrian Garcia-Castañeda, Jon Irureta, Jon Imaz, Aizea Lojo Published: 2026-03-09 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2603.08426v2 Class Incremental Learning (CIL) poses a fundamental challenge: maintaining a balance between the plasticity required to learn new tasks and the stability needed to prevent catastrophic forgetting. While expansion-based methods effectively mitigate forgetting by adding task-specific parameters, they suffer from uncontrolled architectural growth and memory overhead. In this paper, we propose a novel dynamic scaling framework that adaptively manages model capacity through a cyclic "GRow, Assess, ComprEss" (GRACE) strategy. Crucially, we supplement backbone expansion with a novel saturation assessment phase that evaluates the utilization of the model's capacity. This assessment allows the framework to make informed decisions to either expand the architecture or compress the backbones into a streamlined representation, preventing parameter explosion. Experimental results demonstrate that our approach achieves state-of-the-art performance across multiple CIL benchmarks, while reducing memory footprint by up to a 73% compared to purely expansionist models. --- ### IronEngine: Towards General AI Assistant Authors: Xi Mo Published: 2026-03-09 Categories: cs.AI, cs.HC, cs.LG, cs.MA, eess.SY arXiv: https://arxiv.org/abs/2603.08425v1 This paper presents IronEngine, a general AI assistant platform organized around a unified orchestration core that connects a desktop user interface, REST and WebSocket APIs, Python clients, local and cloud model backends, persistent memory, task scheduling, reusable skills, 24-category tool execution, MCP-compatible extensibility, and hardware-facing integration. IronEngine introduces a three-phase pipeline -- Discussion (Planner--Reviewer collaboration), Model Switch (VRAM-aware transition), and Execution (tool-augmented action loop) -- that separates planning quality from execution capability. The system features a hierarchical memory architecture with multi-level consolidation, a vectorized skill repository backed by ChromaDB, an adaptive model management layer supporting 92 model profiles with VRAM-aware context budgeting, and an intelligent tool routing system with 130+ alias normalization and automatic error correction. We present experimental results on file operation benchmarks achieving 100\% task completion with a mean total time of 1541 seconds across four heterogeneous tasks, and provide detailed comparisons with representative AI assistant systems including ChatGPT, Claude Desktop, Cursor, Windsurf, and open-source agent frameworks. Without disclosing proprietary prompts or core algorithms, this paper analyzes the platform's architectural decomposition, subsystem design, experimental performance, safety boundaries, and comparative engineering advantages. The resulting study positions IronEngine as a system-oriented foundation for general-purpose personal assistants, automation frameworks, and future human-centered agent platforms. --- ### SYNAPSE: Framework for Neuron Analysis and Perturbation in Sequence Encoding Authors: Jesús Sánchez Ochoa, Enrique Tomás Martínez Beltrán, Alberto Huertas Celdrán Published: 2026-03-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.08424v1 In recent years, Artificial Intelligence has become a powerful partner for complex tasks such as data analysis, prediction, and problem-solving, yet its lack of transparency raises concerns about its reliability. In sensitive domains such as healthcare or cybersecurity, ensuring transparency, trustworthiness, and robustness is essential, since the consequences of wrong decisions or successful attacks can be severe. Prior neuron-level interpretability approaches are primarily descriptive, task-dependent, or require retraining, which limits their use as systematic, reusable tools for evaluating internal robustness across architectures and domains. To overcome these limitations, this work proposes SYNAPSE, a systematic, training-free framework for understanding and stress-testing the internal behavior of Transformer models across domains. It extracts per-layer (CLS) representations, trains a lightweight linear probe to obtain global and per-class neuron rankings, and applies forward-hook interventions during inference. This design enables controlled experiments on internal representations without altering the original model, thereby allowing weaknesses, stability patterns, and label-specific sensitivities to be measured and compared directly across tasks and architectures. Across all experiments, SYNAPSE reveals a consistent, domain-independent organization of internal representations, in which task-relevant information is encoded in broad, overlapping neuron subsets. This redundancy provides a strong degree of functional stability, while class-wise asymmetries expose heterogeneous specialization patterns and enable label-aware analysis. In contrast, small structured manipulations in weight or logit space are