# Research Papers — 2026-03 · bundle page 126 of 243 > Full-text markdown of papers #6251–6300 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/126 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/125.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/127.md) ### TopoVST: Toward Topology-fidelitous Vessel Skeleton Tracking Authors: Yaoyu Liu, Minghui Zhang, Junjun He, Yun Gu Published: 2026-03-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14909v1 Automatic extraction of vessel skeletons is crucial for many clinical applications. However, achieving topologically faithful delineation of thin vessel skeletons remains highly challenging, primarily due to frequent discontinuities and the presence of spurious skeleton segments. To address these difficulties, we propose TopoVST, a topology-fidelitious vessel skeleton tracker. TopoVST constructs multi-scale sphere graphs to sample the input image and employs graph neural networks to jointly estimate tracking directions and vessel radii. The utilization of multi-scale representations is enhanced through a gating-based feature fusion mechanism, while the issue of class imbalance during training is mitigated by embedding a geometry-aware weighting scheme into the directional loss. In addition, we design a wave-propagation-based skeleton tracking algorithm that explicitly mitigates the generation of spurious skeletons through space-occupancy filtering. We evaluate TopoVST on two vessel datasets with different geometries. Extensive comparisons with state-of-the-art baselines demonstrate that TopoVST achieves competitive performance in both overlapping and topological metrics. Our source code is available at: https://github.com/EndoluminalSurgicalVision-IMR/TopoVST. --- ### PerlAD: Towards Enhanced Closed-loop End-to-end Autonomous Driving with Pseudo-simulation-based Reinforcement Learning Authors: Yinfeng Gao, Qichao Zhang, Deqing Liu, Zhongpu Xia, Guang Li, Kun Ma, Guang Chen, Hangjun Ye, Long Chen, Da-Wei Ding, Dongbin Zhao Published: 2026-03-16 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2603.14908v1 End-to-end autonomous driving policies based on Imitation Learning (IL) often struggle in closed-loop execution due to the misalignment between inadequate open-loop training objectives and real driving requirements. While Reinforcement Learning (RL) offers a solution by directly optimizing driving goals via reward signals, the rendering-based training environments introduce the rendering gap and are inefficient due to high computational costs. To overcome these challenges, we present a novel Pseudo-simulation-based RL method for closed-loop end-to-end autonomous driving, PerlAD. Based on offline datasets, PerlAD constructs a pseudo-simulation that operates in vector space, enabling efficient, rendering-free trial-and-error training. To bridge the gap between static datasets and dynamic closed-loop environments, PerlAD introduces a prediction world model that generates reactive agent trajectories conditioned on the ego vehicle's plan. Furthermore, to facilitate efficient planning, PerlAD utilizes a hierarchical decoupled planner that combines IL for lateral path generation and RL for longitudinal speed optimization. Comprehensive experimental results demonstrate that PerlAD achieves state-of-the-art performance on the Bench2Drive benchmark, surpassing the previous E2E RL method by 10.29% in Driving Score without requiring expensive online interactions. Additional evaluations on the DOS benchmark further confirm its reliability in handling safety-critical occlusion scenarios. --- ### Machine learning for sustainable geoenergy: uncertainty, physics and decision-ready inference Authors: Hannah P. Menke, Ahmed H. Elsheikh, Lingli Wei, Nanzhe Wang, Andreas Busch Published: 2026-03-16 Categories: cond-mat.dis-nn, cs.LG arXiv: https://arxiv.org/abs/2603.14907v1 Geoenergy projects (CO2 storage, geothermal, subsurface H2 generation/storage, critical minerals from subsurface fluids, or nuclear waste disposal) increasingly follow a petroleum-style funnel from screening and appraisal to operations, monitoring, and stewardship. Across this funnel, limited and heterogeneous observations must be turned into risk-bounded operational choices under strong physical and geological constraints - choices that control deployment rate, cost of capital, and the credibility of climate-mitigation claims. These choices are inherently multi-objective, balancing performance against containment, pressure footprint, induced seismicity, energy/water intensity, and long-term stewardship. We argue that progress is limited by four recurring bottlenecks: (i) scarce, biased labels and few field performance outcomes; (ii) uncertainty treated as an afterthought rather than the deliverable; (iii) weak scale-bridging from pore to basin (including coupled chemical-flow-geomechanics); and (iv) insufficient quality assurance (QA), auditability, and governance for regulator-facing deployment. We outline machine learning (ML) approaches that match these realities (hybrid physics-ML, probabilistic uncertainty quantification (UQ), structure-aware representations, and multi-fidelity/continual learning) and connect them to four anchor applications: imaging-to-process digital twins, multiphase flow and near-well conformance, monitoring and inverse problems (monitoring, measurement, and verification (MMV), including deformation and microseismicity), and basin-scale portfolio management. We close with a pragmatic agenda for benchmarks, validation, reporting standards, and policy support needed for reproducible and defensible ML in sustainable geoenergy. --- ### ExPosST: Explicit Positioning with Adaptive Masking for LLM-Based Simultaneous Machine Translation Authors: Yuzhe Shang, Pengzhi Gao, Yazheng Yang, Jiayao Ma, Wei Liu, Jian Luan, Jinsong Su Published: 2026-03-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.14903v2 Large language models (LLMs) have recently demonstrated promising performance in simultaneous machine translation (SimulMT). However, applying decoder-only LLMs to SimulMT introduces a positional mismatch, which leads to a dilemma between decoding efficiency and positional consistency. Existing approaches often rely on specific positional encodings or carefully designed prompting schemes, and thus fail to simultaneously achieve inference efficiency, positional consistency, and broad model compatibility. In this work, we propose ExPosST, a general framework that resolves this dilemma through explicit position allocation. ExPosST reserves fixed positional slots for incoming source tokens, enabling efficient decoding with KV cache across different positional encoding methods. To further bridge the gap between fine-tuning and inference, we introduce a policy-consistent fine-tuning strategy that aligns training with inference-time decoding behavior. Experiments across multiple language pairs demonstrate that ExPosST effectively supports simultaneous translation under diverse policies. --- ### The impact of machine learning forecasting on strategic decision-making for Bike Sharing Systems Authors: Enrico Angelelli, Andrea Mor, Carlotta Orsenigo, M. Grazia Speranza, Carlo Vercellis Published: 2026-03-16 Categories: math.OC, cs.LG arXiv: https://arxiv.org/abs/2603.14901v1 In this paper, machine learning techniques are used to forecast the difference between bike returns and withdrawals at each station of a bike sharing system. The forecasts are integrated into a simulation framework that is used to support long-term decisions and model the daily dynamics, including the relocation of bikes. We assess the quality of the machine learning-based forecasts in two ways. Firstly, we compare the forecasts with alternative prediction methods. Secondly, we analyze the impact of the forecasts on the quality of the output of the simulation framework. The evaluation is based on real-world data of the bike sharing system currently operating in Brescia, Italy. --- ### Photonic Quantum-Enhanced Knowledge Distillation Authors: Kuan-Cheng Chen, Shang Yu, Chen-Yu Liu, Samuel Yen-Chi Chen, Huan-Hsin Tseng, Yen Jui Chang, Wei-Hao Huang, Felix Burt, Esperanza Cuenca Gomez, Zohim Chandani, William Clements, Ian Walmsley et al. Published: 2026-03-16 Categories: quant-ph, cs.ET, cs.LG arXiv: https://arxiv.org/abs/2603.14898v1 Photonic quantum processors naturally produce intrinsically stochastic measurement outcomes, offering a hardware-native source of structured randomness that can be exploited during machine-learning training. Here we introduce Photonic Quantum-Enhanced Knowledge Distillation (PQKD), a hybrid quantum photonic--classical framework in which a programmable photonic circuit generates a compact conditioning signal that constrains and guides a parameter-efficient student network during distillation from a high-capacity teacher. PQKD replaces fully trainable convolutional kernels with dictionary convolutions: each layer learns only a small set of shared spatial basis filters, while sample-dependent channel-mixing weights are derived from shot-limited photonic features and mapped through a fixed linear transform. Training alternates between standard gradient-based optimisation of the student and sampling-robust, gradient-free updates of photonic parameters, avoiding differentiation through photonic hardware. Across MNIST, Fashion-MNIST and CIFAR-10, PQKD traces a controllable compression--accuracy frontier, remaining close to teacher performance on simpler benchmarks under aggressive convolutional compression. Performance degrades predictably with finite sampling, consistent with shot-noise scaling, and exponential moving-average feature smoothing suppresses high-frequency shot-noise fluctuations, extending the practical operating regime at moderate shot budgets. --- ### BiTro: Bidirectional Transfer Learning Enhances Bulk and Spatial Transcriptomics Prediction in Cancer Pathological Images Authors: Jingkun Yu, Guangkai Shang, Changtao Li, Xun Gong, Tianrui Li, Yazhou He, Zhipeng Luo Published: 2026-03-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.14897v1 Cancer pathological analysis requires modeling tumor heterogeneity across multiple modalities, primarily through transcriptomics and whole slide imaging (WSI), along with their spatial relations. On one hand, bulk transcriptomics and WSI images are largely available but lack spatial mapping; on the