# Research Papers — 2026-03 · bundle page 102 of 243 > Full-text markdown of papers #5051–5100 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/102 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/101.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/103.md) ### CoVerRL: Breaking the Consensus Trap in Label-Free Reasoning via Generator-Verifier Co-Evolution Authors: Teng Pan, Yuchen Yan, Zixuan Wang, Ruiqing Zhang, Guiyang Hou, Wenqi Zhang, Weiming Lu, Jun Xiao, Yongliang Shen Published: 2026-03-18 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.17775v2 Label-free reinforcement learning enables large language models to improve reasoning capabilities without ground-truth supervision, typically by treating majority-voted answers as pseudo-labels. However, we identify a critical failure mode: as training maximizes self-consistency, output diversity collapses, causing the model to confidently reinforce systematic errors that evade detection. We term this the consensus trap. To escape it, we propose CoVerRL, a framework where a single model alternates between generator and verifier roles, with each capability bootstrapping the other. Majority voting provides noisy but informative supervision for training the verifier, while the improving verifier progressively filters self-consistent errors from pseudo-labels. This co-evolution creates a virtuous cycle that maintains high reward accuracy throughout training. Experiments across Qwen and Llama model families demonstrate that CoVerRL outperforms label-free baselines by 4.7-5.9% on mathematical reasoning benchmarks. Moreover, self-verification accuracy improves from around 55% to over 85%, confirming that both capabilities genuinely co-evolve. --- ### Attention Sinks Induce Gradient Sinks: Massive Activations as Gradient Regulators in Transformers Authors: Yihong Chen, Zhouchen Lin, Quanming Yao Published: 2026-03-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.17771v2 Attention sinks and massive activations are recurring and closely related phenomena in Transformer models. Existing explanations have largely focused on the forward pass, yet in pre-norm Transformers, large residual-stream norms play only an indirect forward role because sublayers operate on normalized inputs. We study this relationship from the perspective of backpropagation. Empirically and theoretically, we show that under causal masking, attention sinks can induce pronounced gradient concentration, which we term gradient sinks. Since the RMSNorm Jacobian attenuates gradients roughly in inverse proportion to input norm, massive activations can be understood as adaptive regulators of this localized gradient pressure during training. This interpretation predicts that attenuating sink-induced gradients should weaken massive activations. We test this prediction with V-scale, a modification that adjusts backpropagated gradients on the value path. In V-scale models, attention sinks are preserved, whereas massive activations are suppressed. These results identify gradient sinks as a backward-pass counterpart of attention sinks, and massive activations as an adaptive RMSNorm-mediated response that attenuates the resulting localized training pressure. Our code is available at https://anonymous.4open.science/r/GradientSinkCode-B309. --- ### Modeling Overlapped Speech with Shuffles Authors: Matthew Wiesner, Samuele Cornell, Alexander Polok, Lucas Ondel Yang, Lukáš Burget, Sanjeev Khudanpur Published: 2026-03-18 Categories: cs.SD, cs.CL, cs.LG, eess.AS arXiv: https://arxiv.org/abs/2603.17769v1 We propose to model parallel streams of data, such as overlapped speech, using shuffles. Specifically, this paper shows how the shuffle product and partial order finite-state automata (FSAs) can be used for alignment and speaker-attributed transcription of overlapped speech. We train using the total score on these FSAs as a loss function, marginalizing over all possible serializations of overlapping sequences at subword, word, and phrase levels. To reduce graph size, we impose temporal constraints by constructing partial order FSAs. We address speaker attribution by modeling (token, speaker) tuples directly. Viterbi alignment through the shuffle product FSA directly enables one-pass alignment. We evaluate performance on synthetic LibriSpeech overlaps. To our knowledge, this is the first algorithm that enables single-pass alignment of multi-talker recordings. All algorithms are implemented using k2 / Icefall. --- ### Facial Movement Dynamics Reveal Workload During Complex Multitasking Authors: Carter Sale, Melissa N. Stolar, Gaurav Patil, Michael J. Gostelow, Julia Wallier, Margaret C. Macpherson, Jan-Louis Kruger, Mark Dras, Simon G. Hosking, Rachel W. Kallen, Michael J. Richardson Published: 2026-03-18 Categories: cs.HC, cs.CV arXiv: https://arxiv.org/abs/2603.17767v1 Real-time cognitive workload monitoring is crucial in safety-critical environments, yet established measures are intrusive, expensive, or lack temporal resolution. We tested whether facial movement dynamics from a standard webcam could provide a low-cost alternative. Seventy-two participants completed a multitasking simulation (OpenMATB) under varied load while facial keypoints were tracked via OpenPose. Linear kinematics (velocity, acceleration, displacement) and recurrence quantification features were extracted. Increasing load altered dynamics across timescales: movement magnitudes rose, temporal organisation fragmented then reorganised into complex patterns, and eye-head coordination weakened. Random forest classifiers trained on pose kinematics outperformed task performance metrics (85% vs. 55% accuracy) but generalised poorly across participants (43% vs. 33% chance). Participant-specific models reached 50% accuracy with minimal calibration (2 minutes per condition), improving continuously to 73% without plateau. Facial movement dynamics sensitively track workload with brief calibration, enabling adaptive interfaces using commodity cameras, though individual differences limit cross-participant generalisation. --- ### Grounded Multimodal Retrieval-Augmented Drafting of Radiology Impressions Using Case-Based Similarity Search Authors: Himadri S Samanta Published: 2026-03-18 Categories: q-bio.QM, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2603.17765v1 Automated radiology report generation has gained increasing attention with the rise of deep learning and large language models. However, fully generative approaches often suffer from hallucinations and lack clinical grounding, limiting their reliability in real-world workflows. In this study, we propose a multimodal retrieval-augmented generation (RAG) system for grounded drafting of chest radiograph impressions. The system combines contrastive image-text embeddings, case-based similarity retrieval, and citation-constrained draft generation to ensure factual alignment with historical radiology reports. A curated subset of the MIMIC-CXR dataset was used to construct a multimodal retrieval database. Image embeddings were generated using CLIP encoders, while textual embeddings were derived from structured impression sections. A fusion similarity framework was implemented using FAISS indexing for scalable nearest-neighbor retrieval. Retrieved cases were used to construct grounded prompts for draft impression generation, with safety mechanisms enforcing citation coverage and confidence-based refusal. Experimental results demonstrate that multimodal fusion significantly improves retrieval performance compared to image-only retrieval, achieving Recall@5 above 0.95 on clinically relevant findings. The grounded drafting pipeline produces