sufficient to redirect predictions, highlighting complementary vulnerability profiles and illustrating how SYNAPSE can guide the development of more robust Transformer models. --- ### Human-Aware Robot Behaviour in Self-Driving Labs Authors: Satheeshkumar Veeramani, Anna Kisil, Abigail Bentley, Hatem Fakhruldeen, Gabriella Pizzuto, Andrew I. Cooper Published: 2026-03-09 Categories: cs.RO, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2603.08420v2 Self-driving laboratories (SDLs) are rapidly transforming research in chemistry and materials science to accelerate new discoveries. Mobile robot chemists (MRCs) play a pivotal role by autonomously navigating the lab to transport samples, effectively connecting synthesis, analysis, and characterisation equipment. The instruments within an SDL are typically designed or retrofitted to be accessed by both human and robotic chemists, ensuring operational flexibility and integration between manual and automated workflows. In many scenarios, human and robotic chemists may need to use the same equipment simultaneously. Currently, MRCs rely on simple LiDAR-based obstruction detection, which forces the robot to passively wait if a human is present. This lack of situational awareness leads to unnecessary delays and inefficient coordination in time-critical automated workflows in human-robot shared labs. To address this, we present an initial study of an embodied, AI-driven perception method that facilitates proactive human-robot interaction in shared-access scenarios. Our method features a hierarchical human intention prediction model that allows the robot to distinguish between preparatory actions (waiting) and transient interactions (accessing the instrument). Our results demonstrate that the proposed approach enhances efficiency by enabling proactive human-robot interaction, streamlining coordination, and potentially increasing the efficiency of autonomous scientific labs. --- ### Meta-RL with Shared Representations Enables Fast Adaptation in Energy Systems Authors: Théo Zangato, Aomar Osmani, Pegah Alizadeh Published: 2026-03-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.08418v1 Meta-Reinforcement Learning addresses the critical limitations of conventional Reinforcement Learning in multi-task and non-stationary environments by enabling fast policy adaptation and improved generalization. We introduce a novel Meta-RL framework that integrates a bi-level optimization scheme with a hybrid actor-critic architecture specially designed to enhance sample efficiency and inter-task adaptability. To improve knowledge transfer, we meta-learn a shared state feature extractor jointly optimized across actor and critic networks, providing efficient representation learning and limiting overfitting to individual tasks or dominant profiles. Additionally, we propose a parameter-sharing mechanism between the outer- and inner-loop actor networks, to reduce redundant learning and accelerate adaptation during task revisitation. The approach is validated on a real-world Building Energy Management Systems dataset covering nearly a decade of temporal and structural variability, for which we propose a task preparation method to promote generalization. Experiments demonstrate effective task adaptation and better performance compared to conventional RL and Meta-RL methods. --- ### Geometrically Constrained Outlier Synthesis Authors: Daniil Karzanov, Marcin Detyniecki Published: 2026-03-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.08413v2 Deep neural networks for image classification often exhibit overconfidence on out-of-distribution (OOD) samples. To address this, we introduce Geometrically Constrained Outlier Synthesis (GCOS), a training-time regularization framework aimed at improving OOD robustness during inference. GCOS addresses a limitation of prior synthesis methods by generating virtual outliers in the hidden feature space that respect the learned manifold structure of in-distribution (ID) data. The synthesis proceeds in two stages: (i) a dominant-variance subspace extracted from the training features identifies geometrically informed, off-manifold directions; (ii) a conformally-inspired shell, defined by the empirical quantiles of a nonconformity score from a calibration set, adaptively controls the synthesis magnitude to produce boundary samples. The shell ensures that generated outliers are neither trivially detectable nor indistinguishable from in-distribution data, facilitating smoother learning of robust features. This is combined with a contrastive regularization objective that promotes separability of ID and OOD samples in a chosen score space, such as Mahalanobis or energy-based. Experiments demonstrate that GCOS outperforms state-of-the-art methods using standard energy-based inference on near-OOD benchmarks, defined as tasks where outliers share the same semantic domain as in-distribution data. As an exploratory extension, the framework naturally transitions to conformal OOD inference, which translates uncertainty