other hand, spatial transcriptomics (ST) data can offer high spatial resolution, yet facing challenges of high cost, low sequencing depth, and limited sample sizes. Therefore, the data foundation of either side is flawed and has its limit in accurately finding the mapping between the two modalities. To this end, we propose BiTro, a bidirectional transfer learning framework that can enhance bulk and spatial transcriptomics prediction from pathological images. Our contributions are twofold. First, we design a universal and transferable model architecture that works for both bulk+WSI and ST data. A major highlight is that we model WSI images on the cellular level to better capture cells' visual features, morphological phenotypes, and their spatial relations; to map cells' features to their transcriptomics measured in bulk or ST, we adopt multiple instance learning. Second, by using LoRA, our model can be efficiently transferred between bulk and ST data to exploit their complementary information. To test our framework, we conducted comprehensive experiments on five cancer datasets. Results demonstrate that 1) our base model can achieve better or competitive performance compared to existing models on bulk or spatial transcriptomics prediction, and 2) transfer learning can further improve the base model's performance. --- ### Informative Perturbation Selection for Uncertainty-Aware Post-hoc Explanations Authors: Sumedha Chugh, Ranjitha Prasad, Nazreen Shah Published: 2026-03-16 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2603.14894v3 Trust and ethical concerns due to the widespread deployment of opaque machine learning (ML) models motivating the need for reliable model explanations. Post-hoc model-agnostic explanation methods addresses this challenge by learning a surrogate model that approximates the behavior of the deployed black-box ML model in the locality of a sample of interest. In post-hoc scenarios, neither the underlying model parameters nor the training are available, and hence, this local neighborhood must be constructed by generating perturbed inputs in the neighborhood of the sample of interest, and its corresponding model predictions. We propose \emph{Expected Active Gain for Local Explanations} (\texttt{EAGLE}), a post-hoc model-agnostic explanation framework that formulates perturbation selection as an information-theoretic active learning problem. By adaptively sampling perturbations that maximize the expected information gain, \texttt{EAGLE} efficiently learns a linear surrogate explainable model while producing feature importance scores along with the uncertainty/confidence estimates. Theoretically, we establish that cumulative information gain scales as $\mathcal{O}(d \log t)$, where $d$ is the feature dimension and $t$ represents the number of samples, and that the sample complexity grows linearly with $d$ and logarithmically with the confidence parameter $1/δ$. Empirical results on tabular and image datasets corroborate our theoretical findings and demonstrate that \texttt{EAGLE} improves explanation reproducibility across runs, achieves higher neighborhood stability, and improves perturbation sample quality as compared to state-of-the-art baselines such as Tilia, US-LIME, GLIME and BayesLIME. --- ### Informative Perturbation Selection for Uncertainty-Aware Post-hoc Explanations Authors: Sumedha Chugh, Ranjitha Prasad, Nazreen Shah Published: 2026-03-16 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2603.14894v2 Trust and ethical concerns due to the widespread deployment of opaque machine learning (ML) models motivating the need for reliable model explanations. Post-hoc model-agnostic explanation methods addresses this challenge by learning a surrogate model that approximates the behavior of the deployed black-box ML model in the locality of a sample of interest. In post-hoc scenarios, neither the underlying model parameters nor the training are available, and hence, this local neighborhood must be constructed by generating perturbed inputs in the neighborhood of the sample of interest, and its corresponding model predictions. We propose \emph{Expected Active Gain for Local Explanations} (\texttt{EAGLE}), a post-hoc model-agnostic explanation framework that formulates perturbation selection as an information-theoretic active learning problem. By adaptively sampling perturbations that maximize the expected information gain, \texttt{EAGLE} efficiently learns a linear surrogate explainable model while producing feature importance scores along with the uncertainty/confidence estimates. Theoretically, we establish that cumulative information gain scales as $\mathcal{O}(d \log t)$, where $d$ is the feature dimension and $t$ represents the number of samples, and that the sample complexity grows linearly with $d$ and logarithmically with the confidence parameter $1/δ$. Empirical results on tabular and image datasets corroborate our theoretical findings and demonstrate that \texttt{EAGLE} improves explanation reproducibility across runs, achieves higher neighborhood stability, and improves perturbation sample quality as compared to state-of-the-art baselines such as Tilia, US-LIME, GLIME and BayesLIME. --- ### LLMs as Signal Detectors: Sensitivity, Bias, and the Temperature-Criterion Analogy Authors: Jon-Paul Cacioli Published: 2026-03-16 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.14893v1 Large language models (LLMs) are evaluated for calibration using metrics such as Expected Calibration Error that conflate two distinct components: the model's ability to discriminate correct from incorrect answers (sensitivity) and its tendency toward confident or cautious responding (bias). Signal Detection Theory (SDT) decomposes these components. While SDT-derived metrics such as AUROC are increasingly used, the full parametric framework - unequal-variance model fitting, criterion estimation, z-ROC analysis - has not been applied to LLMs as signal detectors. In this pre-registered study, we treat three LLMs as observers performing factual discrimination across 168,000 trials and test whether temperature functions as a criterion shift analogous to payoff manipulations in human psychophysics. Critically, this analogy may break down because temperature changes the generated answer itself, not only the confidence assigned to it. Our results confirm the breakdown with temperature simultaneously increasing sensitivity (AUC) and shifting criterion. All models exhibited unequal-variance evidence distributions (z-ROC slopes 0.52-0.84), with instruct models showing more extreme asymmetry (0.52-0.63) than the base model (0.77-0.87) or human recognition memory (~0.80). The SDT decomposition revealed that models occupying distinct positions in sensitivity-bias space could not be distinguished by calibration metrics alone, demonstrating that the full parametric framework provides diagnostic information unavailable from existing metrics. --- ### Balancing Saliency and Coverage: Semantic Prominence-Aware Budgeting for Visual Token Compression in VLMs Authors: Jaehoon Lee, Mingi Jung, Soohyuk Jang, Seungryong Yoo, Dahuin Jung, Sungroh Yoon Published: 2026-03-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14892v1 Large Vision-Language Models (VLMs) achieve strong multimodal understanding capabilities by leveraging high-resolution visual inputs, but the resulting large number of visual tokens creates a major computational bottleneck. Recent work mitigates this issue through visual token compression, typically compressing tokens based on saliency, diversity, or a fixed combination of both. We observe that the distribution of semantic prominence varies substantially across samples, leading to different optimal trade-offs between local saliency preservation and global coverage. This observation suggests that applying a static compression strategy across all samples can be suboptimal. Motivated by this insight, we propose PromPrune, a sample-adaptive visual token selection framework composed of semantic prominence-aware budget allocation and a two-stage selection pipeline. Our method adaptively balances local saliency preservation and global coverage according to the semantic prominence distribution of each sample. By allocating token budgets between locally salient regions and globally diverse regions, our method maintains strong performance even under high compression ratios. On LLaVA-NeXT-7B, our approach reduces FLOPs by 88% and prefill latency by 22% while preserving 97.5% of the original accuracy. --- ### Decision-Level Ordinal Modeling for Multimodal Essay Scoring with Large Language Models Authors: Han Zhang, Jiamin Su, Li liu Published: 2026-03-16 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.14891v1 Automated essay scoring (AES) predicts multiple rubric-defined trait scores for each essay, where each trait follows an ordered discrete rating scale. Most LLM-based AES methods cast scoring as autoregressive token generation and obtain the final score via decoding and parsing, making the decision implicit. This formulation is particularly sensitive in multimodal AES, where the usefulness of visual inputs varies across essays and traits. To address these limitations, we propose Decision-Level Ordinal Modeling (DLOM), which makes scoring an explicit ordinal decision by reusing the language model head to extract score-wise logits on predefined score tokens, enabling direct optimization and analysis in the score space. For multimodal AES, DLOM-GF introduces a gated fusion module that adaptively combines textual and multimodal score logits. For text-only AES, DLOM-DA adds a distance-aware regularization term to better reflect ordinal distances. Experiments on the multimodal EssayJudge dataset show that DLOM improves over a generation-based SFT baseline across scoring traits, and DLOM-GF yields further gains when modality relevance is heterogeneous. On the text-only ASAP/ASAP++ benchmarks, DLOM remains effective without visual inputs, and DLOM-DA further improves performance and outperforms strong representative baselines. --- ### SDiaReward: Modeling and Benchmarking Spoken Dialogue Rewards with Modality and Colloquialness Authors: Jingyu Lu, Yuhan Wang, Fan Zhuo, Xize Cheng, Changhao Pan, Xueyi Pu, Yifu Chen, Chenyuhao Wen, Tianle Liang, Zhou Zhao Published: 2026-03-16 Categories: eess.AS, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.14889v2 The