interpretable outputs with explicit citation traceability, enabling improved trustworthiness compared to conventional generative approaches. This work highlights the potential of retrieval-augmented multimodal systems for reliable clinical decision support and radiology workflow augmentation --- ### Evidence Packing for Cross-Domain Image Deepfake Detection with LVLMs Authors: Yuxin Liu, Fei Wang, Kun Li, Yiqi Nie, Junjie Chen, Zhangling Duan, Zhaohong Jia Published: 2026-03-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17761v1 Image Deepfake Detection (IDD) separates manipulated images from authentic ones by spotting artifacts of synthesis or tampering. Although large vision-language models (LVLMs) offer strong image understanding, adapting them to IDD often demands costly fine-tuning and generalizes poorly to diverse, evolving manipulations. We propose the Semantic Consistent Evidence Pack (SCEP), a training-free LVLM framework that replaces whole-image inference with evidence-driven reasoning. SCEP mines a compact set of suspicious patch tokens that best reveal manipulation cues. It uses the vision encoder's CLS token as a global reference, clusters patch features into coherent groups, and scores patches with a fused metric combining CLS-guided semantic mismatch with frequency-and noise-based anomalies. To cover dispersed traces and avoid redundancy, SCEP samples a few high-confidence patches per cluster and applies grid-based NMS, producing an evidence pack that conditions a frozen LVLM for prediction. Experiments on diverse benchmarks show SCEP outperforms strong baselines without LVLM fine-tuning. --- ### Harm or Humor: A Multimodal, Multilingual Benchmark for Overt and Covert Harmful Humor Authors: Ahmed Sharshar, Hosam Elgendy, Saad El Dine Ahmed, Yasser Rohaim, Yuxia Wang Published: 2026-03-18 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.17759v2 Dark humor often relies on subtle cultural nuances and implicit cues that require contextual reasoning to interpret, posing safety challenges that current static benchmarks fail to capture. To address this, we introduce a novel multimodal, multilingual benchmark for detecting and understanding harmful and offensive humor. Our manually curated dataset comprises 3,000 texts and 6,000 images in English and Arabic, alongside 1,200 videos that span English, Arabic, and language-independent (universal) contexts. Unlike standard toxicity datasets, we enforce a strict annotation guideline: distinguishing Safe jokes from Harmful ones, with the latter further classified into Explicit (overt) and Implicit (Covert) categories to probe deep reasoning. We systematically evaluate state-of-the-art (SOTA) open and closed-source models across all modalities. Our findings reveal that closed-source models significantly outperform open-source ones, with a notable difference in performance between the English and Arabic languages in both, underscoring the critical need for culturally grounded, reasoning-aware safety alignment. Warning: this paper contains example data that may be offensive, harmful, or biased. --- ### PC-CrossDiff: Point-Cluster Dual-Level Cross-Modal Differential Attention for Unified 3D Referring and Segmentation Authors: Wenbin Tan, Jiawen Lin, Fangyong Wang, Yuan Xie, Yong Xie, Yachao Zhang, Yanyun Qu Published: 2026-03-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17753v1 3D Visual Grounding (3DVG) aims to localize the referent of natural language referring expressions through two core tasks: Referring Expression Comprehension (3DREC) and Segmentation (3DRES). While existing methods achieve high accuracy in simple, single-object scenes, they suffer from severe performance degradation in complex, multi-object scenes that are common in real-world settings, hindering practical deployment. Existing methods face two key challenges in complex, multi-object scenes: inadequate parsing of implicit localization cues critical for disambiguating visually similar objects, and ineffective suppression of dynamic spatial interference from co-occurring objects, resulting in degraded grounding accuracy. To address these challenges, we propose PC-CrossDiff, a unified dual-task framework with a dual-level cross-modal differential attention architecture for 3DREC and 3DRES. Specifically, the framework introduces: (i) Point-Level Differential Attention (PLDA) modules that apply bidirectional differential attention between text and point clouds, adaptively extracting implicit localization cues via learnable weights to improve discriminative representation; (ii) Cluster-Level Differential Attention (CLDA) modules that establish a hierarchical attention mechanism to adaptively enhance localization-relevant spatial relationships while suppressing ambiguous or irrelevant spatial relations through a localization-aware differential attention block. Our method achieves state-of-the-art performance on the ScanRefer, NR3D, and SR3D benchmarks. Notably, on the Implicit subsets of ScanRefer, it improves the Overall@0.50 score by +10.16% for the 3DREC task, highlighting its strong ability to parse implicit spatial cues. --- ### Towards Infinitely Long Neural Simulations: Self-Refining Neural Surrogate Models for Dynamical Systems Authors: Qi Liu, Laure Zanna, Joan Bruna Published: 2026-03-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.17750v1 Recent advances in autoregressive neural surrogate models have enabled orders-of-magnitude speedups in simulating dynamical systems. However, autoregressive models are generally prone to distribution drift: compounding errors in autoregressive rollouts that severely degrade generation quality over long time horizons. Existing work attempts to address this issue by implicitly leveraging the inherent trade-off between short-time accuracy and long-time consistency through hyperparameter tuning. In this work, we introduce a unifying mathematical framework that makes this tradeoff explicit, formalizing and generalizing hyperparameter-based strategies in existing approaches. Within this framework, we propose a robust, hyperparameter-free model implemented as a conditional diffusion model that balances short-time fidelity with long-time consistency by construction. Our model, Self-refining Neural Surrogate model (SNS), can be implemented as a standalone model that refines its own autoregressive outputs or as a complementary model to existing neural surrogates to ensure long-time consistency. We also demonstrate the numerical feasibility of SNS through high-fidelity simulations of complex dynamical systems over arbitrarily long time horizons. --- ### Concept-to-Pixel: Prompt-Free Universal Medical Image Segmentation Authors: Haoyun Chen, Fenghe Tang, Wenxin Ma, Shaohua Kevin Zhou Published: 2026-03-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17746v1 Universal medical image segmentation seeks to use a single foundational model to handle diverse tasks across multiple imaging modalities. However, existing approaches often rely heavily on manual visual prompts or retrieved reference images, which limits their automation and robustness. In addition, naive joint training across modalities often fails to address large domain shifts. To address these limitations, we propose Concept-to-Pixel (C2P), a novel prompt-free universal segmentation framework. C2P explicitly separates anatomical knowledge into two components: Geometric and Semantic representations. It leverages Multimodal Large Language Models (MLLMs) to distill abstract, high-level medical concepts into learnable Semantic Tokens and introduces explicitly supervised Geometric Tokens to enforce universal physical and structural constraints. These