scores into statistically valid p-values and enables thresholds with formal error guarantees, providing a pathway toward more predictable and reliable OOD detection. --- ### Aligning to Illusions: Choice Blindness in Human and AI Feedback Authors: Wenbin Wu Published: 2026-03-09 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.08412v1 Reinforcement Learning from Human Feedback (RLHF) assumes annotator preferences reflect stable internal states. We challenge this through three experiments spanning the preference pipeline. In a human choice blindness study, 91% of surreptitiously swapped preferences go undetected, extending choice blindness to third-person evaluative comparison of unfamiliar text. Testing fifteen LLM judges as potential replacements, we find detection relies on shallow text matching rather than genuine self-monitoring: removing prior reasoning from context causes blindness to surge from near-zero to over 50%, while explicit social pressure induces near-universal compliance. In a dose-response experiment across two architectures from 86M to 2B parameters, one-sixth to one-third of labels must be corrupted before the reward signal halves, yet standard pairwise accuracy remains virtually unchanged. A Best-of-N evaluation confirms this translates to downstream policy degradation: at 50% corruption, reward-guided selection produces no improvement over random sampling, while the proxy model reports monotonically increasing scores. Together, these results reveal a preference construction problem: the signal entering RLHF is shaped by elicitation context in ways that neither human metacognition, LLM self-monitoring, nor standard evaluation metrics can detect. --- ### Sandpiper: Orchestrated AI-Annotation for Educational Discourse at Scale Authors: Daryl Hedley, Doug Pietrzak, Jorge Dias, Ian Burden, Bakhtawar Ahtisham, Zhuqian Zhou, Kirk Vanacore, Josh Marland, Rachel Slama, Justin Reich, Kenneth Koedinger, René Kizilcec Published: 2026-03-09 Categories: cs.HC, cs.CL arXiv: https://arxiv.org/abs/2603.08406v2 Digital educational environments are expanding toward complex AI and human discourse, providing researchers with an abundance of data that offers deep insights into learning and instructional processes. However, traditional qualitative analysis remains a labor-intensive bottleneck, severely limiting the scale at which this research can be conducted. We present Sandpiper, a mixed-initiative system designed to serve as a bridge between high-volume conversational data and human qualitative expertise. By tightly coupling interactive researcher dashboards with agentic Large Language Model (LLM) engines, the platform enables scalable analysis without sacrificing methodological rigor. Sandpiper addresses critical barriers to AI adoption in education by implementing context-aware, automated de-identification workflows supported by secure, university-housed infrastructure to ensure data privacy. Furthermore, the system employs schema-constrained orchestration to eliminate LLM hallucinations and enforces strict adherence to qualitative codebooks. An integrated evaluations engine allows for the continuous benchmarking of AI performance against human labels, fostering an iterative approach to model refinement and validation. We propose a user study to evaluate the system's efficacy in improving research efficiency, inter-rater reliability, and researcher trust in AI-assisted qualitative workflows. --- ### SPIRAL: Self-Evolving Action-Conditioned Video Generation via Reflective Planning Agents Authors: Yu Yang, Yue Liao, Jianbiao Mei, Baisen Wang, Xuemeng Yang, Licheng Wen, Jiangning Zhang, Xiangtai Li, Liang Lv, Hanlin Chen, Botian Shi, Yong Liu et al. Published: 2026-03-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.08403v3 Long-horizon action-conditioned video generation aims to synthesize temporally coherent videos that follow complex action instructions over extended horizons, requiring procedural ordering, persistent action execution, and scene consistency beyond conventional TI2V's short-term fidelity. Existing single-shot video generation models typically operate in an open-loop manner, leading to incomplete action execution, hallucinated motions, and temporal drift. To address this, we propose SPIRAL, a closed-loop framework that performs sequential planning and iterative reflection for action-conditioned long-horizon video generation. Specifically, SPIRAL instantiates a think-act-reflect process: a PlanAgent decomposes high-level goals into sub-actions, which condition a VideoGenerator to synthesize each segment alongside a memory context, while a CriticAgent evaluates intermediate video segments to provide corrective feedback for iterative refinement. This closed-loop design further supports self-evolution by utilizing PlanAgent-proposed actions and CriticAgent-derived rewards for GRPO-based post-training to enhance the video generator's long-horizon consistency. Moreover, we introduce ActVideoGen-Dataset for task-specific training, and