rapid evolution of end-to-end spoken dialogue systems demands transcending mere textual semantics to incorporate paralinguistic nuances and the spontaneous nature of human conversation. However, current methods struggle with two critical gaps: the modality gap, involving prosody and emotion, and the colloquialness gap, distinguishing written scripts from natural speech. To address these challenges, we introduce SDiaReward, an end-to-end multi-turn reward model trained on SDiaReward-Dataset, a novel collection of episode-level preference pairs explicitly targeting these gaps. It operates directly on full multi-turn speech episodes and is optimized with pairwise preference supervision, enabling joint assessment of modality and colloquialness in a single evaluator. We further establish ESDR-Bench, a stratified benchmark for robust episode-level evaluation. Experiments demonstrate that SDiaReward achieves state-of-the-art pairwise preference accuracy, significantly outperforming general-purpose audio LLMs. Further analysis suggests that SDiaReward captures relative conversational expressiveness beyond superficial synthesis cues, improving generalization across domains and recording conditions. Code, data, and demos are available at https://github.com/MM-Speech/SDiaReward/. --- ### PASTE: Physics-Aware Scattering Topology Embedding Framework for SAR Object Detection Authors: Jiacheng Chen, Yuxuan Xiong, Haipeng Wang Published: 2026-03-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14886v1 Current deep learning-based object detection for Synthetic Aperture Radar (SAR) imagery mainly adopts optical image methods, treating targets as texture patches while ignoring inherent electromagnetic scattering mechanisms. Though scattering points have been studied to boost detection performance, most methods still rely on amplitude-based statistical models. Some approaches introduce frequency-domain information for scattering center extraction, but they suffer from high computation cost and poor compatibility with diverse datasets. Thus, effectively embedding scattering topological information into modern detection frameworks remains challenging. To solve these problems, this paper proposes the Physics-Aware Scattering Topology Embedding Framework (PASTE), a novel closed-loop architecture for comprehensive scattering prior integration. By building the full pipeline from topology generation, injection to joint supervision, PASTE elegantly integrates scattering physics into modern SAR detectors. Specifically, it designs a scattering keypoint generation and automatic annotation scheme based on the Attributed Scattering Center (ASC) model to produce scalable and physically consistent priors. A scattering topology injection module guides multi-scale feature learning, and a scattering prior supervision strategy constrains network optimization by aligning predictions with scattering center distributions. Experiments on real datasets show that PASTE is compatible with various detectors and brings relative mAP gains of 2.9% to 11.3% over baselines with acceptable computation overhead. Visualization of scattering maps verifies that PASTE successfully embeds scattering topological priors into feature space, clearly distinguishing target and background scattering regions, thus providing strong interpretability for results. --- ### SpiralDiff: Spiral Diffusion with LoRA for RGB-to-RAW Conversion Across Cameras Authors: Huanjing Yue, Shangbin Xie, Cong Cao, Qian Wu, Lei Zhang, Lei Zhao, Jingyu Yang Published: 2026-03-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14885v1 RAW images preserve superior fidelity and rich scene information compared to RGB, making them essential for tasks in challenging imaging conditions. To alleviate the high cost of data collection, recent RGB-to-RAW conversion methods aim to synthesize RAW images from RGB. However, they overlook two key challenges: (i) the reconstruction difficulty varies with pixel intensity, and (ii) multi-camera conversion requires camera-specific adaptation. To address these issues, we propose SpiralDiff, a diffusion-based framework tailored for RGB-to-RAW conversion with a signal-dependent noise weighting strategy that adapts reconstruction fidelity across intensity levels. In addition, we introduce CamLoRA, a camera-aware lightweight adaptation module that enables a unified model to adapt to different camera-specific ISP characteristics. Extensive experiments on four benchmark datasets demonstrate the superiority of SpiralDiff in RGB-to-RAW conversion quality and its downstream benefits in RAW-based object detection. Our code and model are available at https://github.com/Chuancy-TJU/SpiralDiff. --- ### Customizing ChatGPT for Second Language Speaking Practice: Genuine Support or Just a Marketing Gimmick? Authors: Fanfei Meng Published: 2026-03-16 Categories: cs.HC, cs.CL arXiv: https://arxiv.org/abs/2603.14884v1 ChatGPT, with its customization features and Voice Mode, has the potential for more engaging and peresonalized ESL (English as a Second Language) education. This study examines the efficacy of customized ChatGPT conversational features in facilitating ESL speaking practices, comparing the performance of four versions of ChatGPT Voice Mode: uncustomized Standard mode, uncustomized Advanced mode, customized Standard mode, and customized Advanced mode. Customization was guided by prompt engineering principles and grounded in relevant theories, including Motivation Theory, Culturally Responsive Teaching (CRT), Communicative Language Teaching (CLT), and the Affective Filter Hypothesis. Content analysis found that customized versions generally provided more balanced feedback and emotional support, contributing to a positive and motivating learning environment. However, cultural responsiveness did not show significant improvement despite targeted customization efforts. These initial findings suggest that customization could enhance ChatGPT's capacity as a more effective language tutor, with the standard model already capable of meeting the learning needs. The study underscores the importance of prompt engineering and AI literacy in maximizaing AI's potential in language learning. --- ### LLMind: Bio-inspired Training-free Adaptive Visual Representations for Vision-Language Models Authors: Soumyaratna Debnath, Bui Duc Manh, Zinan Liu, Lin Wang Published: 2026-03-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14882v2 Vision-Language Models (VLMs) typically assume a uniform spatial fidelity across the entire field of view of visual inputs, dedicating equal precision to even the uninformative regions. By contrast, human vision is neither uniform nor static; it is adaptive, selective, and resource-efficient. In light of this, we present the first systematic analysis of bio-inspired visual representation methods, providing insights for more efficient and adaptive VLMs. We propose LLMind (Looking Like the Mind), a novel training-free framework that mimics foveated encoding and cortical magnification in human vision to achieve adaptive, efficient representations for VLMs under tight pixel budgets. Our key idea is to explore a Bio-inspired Adaptive Sampling Strategy (BASS), enabling a Mobius-parameterized module that performs non-uniform sampling while preserving global scene structure. On top of BASS, we introduce closed-loop semantic feedback (CSF) via test-time adaptation to align perceptual saliency with textual information from the frozen VLM. We evaluate LLMind against uniform and other sampling baselines across diverse scene-level and region-guided visual question answering benchmarks. The results show dramatic gains, with average improvements of +20% on VQAv2, +38% on Seed-Bench, and +37% on A-OKVQA compared to uniform sampling under tight pixel budgets. More surprisingly, LLMind retains up to 82%, 92%, and 97% of the full-resolution performance using only 1%, 3%, and 5% of the pixels, respectively. Moreover, LLMind is lightweight, plug-and-play, and compatible with existing VLMs without requiring architectural changes. --- ### RealVLG-R1: A Large-Scale Real-World Visual-Language Grounding Benchmark for Robotic Perception and Manipulation Authors: Linfei Li, Lin Zhang, Ying Shen Published: 2026-03-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14880v1 Visual-language grounding aims to establish semantic correspondences between natural language and visual entities, enabling models to accurately identify and localize target objects based on textual instructions. Existing VLG approaches focus on coarse-grained, object-level localization, while traditional robotic grasping methods rely predominantly on geometric cues and lack language guidance, which limits their applicability in language-driven manipulation scenarios. To address these limitations, we propose the RealVLG framework, which integrates the RealVLG-11B dataset and the RealVLG-R1 model to unify real-world visual-language grounding and grasping tasks. RealVLG-11B dataset provides multi-granularity annotations including bounding boxes, segmentation masks, grasp poses, contact points, and human-verified fine-grained language descriptions, covering approximately 165,000 images, over 800 object instances, 1.3 million segmentation, detection, and language annotations, and roughly 11 billion grasping examples. Building on this dataset, RealVLG-R1 employs Reinforcement Fine-tuning on pretrained large-scale vision-language models to predict bounding boxes, segmentation masks, grasp poses, and contact points in a unified manner given natural language instructions. Experimental results demonstrate that RealVLG supports zero-shot perception and manipulation in real-world unseen environments, establishing a unified semantic-visual multimodal benchmark that provides a comprehensive data and evaluation platform for language-driven robotic perception and grasping policy learning. All data and code are publicly available at https://github.com/lif314/RealVLG-R1. --- ### Seismic full-waveform inversion based on a physics-driven generative adversarial network Authors: Xinyi Zhang, Caiyun Liu, Jie Xiong, Qingfeng Yu Published: 2026-03-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.14879v1 Objectives: Full-waveform inversion (FWI) is a high-resolution geophysical imaging technique that reconstructs subsurface velocity models by iteratively minimizing the misfit between predicted and