disentangled tokens interact deeply with image features to generate input-specific dynamic kernels for precise mask prediction. Furthermore, we introduce a Geometry-Aware Inference Consensus mechanism, which utilizes the model's predicted geometric constraints to assess prediction reliability and suppress outliers. Extensive experiments and analysis on a unified benchmark comprising eight diverse datasets across seven modalities demonstrate the significant superiority of our jointly trained approach, compared to universe- or single-model approaches. Remarkably, our unified model demonstrates strong generalization, achieving impressive results not only on zero-shot tasks involving unseen cases but also in cross-modal transfers across similar tasks. Code is available at: https://github.com/Yundi218/Concept-to-Pixel --- ### Embedding World Knowledge into Tabular Models: Towards Best Practices for Embedding Pipeline Design Authors: Oksana Kolomenko, Ricardo Knauer, Erik Rodner Published: 2026-03-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.17737v1 Embeddings are a powerful way to enrich data-driven machine learning models with the world knowledge of large language models (LLMs). Yet, there is limited evidence on how to design effective LLM-based embedding pipelines for tabular prediction. In this work, we systematically benchmark 256 pipeline configurations, covering 8 preprocessing strategies, 16 embedding models, and 2 downstream models. Our results show that it strongly depends on the specific pipeline design whether incorporating the prior knowledge of LLMs improves the predictive performance. In general, concatenating embeddings tends to outperform replacing the original columns with embeddings. Larger embedding models tend to yield better results, while public leaderboard rankings and model popularity are poor performance indicators. Finally, gradient boosting decision trees tend to be strong downstream models. Our findings provide researchers and practitioners with guidance for building more effective embedding pipelines for tabular prediction tasks. --- ### TAPESTRY: From Geometry to Appearance via Consistent Turntable Videos Authors: Yan Zeng, Haoran Jiang, Kaixin Yao, Qixuan Zhang, Longwen Zhang, Lan Xu, Jingyi Yu Published: 2026-03-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17735v1 Automatically generating photorealistic and self-consistent appearances for untextured 3D models is a critical challenge in digital content creation. The advancement of large-scale video generation models offers a natural approach: directly synthesizing 360-degree turntable videos (TTVs), which can serve not only as high-quality dynamic previews but also as an intermediate representation to drive texture synthesis and neural rendering. However, existing general-purpose video diffusion models struggle to maintain strict geometric consistency and appearance stability across the full range of views, making their outputs ill-suited for high-quality 3D reconstruction. To this end, we introduce TAPESTRY, a framework for generating high-fidelity TTVs conditioned on explicit 3D geometry. We reframe the 3D appearance generation task as a geometry-conditioned video diffusion problem: given a 3D mesh, we first render and encode multi-modal geometric features to constrain the video generation process with pixel-level precision, thereby enabling the creation of high-quality and consistent TTVs. Building upon this, we also design a method for downstream reconstruction tasks from the TTV input, featuring a multi-stage pipeline with 3D-Aware Inpainting. By rotating the model and performing a context-aware secondary generation, this pipeline effectively completes self-occluded regions to achieve full surface coverage. The videos generated by TAPESTRY are not only high-quality dynamic previews but also serve as a reliable, 3D-aware intermediate representation that can be seamlessly back-projected into UV textures or used to supervise neural rendering methods like 3DGS. This enables the automated creation of production-ready, complete 3D assets from untextured meshes. Experimental results demonstrate that our method outperforms existing approaches in both video consistency and final reconstruction quality. --- ### SARE: Sample-wise Adaptive Reasoning for Training-free Fine-grained Visual Recognition Authors: Jingxiao Yang, DaLin He, Miao Pan, Kaixiang Yao, Ge Su, Wenqi Zhang, Yifeng Hu, Tangwei Li, Yuke Li, Xuhong Zhang Published: 2026-03-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.17729v3 Recent advances in Large Vision-Language Models (LVLMs) have enabled training-free Fine-Grained Visual Recognition (FGVR). However, effectively exploiting LVLMs for FGVR remains challenging due to the inherent visual ambiguity of subordinate-level categories. Existing methods predominantly adopt either retrieval-oriented or reasoning-oriented paradigms to tackle this challenge, but both are constrained by two fundamental limitations:(1) They apply the same inference pipeline to all samples without accounting for uneven recognition difficulty, thereby leading to suboptimal accuracy and efficiency; (2) The lack of mechanisms to consolidate and reuse error-specific experience causes repeated failures on similar challenging cases. To address these limitations, we propose SARE, a Sample-wise Adaptive textbfREasoning framework for training-free FGVR. Specifically, SARE adopts a cascaded design that combines fast candidate retrieval with fine-grained reasoning, invoking the latter only when necessary. In the reasoning process, SARE incorporates a self-reflective experience mechanism that leverages past failures to provide transferable discriminative guidance during inference, without any parameter updates. Extensive experiments across 14 datasets substantiate that SARE achieves state-of-the-art performance while substantially reducing computational overhead. --- ### Predicting Trajectories of Long COVID in Adult Women: The Critical Role of Causal Disentanglement Authors: Jing Wang, Jie Shen, Yiming Luo, Amar Sra, Qiaomin Xie, Jeremy C. Weiss Published: 2026-03-18 Categories: cs.LG, cs.CY arXiv: https://arxiv.org/abs/2603.17722v1 Early prediction of Post-Acute Sequelae of SARS-CoV-2 severity is a critical challenge for women's health, particularly given the diagnostic overlap between PASC and common hormonal transitions such as menopause. Identifying and accounting for these confounding factors is essential for accurate long-term trajectory prediction. We conducted a retrospective study of 1,155 women (mean age 61) from the NIH RECOVER dataset. By integrating static clinical profiles with four weeks of longitudinal wearable data (monitoring cardiac activity and sleep), we developed a causal network based on a Large Language Model to predict future PASC scores. Our framework achieved a precision of 86.7\% in clinical severity prediction. Our causal attribution analysis demonstrate the model's ability to differentiate between active pathology and baseline noise: direct indicators such as breathlessness and malaise reached maximum saliency (1.00), while confounding factors like menopause and diabetes were successfully suppressed with saliency scores below 0.27. --- ### DiffVP: Differential Visual Semantic Prompting for LLM-Based CT Report Generation Authors: Yuhe Tian, Kun Zhang, Haoran Ma, Rui Yan, Yingtai Li, Rongsheng Wang, Shaohua Kevin Zhou Published: 2026-03-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17718v1 While large language models (LLMs) have advanced CT report generation, existing methods typically encode 3D volumes holistically, failing to distinguish informative cues