establish ActVideoGen-Bench as a dedicated evaluation suite for measuring action quality and temporal coherence. Experiments across multiple TI2V backbones alongside the self-evolving strategy show consistent gains on ActVideoGen-Bench and VBench, demonstrating the effectiveness of SPIRAL. --- ### A Recipe for Stable Offline Multi-agent Reinforcement Learning Authors: Dongsu Lee, Daehee Lee, Amy Zhang Published: 2026-03-09 Categories: cs.LG, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2603.08399v1 Despite remarkable achievements in single-agent offline reinforcement learning (RL), multi-agent RL (MARL) has struggled to adopt this paradigm, largely persisting with on-policy training and self-play from scratch. One reason for this gap comes from the instability of non-linear value decomposition, leading prior works to avoid complex mixing networks in favor of linear value decomposition (e.g., VDN) with value regularization used in single-agent setups. In this work, we analyze the source of instability in non-linear value decomposition within the offline MARL setting. Our observations confirm that they induce value-scale amplification and unstable optimization. To alleviate this, we propose a simple technique, scale-invariant value normalization (SVN), that stabilizes actor-critic training without altering the Bellman fixed point. Empirically, we examine the interaction among key components of offline MARL (e.g., value decomposition, value learning, and policy extraction) and derive a practical recipe that unlocks its full potential. --- ### Revealing Behavioral Plasticity in Large Language Models: A Token-Conditional Perspective Authors: Liyuan Mao, Le Yu, Jing Zhou, Chujie Zheng, Bowen Yu, Chang Gao, Shixuan Liu, An Yang, Weinan Zhang, JunYang Lin Published: 2026-03-09 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.08398v1 In this work, we reveal that Large Language Models (LLMs) possess intrinsic behavioral plasticity-akin to chameleons adapting their coloration to environmental cues-that can be exposed through token-conditional generation and stabilized via reinforcement learning. Specifically, by conditioning generation on carefully selected token prefixes sampled from responses exhibiting desired behaviors, LLMs seamlessly adapt their behavioral modes at inference time (e.g., switching from step-by-step reasoning to direct answering) without retraining. Based on this insight, we propose Token-Conditioned Reinforcement Learning (ToCoRL), a principled framework that leverages RL to internalize this chameleon-like plasticity, transforming transient inference-time adaptations into stable and learnable behavioral patterns. ToCoRL guides exploration with token-conditional generation and keep enhancing exploitation, enabling emergence of appropriate behaviors. Extensive experiments show that ToCoRL enables precise behavioral control without capability degradation. Notably, we show that large reasoning models, while performing strongly on complex mathematics, can be effectively adapted to excel at factual question answering, which was a capability previously hindered by their step-by-step reasoning patterns. --- ### Decoupling Distance and Networks: Hybrid Graph Attention-Geostatistical Methods for Spatio-temporal Risk Mapping Authors: Toba Temitope Bamidele, Ezra Gayawan, Femi Barnabas Adebola, Olatunji Johnson Published: 2026-03-09 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2603.08393v2 Accurate spatial prediction and rigorous uncertainty quantification are central to modern spatial epidemiology and environmental risk analysis. We introduce a statistically principled hybrid modelling framework that integrates the nonlinear, attention-based representation learning capabilities of a dynamic Graph Attention Network (GATv2) with a latent Gaussian spatial process from model-based geostatistics (MBG). This framework jointly captures relational dependence encoded in graph structures and continuous spatial dependence governed by physical proximity. We evaluate the proposed model via a controlled simulation study and an applied analysis of malaria prevalence data, comparing its predictive accuracy, calibration, and uncertainty quantification against classical geostatistical models and standalone GATv2 architectures. Our analyses show that GATv2 captures complex nonlinear interactions but fails to account for residual spatial autocorrelation, resulting in miscalibrated predictive distributions. Conversely, geostatistical models provide coherent uncertainty quantification through structured covariance functions yet are constrained by linear predictor assumptions and by their reliance on Euclidean distance to encode spatial structure. By integrating attention mechanisms and nonlinear features with an explicit probabilistic spatial random field, the hybrid model captured the relational dependence, consistently improved predictive accuracy, and provided more realistic uncertainty quantification in both simulation and applied settings. Overall, the