observed seismic data. However, under complex geological conditions, conventional FWI suffers from strong dependence on the initial model and tends to produce unstable results when the data are sparse or contaminated by noise. Methods: To address these limitations, this paper proposes a physics-driven generative adversarial network-based full-waveform inversion method. The proposed approach integrates the data-driven capability of deep neural networks with the physical constraints imposed by the seismic wave equation, and employs adversarial training through a discriminator to enhance the stability and robustness of the inversion results. Results: Experimental results on two representative benchmark geological models demonstrate that the proposed method can effectively recover complex velocity structures and achieves superior performance in terms of structural similarity (SSIM) and signal-to-noise ratio (SNR). Conclusions: This method provides a promising solution for alleviating the initial-model dependence in full-waveform inversion and shows strong potential for practical applications. --- ### A Hybrid AI and Rule-Based Decision Support System for Disease Diagnosis and Management Using Labs Authors: Muhammad Hammad Maqsood, Mubashir Sajid, Khubaib Ahmed, Muhammad Usamah Shahid, Muddassar Farooq Published: 2026-03-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.14876v1 This research paper outlines the development and implementation of a novel Clinical Decision Support System (CDSS) that integrates AI predictive modeling with medical knowledge bases. It utilizes the quantifiable information elements in lab results for inferring likely diagnoses a patient might have. Subsequently, suggesting investigations to confirm the likely diagnoses -- an assistive tool for physicians. The system fuses knowledge contained in a rule-base expert system with inferences of data driven predictors based on the features in labs. The data for 593,055 patients was collected from 547 primary care centers across the US to model our decision support system and derive Real-Word Evidence (RWE) to make it relevant for a large demographic of patients. Our Rule-Base comprises clinically validated rules, modeling 59 health conditions that can directly confirm one or more of diseases and assign ICD-10 codes to them. The Likely Diagnosis system uses multi-class classification, covering 37 ICD-10 codes, which are grouped together into 11 categories based on the labs that physicians prescribe to confirm the diagnosis. This research offers a novel system that assists a physician by utilizing medical profile of a patient and routine lab investigations to predict a group of likely diseases and then confirm them, coupled with providing explanations for inferences, thereby assisting physicians to reduce misdiagnosis of patients in clinical decision-making. --- ### Developing an English-Efik Corpus and Machine Translation System for Digitization Inclusion Authors: Offiong Bassey Edet, Mbuotidem Sunday Awak, Emmanuel Oyo-Ita, Benjamin Okon Nyong, Ita Etim Bassey Published: 2026-03-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.14873v1 Low-resource languages serve as invaluable repositories of human history, preserving cultural and intellectual diversity. Despite their significance, they remain largely absent from modern natural language processing systems. While progress has been made for widely spoken African languages such as Swahili, Yoruba, and Amharic, smaller indigenous languages like Efik continue to be underrepresented in machine translation research. This study evaluates the effectiveness of state-of-the-art multilingual neural machine translation models for English-Efik translation, leveraging a small-scale, community-curated parallel corpus of 13,865 sentence pairs. We fine-tuned both the mT5 multilingual model and the NLLB200 model on this dataset. NLLB-200 outperformed mT5, achieving BLEU scores of 26.64 for English-Efik and 31.21 for Efik-English, with corresponding chrF scores of 51.04 and 47.92, indicating improved fluency and semantic fidelity. Our findings demonstrate the feasibility of developing practical machine translation tools for low-resource languages and highlight the importance of inclusive data practices and culturally grounded evaluation in advancing equitable NLP. --- ### IgPose: A Generative Data-Augmented Pipeline for Robust Immunoglobulin-Antigen Binding Prediction Authors: Tien-Cuong Bui, Injae Chung, Wonjun Lee, Junsu Ko, Juyong Lee Published: 2026-03-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.14870v1 Predicting immunoglobulin-antigen (Ig-Ag) binding remains a significant challenge due to the paucity of experimentally-resolved complexes and the limited accuracy of de novo Ig structure prediction. We introduce IgPose, a generalizable framework for Ig-Ag pose identification and scoring, built on a generative data-augmentation pipeline. To mitigate data scarcity, we constructed the Structural Immunoglobulin Decoy Database (SIDD), a comprehensive repository of high-fidelity synthetic decoys. IgPose integrates equivariant graph neural networks, ESM-2 embeddings, and gated recurrent units to synergistically capture both geometric and evolutionary features. We implemented interface-focused k-hop sampling with biologically guided pooling to enhance generalization across diverse interfaces. The framework comprises two sub-networks--IgPoseClassifier for binding pose discrimination and IgPoseScore for DockQ score estimation--and achieves robust performance on curated internal test sets and the CASP-16 benchmark compared to physics and deep learning baselines. IgPose serves as a versatile computational tool for high-throughput antibody discovery pipelines by providing accurate pose filtering and ranking. IgPose is available on GitHub (https://github.com/arontier/igpose). --- ### A Self-Evolving Defect Detection Framework for Industrial Photovoltaic Systems Authors: Haoyu He, Yu Duan, Wenzhen Liu, Hanyuan Hang, Boyu Qin, Qiantu Tuo, Xiaoke Yang, Rui Li Published: 2026-03-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.14869v2 Reliable photovoltaic (PV) power generation requires timely detection of module defects that may reduce energy yield, accelerate degradation, and increase lifecycle operation and maintenance costs during field operation. Electroluminescence (EL) imaging has therefore been widely adopted for PV module inspection. However, automated defect detection in real operational environments remains challenging due to heterogeneous module geometries, low-resolution imaging conditions, subtle defect morphology, long-tailed defect distributions, and continual data shifts introduced by evolving inspection and labeling processes. These factors significantly limit the robustness and long-term maintainability of conventional deep-learning inspection pipelines. To address these challenges, this paper proposes SEPDD, a Self-Evolving Photovoltaic Defect Detection framework designed for evolving industrial PV inspection scenarios. SEPDD integrates automated model optimization with a continual self-evolving learning mechanism, enabling the inspection system to progressively adapt to distribution shifts and newly emerging defect patterns during long-term deployment. Experiments conducted on both a public PV defect benchmark and a private industrial EL dataset demonstrate the effectiveness of the proposed framework. Both datasets exhibit severe class imbalance and significant domain shift. SEPDD achieves a leading mAP50 of 91.4% on the public dataset and 49.5% on the private dataset. It surpasses the autonomous baseline by 14.8% and human experts by 4.7% on the public dataset, and by 4.9% and 2.5%, respectively, on the private dataset. --- ### Sample-Efficient Hypergradient Estimation for Decentralized Bi-Level Reinforcement Learning Authors: Mikoto Kudo, Takumi Tanabe, Akifumi Wachi, Youhei Akimoto Published: 2026-03-16 Categories: cs.LG, cs.AI, cs.GT, cs.MA arXiv: https://arxiv.org/abs/2603.14867v4 Many strategic decision-making problems, such as environment design for warehouse robots, can be naturally formulated as bi-level reinforcement learning (RL), where a leader agent optimizes its objective while a follower solves a Markov decision process (MDP) conditioned on the leader's decisions. In many situations, a fundamental challenge arises when the leader cannot intervene in the follower's optimization process; it can only observe the optimization outcome. We address this decentralized setting by deriving the hypergradient of the leader's objective, i.e., the gradient of the leader's strategy that accounts for changes in the follower's optimal policy. Unlike prior hypergradient-based methods that require extensive data for repeated state visits or rely on gradient estimators whose complexity can increase substantially with the high-dimensional leader's decision space, we leverage the Boltzmann covariance trick to derive an alternative hypergradient formulation. This enables efficient hypergradient estimation solely from interaction samples, even when the leader's decision space is high-dimensional. Additionally, to our knowledge, this is the first method that enables hypergradient-based optimization for 2-player Markov games in decentralized settings. Experiments highlight the impact of hypergradient updates and demonstrate our method's effectiveness in both discrete and continuous state tasks. --- ### Shopping Companion: Benchmarking and Training LLM Agents for Long-Horizon Preference-Grounded E-Commerce Tasks Authors: Zijian Yu, Kejun Xiao, Huaipeng Zhao, Tao Luo, Xiaoyi Zeng Published: 2026-03-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.14864v3 In e-commerce, LLM agents show promise for shopping tasks such as recommendations, budget management, and bundle deals, where accurately capturing user preferences from long-horizon conversations is critical. However, progress is limited by two key challenges: (1) the absence of benchmarks for evaluating long-term preference-aware shopping tasks, and (2) the lack of fine-grained supervision for shopping agent training. To fill the benchmark gap, we introduce Shopping Companion Bench, a novel benchmark comprising two shopping tasks that require cross-session preference memory, grounded in a product pool of over 1.2 million real-world items. Our analysis further identifies two major sources of failure on this