from redundant anatomical background. Inspired by radiological cognitive subtraction, we propose Differential Visual Prompting (DiffVP), which conditions report generation on explicit, high-level semantic scan-to-reference differences rather than solely on absolute visual features. DiffVP employs a hierarchical difference extractor to capture complementary global and local semantic discrepancies into a shared latent space, along with a difference-to-prompt generator that transforms these signals into learnable visual prefix tokens for LLM conditioning. These difference prompts serve as structured conditioning signals that implicitly suppress invariant anatomy while amplifying diagnostically relevant visual evidence, thereby facilitating accurate report generation without explicit lesion localization. On two large-scale benchmarks, DiffVP consistently outperforms prior methods, improving the average BLEU-1-4 by +10.98 and +4.36, respectively, and further boosts clinical efficacy on RadGenome-ChestCT (F1 score 0.421). All codes will be released at https://github.com/ArielTYH/DiffVP/. --- ### Machine Learning for Network Attacks Classification and Statistical Evaluation of Adversarial Learning Methodologies for Synthetic Data Generation Authors: Iakovos-Christos Zarkadis, Christos Douligeris Published: 2026-03-18 Categories: cs.CR, cs.AI, stat.AP, stat.ML arXiv: https://arxiv.org/abs/2603.17717v4 Supervised detection of network attacks has always been a critical part of network intrusion detection systems (NIDS). Nowadays, in a pivotal time for artificial intelligence (AI), with even more sophisticated attacks that utilize advanced techniques, such as generative artificial intelligence (GenAI) and reinforcement learning, it has become a vital component if we wish to protect our personal data, which are scattered across the web. In this paper, we address two tasks, in the first unified multi-modal NIDS dataset, which incorporates flow-level data, packet payload information and temporal contextual features, from the reprocessed CIC-IDS-2017, CIC-IoT-2023, UNSW-NB15 and CIC-DDoS-2019, with the same feature space. In the first task we use machine learning (ML) algorithms, with stratified cross validation, in order to prevent network attacks, with stability and reliability. In the second task we use adversarial learning algorithms to generate synthetic data, compare them with the real ones and evaluate their fidelity, utility and privacy using the SDV framework, f-divergences, distinguishability and non-parametric statistical tests. The findings provide stable ML models for intrusion detection and generative models with high fidelity and utility, by combining the Synthetic Data Vault framework, the TRTS and TSTR tests, with non-parametric statistical tests and f-divergence measures. --- ### Eye image segmentation using visual and concept prompts with Segment Anything Model 3 (SAM3) Authors: Diederick C. Niehorster, Marcus Nyström Published: 2026-03-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.17715v1 Previous work has reported that vision foundation models show promising zero-shot performance in eye image segmentation. Here we examine whether the latest iteration of the Segment Anything Model, SAM3, offers better eye image segmentation performance than SAM2, and explore the performance of its new concept (text) prompting mode. Eye image segmentation performance was evaluated using diverse datasets encompassing both high-resolution high-quality videos from a lab environment and the TEyeD dataset consisting of challenging eye videos acquired in the wild. Results show that in most cases SAM3 with either visual or concept prompts did not perform better than SAM2, for both lab and in-the-wild datasets. Since SAM2 not only performed better but was also faster, we conclude that SAM2 remains the best option for eye image segmentation. We provide our adaptation of SAM3's codebase that allows processing videos of arbitrary duration. --- ### From Virtual Environments to Real-World Trials: Emerging Trends in Autonomous Driving Authors: A. Humnabadkar, A. Sikdar, B. Cave, H. Zhang, N. Bessis, A. Behera Published: 2026-03-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.17714v2 Autonomous driving technologies have achieved significant advances in recent years, yet their real-world deployment remains constrained by data scarcity, safety requirements, and the need for generalization across diverse environments. In response, synthetic data and virtual environments have emerged as powerful enablers, offering scalable, controllable, and richly annotated scenarios for training and evaluation. This survey presents a comprehensive review of recent developments at the intersection of autonomous driving, simulation technologies, and synthetic datasets. We organize the landscape across three core dimensions: (i) the use of synthetic data for perception and planning, (ii) digital twin-based simulation for system validation, and (iii) domain adaptation strategies bridging synthetic and real-world data. We also highlight the role of vision-language models and simulation realism in enhancing scene understanding and generalization. A detailed taxonomy of datasets, tools, and simulation platforms is provided, alongside an analysis of trends in benchmark design. Finally, we discuss critical challenges and open research directions, including Sim2Real transfer, scalable safety validation, cooperative autonomy, and simulation-driven policy learning, that must be addressed to accelerate the path toward safe, generalizable, and globally deployable autonomous driving systems. --- ### AERR-Nav: Adaptive Exploration-Recovery-Reminiscing Strategy for Zero-Shot Object Navigation Authors: Jingzhi Huang, Junkai Huang, Haoyang Yang, Haoang Li, Yi Wang Published: 2026-03-18 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2603.17712v1 Zero-Shot Object Navigation (ZSON) in unknown multi-floor environments presents a significant challenge. Recent methods, mostly based on semantic value greedy waypoint selection, spatial topology-enhanced memory, and Multimodal Large Language Model (MLLM) as a decision-making framework, have led to improvements. However, these architectures struggle to balance exploration and exploitation for ZSON when encountering unseen environments, especially in multi-floor settings, such as robots getting stuck at narrow intersections, endlessly wandering, or failing to find stair entrances. To overcome these challenges, we propose AERR-Nav, a Zero-Shot Object Navigation framework that dynamically adjusts its state based on the robot's environment. Specifically, AERR-Nav has the following two key advantages: (1) An Adaptive Exploration-Recovery-Reminiscing Strategy, enables robots to dynamically transition between three states, facilitating specialized responses to diverse navigation scenarios. (2) An Adaptive Exploration State featuring Fast and Slow-Thinking modes helps robots better balance exploration, exploitation, and higher-level reasoning based on evolving environmental information. Extensive experiments on the HM3D and MP3D benchmarks demonstrate that our AERR-Nav achieves state-of-the-art performance among zero-shot methods. Comprehensive ablation studies further validate the efficacy of our proposed strategy and modules. --- ### Parameter-Efficient Modality-Balanced Symmetric Fusion for Multimodal Remote Sensing Semantic Segmentation Authors: Haocheng Li, Juepeng Zheng, Shuangxi Miao, Ruibo Lu, Guosheng Cai, Haohuan Fu, Jianxi Huang Published: 2026-03-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17705v1 Multimodal remote sensing semantic segmentation enhances scene