findings demonstrate that the hybrid model constitutes a statistically coherent and empirically robust framework for modelling complex spatial and spatio-temporal processes in settings where both distance-based and structure-based dependencies operate. --- ### COACH meets QUORUM: A Framework and Pipeline for Aligning User, Expert and Developer Perspectives in LLM-generated Health Counselling Authors: Yee Man Ng, Bram van Dijk, Pieter Beynen, Otto Boekesteijn, Joris Jansen, Gerard van Oortmerssen, Max van Duijn, Marco Spruit Published: 2026-03-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.08392v1 Systems that collect data on sleep, mood, and activities can provide valuable lifestyle counselling to populations affected by chronic disease and its consequences. Such systems are, however, challenging to develop; besides reliably extracting patterns from user-specific data, systems should also contextualise these patterns with validated medical knowledge to ensure the quality of counselling, and generate counselling that is relevant to a real user. We present QUORUM, a new evaluation framework that unifies these developer-, expert-, and user-centric perspectives, and show with a real case study that it meaningfully tracks convergence and divergence in stakeholder perspectives. We also present COACH, a Large Language Model-driven pipeline to generate personalised lifestyle counselling for our Healthy Chronos use case, a diary app for cancer patients and survivors. Applying our framework shows that overall, users, medical experts, and developers converge on the opinion that the generated counselling is relevant, of good quality, and reliable. However, stakeholders also diverge on the tone of the counselling, sensitivity to errors in pattern-extraction, and potential hallucinations. These findings highlight the importance of multi-stakeholder evaluation for consumer health language technologies and illustrate how a unified evaluation framework can support trustworthy, patient-centered NLP systems in real-world settings. --- ### Adaptive Loops and Memory in Transformers: Think Harder or Know More? Authors: Markus Frey, Behzad Shomali, Ali Hamza Bashir, David Berghaus, Joachim Koehler, Mehdi Ali Published: 2026-03-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.08391v3 Chain-of-thought (CoT) prompting enables reasoning in language models but requires explicit verbalization of intermediate steps. Looped transformers offer an alternative by iteratively refining representations within hidden states. This parameter efficiency comes at a cost, as looped models lack the storage capacity of deeper models which use unique weights per layer. In this work, we investigate transformer models that feature both adaptive per-layer looping, where each transformer block learns to iterate its hidden state via a learned halting mechanism, and gated memory banks, that provide additional learned storage. We find that looping primarily benefits mathematical reasoning, while memory banks help recover performance on commonsense tasks compared to parameter and FLOP matched models. Combining both mechanisms yields a model that outperforms an iso-FLOP baseline, with three times the number of layers, across math benchmarks. Analysis of model internals reveals layer specialization: early layers learn to loop minimally and access memory sparingly, while later layers do both more heavily. --- ### DuetHOI: Language-Guided Bimanual Hand--Object Motion Generation with Articulation Planning and Contact Refinement Authors: Zhi Wang, Yuyan Liu, Liu liu, Ruonan Liu, Ruixuan Liu Published: 2026-03-09 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2603.08390v3 Bimanual articulated-object interaction generation requires a model to capture the evolution of object articulation, coordination between the two hands, and fine-grained hand--object contact. Existing methods typically encode object and hand motion as a unified high-dimensional sequence, making it difficult to explicitly accommodate the different scales of manipulation progress, relative bimanual motion, and local hand pose. We propose \textbf{DuetHOI}, a structured framework for bimanual articulated-object interaction generation. DuetHOI first uses ContactVAE to predict contact intent on the object surface from language and object geometry. Conditioned on this spatial intent, ArtPlanner provides a trajectory-level articulation reference, and DualFormer generates the global interaction using object states, object-centered hand positions, and compact hand-pose tokens learned by ManiVAE. After global generation, ProxiRefine fixes the object trajectory and residually corrects the two hands using current hand--object proximity, improving local surface alignment. Experiments across articulated and rigid objects and single- and bimanual settings show that DuetHOI outperforms three adapted baselines on most contact and hand--object consistency metrics, with particularly strong results in bimanual articulated interaction generation. ---