benchmark: cascading errors caused by preference hallucination, and insufficient verification of product attributes against user requirements. To address these failure modes, we design annotation-free, tool-wise rewards that provide process supervision for each tool call, alleviating reward sparsity in long-horizon tasks. Experimental results demonstrate that even state-of-the-art models such as GPT-5 achieve success rates below 70%, highlighting the difficulty of our benchmark. Notably, our fine-tuned lightweight 4B model consistently outperforms strong baselines in both preference capture and task performance, suggesting the effectiveness of our reward design. --- ### A Score Filter Enhanced Data Assimilation Framework for Data-Driven Dynamical Systems Authors: Jingqiao Tang, Ryan Bausback, Feng Bao, Guannan Zhang, Phuoc-Toan Huynh Published: 2026-03-16 Categories: math.DS, cs.LG, math.PR arXiv: https://arxiv.org/abs/2603.14863v1 We introduce a score-filter-enhanced data assimilation framework designed to reduce predictive uncertainty in machine learning (ML) models for data-driven dynamical system forecasting. Machine learning serves as an efficient numerical model for predicting dynamical systems. However, even with sufficient data, model uncertainty remains and accumulates over time, causing the long-term performance of ML models to deteriorate. To overcome this difficulty, we integrate data assimilation techniques into the training process to iteratively refine the model predictions by incorporating observational information. Specifically, we apply the Ensemble Score Filter (EnSF), a generative AI-based training-free diffusion model approach, for solving the data assimilation problem in high-dimensional nonlinear complex systems. This leads to a hybrid data assimilation-training framework that combines ML with EnSF to improve long-term predictive performance. We shall demonstrate that EnSF-enhanced ML can effectively reduce predictive uncertainty in ML-based Lorenz-96 system prediction and the Korteweg-De Vries (KdV) equation prediction. --- ### Video Detector: A Dual-Phase Vision-Based System for Real-Time Traffic Intersection Control and Intelligent Transportation Analysis Authors: Mustafa Fatih Şen, Halûk Gümüşkaya, Şenol Pazar Published: 2026-03-16 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.14861v1 Urban traffic management increasingly requires intelligent sensing systems capable of adapting to dynamic traffic conditions without costly infrastructure modifications. Vision-based vehicle detection has therefore become a key technology for modern intelligent transportation systems. This study presents Video Detector (VD), a dual-phase vision-based traffic intersection management system designed as a flexible and cost-effective alternative to traditional inductive loop detectors. The framework integrates a real-time module (VD-RT) for intersection control with an offline analytical module (VD-Offline) for detailed traffic behavior analysis. Three system configurations were implemented using SSD Inception v2, Faster R-CNN Inception v2, and CenterNet ResNet-50 V1 FPN, trained on datasets totaling 108,000 annotated images across 6-10 vehicle classes. Experimental results show detection performance of up to 90% test accuracy and 29.5 mAP@0.5, while maintaining real-time throughput of 37 FPS on HD video streams. Field deployments conducted in collaboration with Istanbul IT and Smart City Technologies Inc. (ISBAK) demonstrate stable operation under diverse environmental conditions. The system supports virtual loop detection, vehicle counting, multi-object tracking, queue estimation, speed analysis, and multiclass vehicle classification, enabling comprehensive intersection monitoring without the need for embedded road sensors. The annotated dataset and training pipeline are publicly released to support reproducibility. These results indicate that the proposed framework provides a scalable and deployable vision-based solution for intelligent transportation systems and smart-city traffic management. --- ### Architecture-Agnostic Feature Synergy for Universal Defense Against Heterogeneous Generative Threats Authors: Bingxue Zhang, Yang Gao, Feida Zhu, Yanyan Shen, Yang Shi Published: 2026-03-16 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2603.14860v1 Generative AI deployment poses unprecedented challenges to content safety and privacy. However, existing defense mechanisms are often tailored to specific architectures (e.g., Diffusion Models or GANs), creating fragile "defense silos" that fail against heterogeneous generative threats. This paper identifies a fundamental optimization barrier in naive pixel-space ensemble strategies: due to divergent objective functions, pixel-level gradients from heterogeneous generators become statistically orthogonal, causing destructive interference. To overcome this, we observe that despite disparate low-level mechanisms, high-level feature representations of generated content exhibit alignment across architectures. Based on this, we propose the Architecture-Agnostic Targeted Feature Synergy (ATFS) framework. By introducing a target guidance image, ATFS reformulates multi-model defense as a unified feature space alignment task, enabling intrinsic gradient alignment without complex rectification. Extensive experiments show ATFS achieves SOTA protection in heterogeneous scenarios (e.g., Diffusion+GAN). It converges rapidly, reaching over 90% performance within 40 iterations, and maintains strong attack potency even under tight perturbation budgets. The framework seamlessly extends to unseen architectures (e.g., VQ-VAE) by switching the feature extractor, and demonstrates robust resistance to JPEG compression and scaling. Being computationally efficient and lightweight, ATFS offers a viable pathway to dismantle defense silos and enable universal generative security. Code and models are open-sourced for reproducibility. --- ### From Horizontal to Rotated: Cross-View Object Geo-Localization with Orientation Awareness Authors: Chenlin Fu, Ao Gong, Yingying Zhu Published: 2026-03-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14856v1 Cross-View object geo-localization (CVOGL) aims to precisely determine the geographic coordinates of a query object from a ground or drone perspective by referencing a satellite map. Segmentation-based approaches offer high precision but require prohibitively expensive pixel-level annotations, whereas more economical detection-based methods suffer from lower accuracy. This performance disparity in detection is primarily caused by two factors: the poor geometric fit of Horizontal Bounding Boxes (HBoxes) for oriented objects and the degradation in precision due to feature map scaling. Motivated by these, we propose leveraging Rotated Bounding Boxes (RBoxes) as a natural extension of the detection-based paradigm. RBoxes provide a much tighter geometric fit to oriented objects. Building on this, we introduce OSGeo, a novel geo-localization framework, meticulously designed with a multi-scale perception module and an orientation-sensitive head to accurately regress RBoxes. To support this scheme, we also construct and release CVOGL-R, the first dataset with precise RBox annotations for CVOGL. Extensive experiments demonstrate that our OSGeo achieves state-of-the-art performance, consistently matching or even surpassing the accuracy of leading segmentation-based methods but with an annotation cost that is over an order of magnitude lower. --- ### PCodeTrans: Translate Decompiled Pseudocode to Compilable and Executable Equivalent Authors: Yuxin Cui, Zeyu Gao, Shuxian He, Siliang Qin, Chao Zhang Published: 2026-03-16 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2603.14855v1 Decompilation is foundational to binary analysis, yet conventional tools prioritize human readability over strict recompilability and verifiable runtime correctness. While recent LLM-based approaches attempt to refine decompiled pseudocode, they typically either optimize solely for readability or rely on static analysis for evaluation. This makes them prone to "semantic hallucinations" that compromise accuracy and fail to resolve actual runtime failures. For critical tasks like software modernization and vulnerability remediation, recovered code must not only compile but replicate the original binary's behavior. We present PCodeTrans, a feedback-driven framework that bridges the gap between decompilation, recompilation, and rigorous function-level dynamic validation. After extracting a minimal yet coherent context to guarantee recompilability, PCodeTrans employs an in situ substitutable engine to hot-swap the compiled function directly into the unmodified binary, natively preserving its authentic execution context and global dependencies. Guided by fine-grained differential tracing, PCodeTrans generates precise runtime feedback to iteratively guide an LLM in repairing semantic discrepancies. Evaluated on Coreutils and Binutils, PCodeTrans achieves unprecedented recovery performance when rectifying raw Hex-Rays outputs, attaining 100% function-level compilability on unstripped binaries alongside 99.55% and 99.89% test-validated behavioral consistency, respectively. In doing so, it resolves 76.56% and 79.74% of logic errors exposed by official test suites. Exhibiting exceptional resilience, PCodeTrans maintains over 96% behavioral consistency even on fully stripped binaries. By significantly outperforming all existing baselines, PCodeTrans paves a practical path to reliably translate decompiled pseudocode into compilable and executable equivalents. --- ### AutoMoT: A Unified Vision-Language-Action Model with Asynchronous Mixture-of-Transformers for End-to-End Autonomous Driving Authors: Wenhui Huang, Songyan Zhang, Qihang Huang, Zhidong Wang, Zhiqi Mao, Collister Chua, Zhan Chen, Long Chen, Chen Lv Published: 2026-03-16 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2603.14851v3 Integrating vision-language models (VLMs) into end-to-end (E2E) autonomous driving (AD) systems has shown promise in improving scene understanding. However, existing integration strategies suffer from several limitations: they either struggle to resolve distribution misalignment between reasoning and action spaces, underexploit the general reasoning capabilities of pretrained VLMs, or incur substantial inference latency during action policy