interpretation by exploiting complementary physical cues from heterogeneous data. Although pretrained Vision Foundation Models (VFMs) provide strong general-purpose representations, adapting them to multimodal tasks often incurs substantial computational overhead and is prone to modality imbalance, where the contribution of auxiliary modalities is suppressed during optimization. To address these challenges, we propose MoBaNet, a parameter-efficient and modality-balanced symmetric fusion framework. Built upon a largely frozen VFM backbone, MoBaNet adopts a symmetric dual-stream architecture to preserve generalizable representations while minimizing the number of trainable parameters. Specifically, we design a Cross-modal Prompt-Injected Adapter (CPIA) to enable deep semantic interaction by generating shared prompts and injecting them into bottleneck adapters under the frozen backbone. To obtain compact and discriminative multimodal representations for decoding, we further introduce a Difference-Guided Gated Fusion Module (DGFM), which adaptively fuses paired stage features by explicitly leveraging cross-modal discrepancy to guide feature selection. Furthermore, we propose a Modality-Conditional Random Masking (MCRM) strategy to mitigate modality imbalance by masking one modality only during training and imposing hard-pixel auxiliary supervision on modality-specific branches. Extensive experiments on the ISPRS Vaihingen and Potsdam benchmarks demonstrate that MoBaNet achieves state-of-the-art performance with significantly fewer trainable parameters than full fine-tuning, validating its effectiveness for robust and balanced multimodal fusion. The source code in this work is available at https://github.com/sauryeo/MoBaNet. --- ### DancingBox: A Lightweight MoCap System for Character Animation from Physical Proxies Authors: Haocheng Yuan, Adrien Bousseau, Hao Pan, Lei Zhong, Changjian Li Published: 2026-03-18 Categories: cs.GR, cs.CV, cs.HC arXiv: https://arxiv.org/abs/2603.17704v1 Creating compelling 3D character animations typically requires either expert use of professional software or expensive motion capture systems operated by skilled actors. We present DancingBox, a lightweight, vision-based system that makes motion capture accessible to novices by reimagining the process as digital puppetry. Instead of tracking precise human motions, DancingBox captures the approximate movements of everyday objects manipulated by users with a single webcam. These coarse proxy motions are then refined into realistic character animations by conditioning a generative motion model on bounding-box representations, enriched with human motion priors learned from large-scale datasets. To overcome the lack of paired proxy-animation data, we synthesize training pairs by converting existing motion capture sequences into proxy representations. A user study demonstrates that DancingBox enables intuitive and creative character animation using diverse proxies, from plush toys to bananas, lowering the barrier to entry for novice animators. --- ### MALLES: A Multi-agent LLMs-based Economic Sandbox with Consumer Preference Alignment Authors: Yusen Wu, Yiran Liu, Xiaotie Deng Published: 2026-03-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.17694v1 In the real economy, modern decision-making is fundamentally challenged by high-dimensional, multimodal environments, which are further complicated by agent heterogeneity and combinatorial data sparsity. This paper introduces a Multi-Agent Large Language Model-based Economic Sandbox (MALLES), leveraging the inherent generalization capabilities of large-sacle models to establish a unified simulation framework applicable to cross-domain and cross-category scenarios. Central to our approach is a preference learning paradigm in which LLMs are economically aligned via post-training on extensive, heterogeneous transaction records across diverse product categories. This methodology enables the models to internalize and transfer latent consumer preference patterns, thereby mitigating the data sparsity issues prevalent in individual categories. To enhance simulation stability, we implement a mean-field mechanism designed to model the dynamic interactions between the product environment and customer populations, effectively stabilizing sampling processes within high-dimensional decision spaces. Furthermore, we propose a multi-agent discussion framework wherein specialized agents collaboratively process extensive product information. This architecture distributes cognitive load to alleviate single-agent attention bottlenecks and captures critical decision factors through structured dialogue. Experiments demonstrate that our framework achieves significant improvements in product selection accuracy, purchase quantity prediction, and simulation stability compared to existing economic and financial LLM simulation baselines. Our results substantiate the potential of large language models as a foundational pillar for high-fidelity, scalable decision simulation and latter analysis in the real economy based on foundational database. --- ### Learning Transferable Temporal Primitives for Video Reasoning via Synthetic Videos Authors: Songtao Jiang, Sibo Song, Chenyi Zhou, Yuan Wang, Ruizhe Chen, Tongkun Guan, Ruilin Luo, Yan Zhang, Zhihang Tang, Yuchong Sun, Hang Zhang, Zhibo Yang et al. Published: 2026-03-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17693v1 The transition from image to video understanding requires vision-language models (VLMs) to shift from recognizing static patterns to reasoning over temporal dynamics such as motion trajectories, speed changes, and state transitions. Yet current post-training methods fall short due to two critical limitations: (1) existing datasets often lack temporal-centricity, where answers can be inferred from isolated keyframes rather than requiring holistic temporal integration; and (2) training data generated by proprietary models contains systematic errors in fundamental temporal perception, such as confusing motion directions or misjudging speeds. We introduce SynRL, a post-training framework that teaches models temporal primitives, the fundamental building blocks of temporal understanding including direction, speed, and state tracking. Our key insight is that these abstract primitives, learned from programmatically generated synthetic videos, transfer effectively to real-world scenarios. We decompose temporal understanding into short-term perceptual primitives (speed, direction) and long-term cognitive primitives, constructing 7.7K CoT and 7K RL samples with ground-truth frame-level annotations through code-based video generation. Despite training on simple geometric shapes, SynRL achieves substantial improvements across 15 benchmarks spanning temporal grounding, complex reasoning, and general video understanding. Remarkably, our 7.7K synthetic CoT samples outperform Video-R1 with 165K real-world samples. We attribute this to fundamental temporal skills, such as tracking frame by frame changes and comparing velocity, that transfer effectively from abstract synthetic patterns to complex real-world scenarios. This establishes a new paradigm for video post-training: video temporal learning through carefully designed synthetic data provides a more cost efficient scaling path. --- ### Can Blindfolded LLMs Still Trade? An Anonymization-First Framework for Portfolio Optimization Authors: Joohyoung Jeon, Hongchul Lee Published: 2026-03-18 Categories: cs.LG, cs.AI, q-fin.CP, q-fin.PM arXiv: https://arxiv.org/abs/2603.17692v1 For LLM trading agents to be genuinely trustworthy, they must demonstrate understanding of market