generation, which degrades driving performance. To address these challenges, we propose AutoMoT in this work, an end-to-end AD framework that unifies reasoning and action generation within a single vision-language-action (VLA) model. Our approach leverages a mixture-of-transformer (MoT) architecture with joint attention sharing, which preserves the general reasoning capabilities of pre-trained VLMs while enabling efficient fast-slow inference through asynchronous execution at different task frequencies. Extensive experiments on multiple benchmarks, under both open- and closed-loop settings, demonstrate that AutoMoT achieves competitive performance compared to state-of-the-art methods. We further investigate the functional boundary of pre-trained VLMs in AD, examining when AD-tailored fine-tuning is necessary. Our results show that pre-trained VLMs can achieve competitive multi-task scene understanding performance through semantic prompting alone, while fine-tuning remains essential for action-level tasks such as decision-making and trajectory planning. We refer to https://automot-website.github.io/ for the demonstration videos and qualitative results. --- ### From Artefact to Insight: Efficient Low-Rank Adaptation of BrushNet for Scanning Probe Microscopy Image Restoration Authors: Ziwei Wei, Yao Shen, Wanheng Lu, Ghim Wei Ho, Kaiyang Zeng Published: 2026-03-16 Categories: cs.CV, cond-mat.mes-hall arXiv: https://arxiv.org/abs/2603.14850v1 Scanning Probe Microscopy or SPM offers nanoscale resolution but is frequently marred by structured artefacts such as line scan dropout, gain induced noise, tip convolution, and phase hops. While most available methods treat SPM artefact removal as isolated denoising or interpolation tasks, the generative inpainting perspective remains largely unexplored. In this work, we introduce a diffusion based inpainting framework tailored to scientific grayscale imagery. By fine tuning less than 0.2 percent of BrushNet weights with rank constrained low rank adaptation (LoRA), we adapt a pretrained diffusion model using only 7390 artefact, clean pairs distilled from 739 experimental scans. On our forthcoming public SPM InpBench benchmark, the LoRA enhanced model lifts the Peak Signal to Noise Ratio or PSNR by 6.61 dB and halves the Learned Perceptual Image Patch Similarity or LPIPS relative to zero-shot inference, while matching or slightly surpassing the accuracy of full retraining, trainable on a single GPU instead of four high-memory cards. The approach generalizes across various SPM image channels including height, amplitude and phase, faithfully restores subtle structural details, and suppresses hallucination artefacts inherited from natural image priors. This lightweight framework enables efficient, scalable recovery of irreplaceable SPM images and paves the way for a broader diffusion model adoption in nanoscopic imaging analysis. --- ### Personalized Federated Learning with Residual Fisher Information for Medical Image Segmentation Authors: Meilu Zhu, Yuxing Li, Zhiwei Wang, Edmund Y. Lam Published: 2026-03-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14848v1 Federated learning enables multiple clients (institutions) to collaboratively train machine learning models without sharing their private data. To address the challenge of data heterogeneity across clients, personalized federated learning (pFL) aims to learn customized models for each client. In this work, we propose pFL-ResFIM, a novel pFL framework that achieves client-adaptive personalization at the parameter level. Specifically, we introduce a new metric, Residual Fisher Information Matrix (ResFIM), to quantify the sensitivity of model parameters to domain discrepancies. To estimate ResFIM for each client model under privacy constraints, we employ a spectral transfer strategy that generates simulated data reflecting the domain styles of different clients. Based on the estimated ResFIM, we partition model parameters into domain-sensitive and domain-invariant components. A personalized model for each client is then constructed by aggregating only the domain-invariant parameters on the server. Extensive experiments on public datasets demonstrate that pFL-ResFIM consistently outperforms state-of-the-art methods, validating its effectiveness. --- ### Lost in Aggregation: On a Fundamental Expressivity Limit of Message-Passing Graph Neural Networks Authors: Eran Rosenbluth Published: 2026-03-16 Categories: cs.LG, cs.CC arXiv: https://arxiv.org/abs/2603.14846v4 We define an information-complexity property for aggregation functions, capturing a vast range of practical aggregations, and prove that any Message-Passing Graph Neural Network (MP-GNN) model with such aggregations induces only a polynomial number of equivalence classes on all graphs - while the number of non-isomorphic graphs is super-exponential (in number of vertices). Adding a familiar perspective, we observe that merely 2 iterations of Color Refinement (CR) induce at least an exponential number of equivalence classes, making the aforementioned MP-GNNs relatively infinitely weaker. Previous studies state that sum-aggregation MP-GNNs match full CR however they consider a weak, 'non-uniform', notion of distinguishing-power where each graph size may require a different MP-GNN to distinguish graphs up to that size. Our results concern both distinguishing between non-equivariant vertices and distinguishing between non-isomorphic graphs. --- ### Lost in Aggregation: On a Fundamental Expressivity Limit of Message-Passing Graph Neural Networks Authors: Eran Rosenbluth Published: 2026-03-16 Categories: cs.LG, cs.CC arXiv: https://arxiv.org/abs/2603.14846v3 We define an information-complexity property for aggregation functions, capturing a vast range of practical aggregations, and prove that any Message-Passing Graph Neural Network (MP-GNN) model with such aggregations induces only a polynomial number of equivalence classes on all graphs - while the number of non-isomorphic graphs is super-exponential (in number of vertices). Adding a familiar perspective, we observe that merely 2 iterations of Color Refinement (CR) induce at least an exponential number of equivalence classes, making the aforementioned MP-GNNs relatively infinitely weaker. Previous studies state that sum-aggregation MP-GNNs match full CR however they consider a weak, 'non-uniform', notion of distinguishing-power where each graph size may require a different MP-GNN to distinguish graphs up to that size. Our results concern both distinguishing between non-equivariant vertices and distinguishing between non-isomorphic graphs. --- ### Integrating Weather Foundation Model and Satellite to Enable Fine-Grained Solar Irradiance Forecasting Authors: Ziqing Ma, Kai Ying, Xinyue Gu, Tian Zhou, Tianyu Zhu, Haifan Zhang, Peisong Niu, Zheng Wang, Cong Bai, Liang Sun Published: 2026-03-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.14845v3 Accurate day-ahead solar irradiance forecasting is essential for integrating solar energy into the power grid. However, it remains challenging due to the pronounced diurnal cycle and inherently complex cloud dynamics. Current methods either lack fine-scale resolution (e.g., numerical weather prediction, weather foundation models) or degrade at longer lead times (e.g., satellite extrapolation). We propose Baguan-solar, a two-stage multimodal framework that fuses forecasts from Baguan, a global weather foundation model, with high-resolution geostationary satellite imagery to produce 24-hour irradiance forecasts at kilometer scale. Its decoupled two-stage design first forecasts day-night continuous intermediates (e.g., cloud cover) and then infers irradiance, while its modality fusion jointly preserves fine-scale cloud structures from satellite and large-scale constraints from Baguan forecasts. Evaluated over East Asia using CLDAS as ground truth, Baguan-solar outperforms strong baselines (including ECMWF IFS, vanilla Baguan, and SolarSeer), reducing RMSE by 16.08% and better resolving cloud-induced transients. An operational deployment of Baguan-solar has supported solar power forecasting in an eastern province in China, since July 2025. Our code is accessible at https://github.com/DAMO-DI-ML/Baguan-solar.git. --- ### ContiGuard: A Framework for Continual Toxicity Detection Against Evolving Evasive Perturbations Authors: Hankun Kang, Xin Miao, Jianhao Chen, Jintao Wen, Mayi Xu, Weiyu Zhang, Wenpeng Lu, Tieyun Qian Published: 2026-03-16 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.14843v1 Toxicity detection mitigates the dissemination of toxic content (e.g., hateful comments, posts, and messages within online social actions) to safeguard a healthy online social environment. However, malicious users persistently develop evasive perturbations to disguise toxic content and evade detectors. Traditional detectors or methods are static over time and are inadequate in addressing these evolving evasion tactics. Thus, continual learning emerges as a logical approach to dynamically update detection ability against evolving perturbations. Nevertheless, disparities across perturbations hinder the detector's continual learning on perturbed text. More importantly, perturbation-induced noises distort semantics to degrade comprehension and also impair critical feature learning to render detection sensitive to perturbations. These amplify the challenge of continual learning against evolving perturbations. In this work, we present ContiGuard, the first framework tailored for continual learning of the detector on time-evolving perturbed text (termed continual toxicity detection) to enable the detector to continually update capability and maintain sustained resilience against evolving perturbations. Specifically, to boost the comprehension, we present an LLM-powered semantic enriching strategy, where we dynamically incorporate possible meaning and toxicity-related clues excavated by LLM into the perturbed text to improve the comprehension. To mitigate non-critical features and amplify critical ones, we propose a discriminability-driven feature learning strategy, where we strengthen discriminative features while suppressing the less-discriminative ones to shape a robust classification boundary for detection... --- ### Real-Time Driver Safety Scoring Through Inverse Crash Probability Modeling Authors: Joyjit Roy, Samaresh Kumar Singh, Sushanta Das, Mojtaba