dynamics rather than exploitation of memorized ticker associations. Building responsible multi-agent systems demands rigorous signal validation: proving that predictions reflect legitimate patterns, not pre-trained recall. We address two sources of spurious performance: memorization bias from ticker-specific pre-training, and survivorship bias from flawed backtesting. Our approach is to blindfold the agents--anonymizing all identifiers--and verify whether meaningful signals persist. BlindTrade anonymizes tickers and company names, and four LLM agents output scores along with reasoning. We construct a GNN graph from reasoning embeddings and trade using PPO-DSR policy. On 2025 YTD (through 2025-08-01), we achieved Sharpe 1.40 +/- 0.22 across 20 seeds and validated signal legitimacy through negative control experiments. To assess robustness beyond a single OOS window, we additionally evaluate an extended period (2024--2025), revealing market-regime dependency: the policy excels in volatile conditions but shows reduced alpha in trending bull markets. --- ### Stochastic set-valued optimization and its application to robust learning Authors: Tommaso Giovannelli, Jingfu Tan, Luis Nunes Vicente Published: 2026-03-18 Categories: math.OC, cs.LG arXiv: https://arxiv.org/abs/2603.17691v1 In this paper, we develop a stochastic set-valued optimization (SVO) framework tailored for robust machine learning. In the SVO setting, each decision variable is mapped to a set of objective values, and optimality is defined via set relations. We focus on SVO problems with hyperbox sets, which can be reformulated as multi-objective optimization (MOO) problems with finitely many objectives and serve as a foundation for representing or approximating more general mapped sets. Two special cases of hyperbox-valued optimization (HVO) are interval-valued (IVO) and rectangle-valued (RVO) optimization. We construct stochastic IVO/RVO formulations that incorporate subquantiles and superquantiles into the objective functions of the MOO reformulations, providing a new characterization for subquantiles. These formulations provide interpretable trade-offs by capturing both lower- and upper-tail behaviors of loss distributions, thereby going beyond standard empirical risk minimization and classical robust models. To solve the resulting multi-objective problems, we adopt stochastic multi-gradient algorithms and select a Pareto knee solution. In numerical experiments, the proposed algorithms with this selection strategy exhibit improved robustness and reduced variability across test replications under distributional shift compared with empirical risk minimization, while maintaining competitive accuracy. --- ### Objective Mispricing Detection for Shortlisting Undervalued Football Players via Market Dynamics and News Signals Authors: Chinenye Omejieke, Shuyao Chen, Xia Cui Published: 2026-03-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.17687v1 We present a practical, reproducible framework for identifying undervalued football players grounded in objective mispricing. Instead of relying on subjective expert labels, we estimate an expected market value from structured data (historical market dynamics, biographical and contract features, transfer history) and compare it to the observed valuation to define mispricing. We then assess whether news-derived Natural Language Processing (NLP) features (i.e., sentiment statistics and semantic embeddings from football articles) complement market signals for shortlisting undervalued players. Using a chronological (leakage-aware) evaluation, gradient-boosted regression explains a large share of the variance in log-transformed market value. For undervaluation shortlisting, ROC-AUC-based ablations show that market dynamics are the primary signal, while NLP features provide consistent, secondary gains that improve robustness and interpretability. SHAP analyses suggest the dominance of market trends and age, with news-derived volatility cues amplifying signals in high-uncertainty regimes. The proposed pipeline is designed for decision support in scouting workflows, emphasizing ranking/shortlisting over hard classification thresholds, and includes a concise reproducibility and ethics statement. --- ### Flow Matching Policy Optimization with Mirror Descent and Entropy Constraints Authors: Ting Gao, Stavros Orfanoudakis, Nan Lin, Winnie Daamen, Serge Hoogendoorn, Elvin Isufi Published: 2026-03-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.17685v3 Balancing policy expressiveness with the exploration-exploitation trade-off is a core challenge in online Reinforcement Learning (RL). While Stochastic Differential Equation (SDE)-based diffusion policies can represent complex, multimodal action distributions, they suffer from two critical limitations: their stochastic reverse processes render entropy intractable (necessitating heuristic exploration), and computing policy gradients through long denoising chains is expensive and unstable. In this work, we show that ODE-based flow matching inherently resolves these issues by enabling both simulation-free policy optimization and tractable entropy computation. Building on this, we introduce Flow Matching Policy Optimization with Mirror Descent and Entropy Constraints (FMER). Our framework exploits this insight in three ways. First, we theoretically establish that minimizing an advantage-weighted conditional flow matching loss acts as a simulation-free surrogate for policy mirror descent. This steers the velocity field toward high-value regions while entirely avoiding backpropagation through the ODE solver. Second, we derive an analytic entropy objective that corrects for the density distortion caused by the $\tanh$ transformation (mapping an unbounded latent space to bounded actions), thereby facilitating principled maximum-entropy optimization. Finally, we dynamically tune the mirror descent temperature based on the effective sample size to enforce a robust trust region during training. Empirical evaluations demonstrate that FMER achieves superior performance on the challenging sparse-reward FrankaKitchen environment, while maintaining competitive results across standard dense-reward MuJoCo benchmarks. --- ### Does YOLO Really Need to See Every Training Image in Every Epoch? Authors: Xingxing Xie, Jiahua Dong, Junwei Han, Gong Cheng Published: 2026-03-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17684v1 YOLO detectors are known for their fast inference speed, yet training them remains unexpectedly time-consuming due to their exhaustive pipeline that processes every training image in every epoch, even when many images have already been sufficiently learned. This stands in clear contrast to the efficiency suggested by the ``You Only Look Once'' philosophy. This naturally raises an important question: \textit{Does YOLO really need to see every training image in every epoch?