Bahramgiri Published: 2026-03-16 Categories: cs.LG, cs.AI, cs.DC, cs.ET arXiv: https://arxiv.org/abs/2603.14841v4 Road crashes remain a leading cause of preventable fatalities. Existing prediction models predominantly produce binary outcomes, which offer limited actionable insights for realtime driver feedback. These approaches often lack continuous risk quantification, interpretability, and explicit consideration of vulnerable road users (VRUs), such as pedestrians and cyclists. This research introduces SafeDriver-IQ, a framework that transforms binary crash classifiers into continuous 0-100 safety scores by combining national crash statistics with naturalistic driving data from autonomous vehicles. The framework fuses National Highway Traffic Safety Administration (NHTSA) crash records with Waymo Open Motion Dataset scenarios, engineers domain-informed features, and incorporates a calibration layer grounded in transportation safety literature. Evaluation across 15 complementary analyses indicates that the framework reliably differentiates high-risk from low-risk driving conditions with strong discriminative performance. Findings further reveal that 87% of crashes involve multiple co-occurring risk factors, with non-linear compounding effects that increase the risk to 4.5x baseline. SafeDriver-IQ delivers proactive, explainable safety intelligence relevant to advanced driver-assistance systems (ADAS), fleet management, and urban infrastructure planning. Beyond the specific application, the inverse modeling paradigm is domain-agnostic. Any binary risk classifier can be converted into a continuous, explainable safety-scoring system using the same pipeline without retraining. This framework shifts the focus from reactive crash counting to real-time risk prevention. --- ### Real-Time Driver Safety Scoring Through Inverse Crash Probability Modeling Authors: Joyjit Roy, Samaresh Kumar Singh, Sushanta Das Published: 2026-03-16 Categories: cs.LG, cs.AI, cs.DC, cs.ET arXiv: https://arxiv.org/abs/2603.14841v3 Road crashes remain a leading cause of preventable fatalities. Existing prediction models predominantly produce binary outcomes, which offer limited actionable insights for real-time driver feedback. These approaches often lack continuous risk quantification, interpretability, and explicit consideration of vulnerable road users (VRUs), such as pedestrians and cyclists. This research introduces SafeDriver-IQ, a framework that transforms binary crash classifiers into continuous 0-100 safety scores by combining national crash statistics with naturalistic driving data from autonomous vehicles. The framework fuses National Highway Traffic Safety Administration (NHTSA) crash records with Waymo Open Motion Dataset scenarios, engineers domain-informed features, and incorporates a calibration layer grounded in transportation safety literature. Evaluation across 15 complementary analyses indicates that the framework reliably differentiates high-risk from low-risk driving conditions with strong discriminative performance. Findings further reveal that 87% of crashes involve multiple co-occurring risk factors, with non-linear compounding effects that increase the risk to 4.5x baseline. SafeDriver-IQ delivers proactive, explainable safety intelligence relevant to advanced driver-assistance systems (ADAS), fleet management, and urban infrastructure planning. Beyond the specific application, the inverse modeling paradigm is domain-agnostic. Any binary risk classifier can be converted into a continuous, explainable safety-scoring system using the same pipeline without retraining. This framework shifts the focus from reactive crash counting to real-time risk prevention. --- ### The Impact of Ideological Discourses in RAG: A Case Study with COVID-19 Treatments Authors: Elmira Salari, Maria Claudia Nunes Delfino, Hazem Amamou, José Victor de Souza, Shruti Kshirsagar, Alan Davoust, Anderson Avila Published: 2026-03-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.14838v1 This paper studies the impact of retrieved ideological texts on the outputs of large language models (LLMs). While interest in understanding ideology in LLMs has recently increased, little attention has been given to this issue in the context of Retrieval-Augmented Generation (RAG). To fill this gap, we design an external knowledge source based on ideological loaded texts about COVID-19 treatments. Our corpus is based on 1,117 academic articles representing discourses about controversial and endorsed treatments for the disease. We propose a corpus linguistics framework, based on Lexical Multidimensional Analysis (LMDA), to identify the ideologies within the corpus. LLMs are tasked to answer questions derived from three identified ideological dimensions, and two types of contextual prompts are adopted: the first comprises the user question and ideological texts; and the second contains the question, ideological texts, and LMDA descriptions. Ideological alignment between reference ideological texts and LLMs' responses is assessed using cosine similarity for lexical and semantic representations. Results demonstrate that LLMs' responses based on ideological retrieved texts are more aligned with the ideology encountered in the external knowledge, with the enhanced prompt further influencing LLMs' outputs. Our findings highlight the importance of identifying ideological discourses within the RAG framework in order to mitigate not just unintended ideological bias, but also the risks of malicious manipulation of such models. --- ### DamageArbiter: A Multimodal Arbitration Framework for Disaster Damage Assessment from Street-View Imagery Authors: Yifan Yang, Lei Zou, Wenjing Gong, Kani Fu, Zongrong Li, Siqin Wang, Bing Zhou, Heng Cai, Hao Tian Published: 2026-03-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14837v2 Analyzing street-view imagery with computer vision models offers a promising approach for rapid, hyperlocal disaster damage assessment, but existing approaches typically rely on black-box pre-trained vision models, which lack interpretability and reliability. This study proposes DamageArbiter, a multimodal disagreement-driven arbitration framework designed to improve the accuracy and reliability of street-view-based damage assessment. DamageArbiter leverages the complementary strengths of unimodal and multimodal models and employs a lightweight logistic regression meta-classifier to arbitrate cases in which model predictions disagree. Using 2,556 post-disaster street-view images, paired with manually generated or large language model (LLM)-generated text descriptions, we systematically compared DamageArbiter with fine-tuned unimodal (image-only and text-only) models and CLIP-based multimodal models in terms of classification performance and overconfidence errors. Results show that DamageArbiter improved accuracy to 75.85% and the Matthews correlation coefficient (MCC) to 0.6188, compared with the best-performing text-only baseline (63.07% accuracy, 0.4126 MCC), image-only baseline (74.33% accuracy, 0.5947 MCC), and CLIP baseline (74.22% accuracy, 0.5915 MCC). The overconfidence analysis further reveals that DamageArbiter substantially reduced the overconfidence error from 70.58% for the best-performing baseline, the image-only ViT model, to 16.45%. Overall, this study demonstrates that accuracy alone is insufficient for evaluating disaster damage classification models and highlights the importance of measuring overconfidence errors as part of model reliability assessment. DamageArbiter thus offers a more reliable framework for rapid, hyperlocal disaster damage assessment from street-view imagery. --- ### Ablate and Rescue: A Causal Analysis of Residual Stream Hyper-Connections Authors: William Peng, Josheev Rai, Kevin Tseng, Siwei Wang, Sean Wu Published: 2026-03-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.14833v1 Multi-stream transformer architectures have recently been proposed as a promising direction for managing representation collapse and the vanishing gradient problem for residual connections, yet their internal mechanisms remain unexplored. In particular, the recently introduced Manifold-Constrained Hyper-Connections (mHC) architecture posits multiple residual streams with constrained interaction, but lacks in-depth mechanistic analysis. We present the first open-source mHC language model (https://huggingface.co/wgpeng/mhc-780m) and analyze the multiple-stream architecture with a suite of representation-level metrics and causal interventions to probe how parallel streams encode and utilize information. Specifically, we introduce a systematic stream ablation-and-rescue framework that enables direct causal comparison of residual streams during inference. Through targeted pairwise interventions and controlled recovery experiments, we distinguish functional redundancy from asymmetric utilization and reveal how information is distributed across streams beyond what is observable from representational similarity alone. --- ### Halfway to 3D: Ensembling 2.5D and 3D Models for Robust COVID-19 CT Diagnosis Authors: Tuan-Anh Yang, Bao V. Q. Bui, Chanh-Quang Vo-Van, Truong-Son Hy Published: 2026-03-16 Categories: eess.IV, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.14832v2 We propose a deep learning framework for COVID-19 detection and disease classification from chest CT scans that integrates both 2.5D and 3D representations to capture complementary slice-level and volumetric information. The 2.5D branch processes multi-view CT slices (axial, coronal, sagittal) using a DINOv3 vision transformer to extract robust visual features, while the 3D branch employs a ResNet-18 architecture to model volumetric context and is pretrained with Variance Risk Extrapolation (VREx) followed by supervised contrastive learning to improve cross-source robustness. Predictions from both branches are combined through logit-level ensemble inference. Experiments on the PHAROS-AIF-MIH benchmark demonstrate the effectiveness of the proposed approach: for binary COVID-19 detection, the ensemble achieves 94.48% accuracy and a 0.9426 Macro F1-score, outperforming both individual models, while for multi-class disease classification the 2.5D DINOv3 model achieves the best performance with 79.35% accuracy and a 0.7497 Macro F1-score. These results highlight the benefit of combining pretrained slice-based representations with volumetric modeling for robust multi-source medical imaging analysis. Code is available at https://github.com/HySonLab/PHAROS-AIF-MIH --- ### Neural Networks as Local-to-Global Computations Authors: Vicente Bosca, Robert Ghrist Published: 2026-03-16 Categories: math.AT, cs.LG, math.DS arXiv: https://arxiv.org/abs/2603.14831v3 We construct a cellular sheaf from any feedforward ReLU neural network by placing one vertex for each intermediate quantity in the forward pass and encoding each computational step - affine transformation, activation, output - as a restriction map on an edge. The restricted coboundary operator on the free coordinates is unitriangular, so its determinant is $1$ and the restricted Laplacian is positive definite for every activation pattern. It follows that the relative cohomology vanishes and the forward pass output is the unique harmonic extension of the boundary data. The sheaf heat equation converges exponentially to this output despite the state-dependent switching introduced by piecewise linear activations. Unlike the forward pass, the heat equation propagates information bidirectionally across layers, enabling pinned neurons that impose constraints in both directions, training through local discrepancy minimization without a backward pass, and per-edge diagnostics that decompose network behavior by layer and operation type. We validate the framework experimentally on small synthetic tasks, confirming the convergence theorems and demonstrating that sheaf-based training, while not yet competitive with stochastic gradient descent, obeys quantitative scaling laws predicted by the theory. --- ### Dataset Distillation Efficiently Encodes Low-Dimensional Representations from Gradient-Based Learning of Non-Linear Tasks Authors: Yuri Kinoshita, Naoki Nishikawa, Taro Toyoizumi Published: 2026-03-16 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2603.14830v3 Dataset distillation, a training-aware data compression technique, has recently attracted increasing attention as an effective tool for mitigating costs of optimization and data storage. However, progress remains largely empirical. Mechanisms underlying the extraction of task-relevant information from the training process and the efficient encoding of such information into synthetic data points remain elusive. In this paper, we theoretically analyze practical algorithms of dataset distillation applied to the gradient-based training of two-layer neural networks with width $L$. By focusing on a non-linear task structure called multi-index model, we prove that the low-dimensional structure of the problem is efficiently encoded into the resulting distilled data. This dataset reproduces a model with high generalization ability for a required memory complexity of $\tildeΘ$$(r^2d+L)$, where $d$ and $r$ are the input and intrinsic dimensions of the task. To the best of our knowledge, this is one of the first theoretical works that include a specific task structure, leverage its intrinsic dimensionality to quantify the compression rate and study dataset distillation implemented solely via gradient-based algorithms. --- ### SemanticFace: Semantic Facial Action Estimation via Semantic Distillation in Interpretable Space Authors: Zejian Kang, Kai Zheng, Yuanchen Fei, Wentao Yang, Hongyuan Zou, Xiangru Huang Published: 2026-03-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14827v2 Facial action estimation from a single image is often formulated as predicting or fitting parameters in compact expression spaces, which lack explicit semantic interpretability. However, many practical applications, such as avatar control and human-computer interaction, require interpretable facial actions that correspond to meaningful muscle movements. In this work, we propose SemanticFace, a framework for facial action estimation in the interpretable ARKit blendshape space that reformulates coefficient prediction as structured semantic reasoning. SemanticFace adopts a two-stage semantic distillation paradigm: it first derives structured semantic supervision from ground-truth ARKit coefficients and then distills this knowledge into a multimodal large language model to predict interpretable facial action coefficients from images. Extensive experiments demonstrate that language-aligned semantic supervision improves both coefficient accuracy and perceptual consistency, while enabling strong cross-identity generalization and robustness to large domain shifts, including cartoon faces. --- ### Two Birds, One Projection: Harmonizing Safety and Utility in LVLMs via Inference-time Feature Projection Authors: Yewon Han, Yumin Seol, EunGyung Kong, Minsoo Jo, Taesup Kim Published: 2026-03-16 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.14825v1 Existing jailbreak defence frameworks for Large Vision-Language Models often suffer from a safety utility tradeoff, where strengthening safety inadvertently degrades performance on general visual-grounded reasoning tasks. In this work, we investigate whether safety and utility are inherently antagonistic objectives. We focus on a modality induced bias direction consistently observed across datasets, which arises from suboptimal coupling between the Large Language Model backbone and visual encoders. We further demonstrate that this direction undermines performance on both tasks. Leveraging this insight, we propose Two Birds, One Projection, an efficient inference time jailbreak defence that projects cross-modal features onto the null space of the identified bias direction to remove the corresponding components. Requiring only a single forward pass, our method effectively breaks the conventional tradeoff, simultaneously improving both safety and utility across diverse benchmarks. --- ### Planning as Goal Recognition: Deriving Heuristics from Intention Models -- Extended Version Authors: Giacomo Rosa, Jean Honorio, Nir Lipovetzky, Sebastian Sardina Published: 2026-03-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.14824v2 Classical planning aims to find a sequence of actions, a plan, that maps a starting state into one of the goal states. If a trajectory appears to be leading to the goal, should we prioritise exploring it? Seminal work in goal recognition (GR) has defined GR in terms of a classical planning problem, adopting classical solvers and heuristics to recognise plans. We come full circle, and study the adoption and properties of GR-derived heuristics for seeking solutions to classical planning problems. We propose a new divergence-based framework for assessing goal intention, which informs a new class of efficiently-computable heuristics. As a proof of concept, we derive two such heuristics, and show that they can already yield improvements for top-scoring classical planners. Our work provides foundational knowledge for understanding and deriving probabilistic intention-based heuristics for planning. --- ### RadarXFormer: Robust Object Detection via Cross-Dimension Fusion of 4D Radar Spectra and Images for Autonomous Driving Authors: Yue Sun, Yeqiang Qian, Zhe Wang, Tianhui Li, Chunxiang Wang, Ming Yang Published: 2026-03-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14822v1 Reliable perception is essential for autonomous driving systems to operate safely under diverse real-world traffic conditions. However, camera- and LiDAR-based perception systems suffer from performance degradation under adverse weather and lighting conditions, limiting their robustness and large-scale deployment in intelligent transportation systems. Radar-vision fusion provides a promising alternative by combining the environmental robustness and cost efficiency of millimeter-wave (mmWave) radar with the rich semantic information captured by cameras. Nevertheless, conventional 3D radar measurements lack height resolution and remain highly sparse, while emerging 4D mmWave radar introduces elevation information but also brings challenges such as signal noise and large data volume. To address these issues, this paper proposes RadarXFormer, a 3D object detection framework that enables efficient cross-modal fusion between 4D radar spectra and RGB images. Instead of relying on sparse radar point clouds, RadarXFormer directly leverages raw radar spectra and constructs an efficient 3D representation that reduces data volume while preserving complete 3D spatial information. The "X" highlights the proposed cross-dimension (3D-2D) fusion mechanism, in which multi-scale 3D spherical radar feature cubes are fused with complementary 2D image feature maps. Experiments on the K-Radar dataset demonstrate improved detection accuracy and robustness under challenging conditions while maintaining real-time inference capability. --- ### RAZOR: Ratio-Aware Layer Editing for Targeted Unlearning in Vision Transformers and Diffusion Models Authors: Ravi Ranjan, Utkarsh Grover, Xiaomin Lin, Agoritsa Polyzou Published: 2026-03-16 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.14819v1 Transformer based diffusion and vision-language models have achieved remarkable success; yet, efficiently removing undesirable or sensitive information without retraining remains a central challenge for model safety and compliance. We introduce Ratio-Aware Zero/One-step Optimized Retentive unlearning (RAZOR), a lightweight, model-agnostic unlearning framework that generalizes forgetting updates to coordinated multi-layer and multi-head edits within transformer backbones. RAZOR identifies the most important layers and attention heads by measuring how much they contribute to forgetting the target data while preserving useful knowledge. Then, it updates these parts of the model using a carefully regularized rule to avoid harming overall performance. The set of edited components grows gradually, ensuring precise unlearning without over-editing or damaging unrelated capabilities. We evaluate RAZOR on CLIP, Stable Diffusion, and vision-language models (VLMs) using widely adopted unlearning benchmarks covering identity, style, and object erasure tasks. Our results show that RAZOR achieves highly accurate and stable forgetting, even under quantization. This approach offers stronger retention and better efficiency than prior methods. Notably, it also operates significant faster than conventional techniques. These results demonstrate that RAZOR is a practical and scalable solution for safe, adaptive unlearning in transformer-based vision models. ---