} To explore this, we propose an Anti-Forgetting Sampling Strategy (AFSS) that dynamically determines which images should be used and which can be skipped during each epoch, allowing the detector to learn more effectively and efficiently. Specifically, AFSS measures the learning sufficiency of each training image as the minimum of its detection recall and precision, and dynamically categorizes training images into easy, medium, or hard levels accordingly. Easy training images are sparsely resampled during training in a continuous review manner, with priority given to those that have not been used for a long time to reduce redundancy and prevent forgetting. Moderate training images are partially selected, prioritizing recently unused ones and randomly choosing the rest from unselected images to ensure coverage and prevent forgetting. Hard training images are fully sampled in every epoch to ensure sufficient learning. The learning sufficiency of each training image is periodically updated, enabling detectors to adaptively shift its focus toward the informative training images over time while progressively discarding redundant ones. On widely used natural image detection benchmarks (MS COCO 2017 and PASCAL VOC 2007) and remote sensing detection datasets (DOTA-v1.0 and DIOR-R), AFSS achieves more than $1.43\times$ training speedup for YOLO-series detectors while also improving accuracy. --- ### Sensi: Learn One Thing at a Time -- Curriculum-Based Test-Time Learning for LLM Game Agents Authors: Mohsen Arjmandi Published: 2026-03-18 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.17683v1 Large language model (LLM) agents deployed in unknown environments must learn task structure at test time, but current approaches require thousands of interactions to form useful hypotheses. We present Sensi, an LLM agent architecture for the ARC-AGI-3 game-playing challenge that introduces structured test-time learning through three mechanisms: (1) a two-player architecture separating perception from action, (2) a curriculum-based learning system managed by an external state machine, and (3) a database-as-control-plane that makes the agents context window programmatically steerable. We further introduce an LLM-as-judge component with dynamically generated evaluation rubrics to determine when the agent has learned enough about one topic to advance to the next. We report results across two iterations: Sensi v1 solves 2 game levels using the two-player architecture alone, while Sensi v2 adds curriculum learning and solves 0 levels - but completes its entire learning curriculum in approximately 32 action attempts, achieving 50-94x greater sample efficiency than comparable systems that require 1600-3000 attempts. We precisely diagnose the failure mode as a self-consistent hallucination cascade originating in the perception layer, demonstrating that the architectural bottleneck has shifted from learning efficiency to perceptual grounding - a more tractable problem. --- ### Murmurations, Mestre--Nagao sums, and Convolutional Neural Networks for elliptic curves Authors: Joanna Bieri, Edgar Costa, Alyson Deines, Kyu-Hwan Lee, David Lowry-Duda, Thomas Oliver, Yidi Qi, Tamara Veenstra Published: 2026-03-18 Categories: math.NT, stat.ML arXiv: https://arxiv.org/abs/2603.17681v2 We apply one-dimensional convolutional neural networks to the Frobenius traces of elliptic curves over $\mathbb{Q}$ and evaluate and interpret their predictive capacity. In keeping with similar experiments by Kazalicki--Vlah, Bujanović--Kazalicki--Novak, and Pozdnyakov, we observe high accuracy predictions for the analytic rank across a range of conductors. We interpret the prediction using saliency curves and explore the interesting interplay between saliency, murmurations and Mestre--Nagao sums. --- ### Murmurations, Mestre--Nagao sums, and Convolutional Neural Networks for elliptic curves Authors: Joanna Bieri, Edgar Costa, Alyson Deines, Kyu-Hwan Lee, David Lowry-Duda, Thomas Oliver, Yidi Qi, Tamara Veenstra Published: 2026-03-18 Categories: math.NT, stat.ML arXiv: https://arxiv.org/abs/2603.17681v1 We apply one-dimensional convolutional neural networks to the Frobenius traces of elliptic curves over $\mathbb{Q}$ and evaluate and interpret their predictive capacity. In keeping with similar experiments by Kazalicki--Vlah, Bujanović--Kazalicki--Novak, and Pozdnyakov, we observe high accuracy predictions for the analytic rank across a range of conductors. We interpret the prediction using saliency curves and explore the interesting interplay between murmurations and Mestre--Nagao sums, the details of which vary with the conductor and the (predicted) rank. --- ### WeatherReasonSeg: A Benchmark for Weather-Aware Reasoning Segmentation in Visual Language Models Authors: Wanjun Du, Zifeng Yuan, Tingting Chen, Fucai Ke, Beibei Lin, Shunli Zhang Published: 2026-03-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.17680v1 Existing vision-language models (VLMs) have demonstrated impressive performance in reasoning-based segmentation. However, current benchmarks are primarily constructed from high-quality images captured under idealized conditions. This raises a critical question: when visual cues are severely degraded by adverse weather conditions such as rain, snow, or fog, can VLMs sustain reliable reasoning segmentation capabilities? In response to this challenge, we introduce WeatherReasonSeg, a benchmark designed to evaluate VLM performance in reasoning-based segmentation under adverse weather conditions. It consists of two complementary components. First, we construct a controllable reasoning dataset by applying synthetic weather with varying severity levels to existing segmentation datasets, enabling fine-grained robustness analysis. Second, to capture real-world complexity, we curate a real-world adverse-weather reasoning segmentation dataset with semantically consistent queries generated via mask-guided LLM prompting. We further broaden the evaluation scope across five reasoning dimensions, including functionality, application scenarios, structural attributes, interactions, and requirement matching. Extensive experiments across diverse VLMs reveal two key findings: (1) VLM performance degrades monotonically with increasing weather severity, and (2) different weather types induce distinct vulnerability patterns. We hope WeatherReasonSeg will serve as a foundation for advancing robust, weather-aware reasoning. --- ### Illumination-Aware Contactless Fingerprint Spoof Detection via Paired Flash-Non-Flash Imaging Authors: Roja Sahoo, Anoop Namboodiri Published: 2026-03-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17679v2 Contactless fingerprint recognition enables hygienic and convenient biometric authentication but poses new challenges for spoof detection due to the absence of physical contact and traditional liveness cues. Most existing methods rely on single-image acquisition and appearance-based features, which often generalize poorly across devices, capture conditions, and spoof materials. In this work, we study paired flash-non-flash contactless fingerprint acquisition as a lightweight active sensing mechanism for spoof detection. Through a preliminary empirical analysis, we show that flash illumination accentuates material- and structure-dependent properties, including ridge visibility, subsurface scattering, micro-geometry, and surface oils, while non-flash images provide a baseline appearance context. We analyze lighting-induced differences using interpretable metrics such as inter-channel correlation, specular reflection characteristics, texture realism, and differential imaging. These complementary features help discriminate genuine fingerprints from printed, digital, and molded presentation attacks. We further examine the limitations of paired acquisition, including sensitivity to imaging settings, dataset scale, and emerging high-fidelity spoofs. Our findings demonstrate the potential of illumination-aware analysis to improve robustness and interpretability in contactless fingerprint presentation attack detection, motivating future work on paired acquisition and physics-informed feature design. Code is available in the repository. --- ### Adaptive Guidance for Retrieval-Augmented Masked Diffusion Models Authors: Jaemin Kim, Jong Chul Ye Published: 2026-03-18 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.17677v2 Retrieval-Augmented Generation (RAG) improves factual grounding by incorporating external knowledge into language model generation. However, when retrieved context is noisy, unreliable, or inconsistent with the model's parametric knowledge, it introduces retrieval-prior conflicts that can degrade generation quality. While this problem has been studied in autoregressive language models, it remains largely unexplored in diffusion-based language models, where the iterative denoising process introduces unique challenges for integrating retrieved context. In this work, we propose Adaptive Retrieval-Augmented Masked Diffusion (ARAM), a training-free adaptive guidance framework for Masked Diffusion Models (MDMs) in RAG settings. ARAM dynamically calibrates the guidance scale during denoising according to the Signal-to-Noise Ratio (SNR) of the distributional shift induced by retrieved context. Intuitively, the model strengthens guidance when the retrieved context provides reliable corrective evidence and suppresses it when the contextual signal is noisy or non-supportive. Extensive experiments on multiple knowledge-intensive QA benchmarks show that ARAM improves overall QA performance over competitive RAG baselines. --- ### Inhibitory normalization of error signals improves learning in neural circuits Authors: Roy Henha Eyono, Daniel Levenstein, Arna Ghosh, Jonathan Cornford, Blake Richards Published: 2026-03-18 Categories: q-bio.NC, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.17676v1 Normalization is a critical operation in neural circuits. In the brain, there is evidence that normalization is implemented via inhibitory interneurons and allows neural populations to adjust to changes in the distribution of their inputs. In artificial neural networks (ANNs), normalization is used to improve learning in tasks that involve complex input distributions. However, it is unclear whether inhibition-mediated normalization in biological neural circuits also improves learning. Here, we explore this possibility using ANNs with separate excitatory and inhibitory populations trained on an image recognition task with variable luminosity. We find that inhibition-mediated normalization does not improve learning if normalization is applied only during inference. However, when this normalization is extended to include back-propagated errors, performance improves significantly. These results suggest that if inhibition-mediated normalization improves learning in the brain, it additionally requires the normalization of learning signals. --- ### DeepCORO-CLIP: A Multi-View Foundation Model for Comprehensive Coronary Angiography Video-Text Analysis and External Validation Authors: Sarra Harrabi, Yichen Wu, Geoffrey H. Tison, Minhaj Ansari, Milos Vukadinovic, David Ouyang, Joshua P. Barrios, Jacques Delfrate, Robert Avram Published: 2026-03-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17675v1 Coronary angiography is the reference standard for evaluating coronary artery disease, yet visual interpretation remains variable between readers. Existing artificial intelligence methods typically analyze single frames or projections and focus mainly on stenosis, limiting comprehensive coronary assessment. We present DeepCORO-CLIP, a multi-view foundation model trained with video-text contrastive learning on 203,808 angiography videos from 28,117 patients across 32,473 studies at the Montreal Heart Institute and externally validated on 4,249 studies from the University of California, San Francisco. DeepCORO-CLIP integrates multiple projections with attention-based pooling for study-level assessment across diagnostic, prognostic, and disease progression tasks. For significant stenosis detection, the model achieved an AUROC of 0.888 internally and 0.89 on external validation. Mean absolute error against core laboratory quantitative coronary angiography was 13.6%, lower than clinical reports at 19.0%. The model also performed strongly for chronic total occlusion, intracoronary thrombus, and coronary calcification detection. Transfer learning enabled prediction of one-year major adverse cardiovascular events with AUROC 0.79 and estimation of left ventricular ejection fraction with mean absolute error 7.3%. Embeddings also captured disease progression across serial examinations. With a mean inference time of 4.2 seconds in hospital deployment, DeepCORO-CLIP provides a foundation for automated coronary angiography interpretation at the point of care. Code, sample data, model weights, and deployment infrastructure are publicly released. --- ### Towards Reliable Local Security Agents: Verifiable Post-Training for Linux Privilege Escalation Authors: Philipp Normann, Andreas Happe, Jürgen Cito, Daniel Arp Published: 2026-03-18 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2603.17673v2 LLM agents are becoming increasingly important in the security domain, but leading systems are often closed-source, cloud-based, hard to reproduce or use with sensitive code. This creates a need for small, local models that can perform security tasks under strict resource constraints, though effective methods for developing them remain unexplored. In this paper, we address this gap by proposing a two-stage post-training recipe that turns a small local language model into a security agent. To this end, we focus on Linux privilege escalation as a representative setting to systematically study the training of local models, as the task is both automatically verifiable and requires multi-step interactive reasoning. Using an experimental setup that mitigates data leakage, we post-train a small 4B model in two stages: supervised fine-tuning on traces from procedural privilege-escalation environments, followed by reinforcement learning with verifiable rewards. On a held-out benchmark of 12 Linux privilege-escalation scenarios, supervised fine-tuning doubles the baseline success rate under a tight budget of 20 interaction rounds, and subsequent reinforcement learning training improves our model, PrivEsc-LLM 4B, to 93.3% success, behind only Claude Opus 4.7 at this budget. At the same time, the expected inference cost per successful escalation decreases by more than 80x. Our findings not only show that small local models can be adapted to complex security tasks, but also document the challenges involved, offering guidance for transferring this recipe to other settings. --- ### Few-Step Diffusion Sampling Through Instance-Aware Discretizations Authors: Liangyu Yuan, Ruoyu Wang, Tong Zhao, Dingwen Fu, Mingkun Lei, Beier Zhu, Chi Zhang Published: 2026-03-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17671v1 Diffusion and flow matching models generate high-fidelity data by simulating paths defined by Ordinary or Stochastic Differential Equations (ODEs/SDEs), starting from a tractable prior distribution. The probability flow ODE formulation enables the use of advanced numerical solvers to accelerate sampling. Orthogonal yet vital to solver design is the discretization strategy. While early approaches employed handcrafted heuristics and recent methods adopt optimization-based techniques, most existing strategies enforce a globally shared timestep schedule across all samples. This uniform treatment fails to account for instance-specific complexity in the generative process, potentially limiting performance. Motivated by controlled experiments on synthetic data, which reveals the suboptimality of global schedules under instance-specific dynamics, we propose an instance-aware discretization framework. Our method learns to adapt timestep allocations based on input-dependent priors, extending gradient-based discretization search to the conditional generative setting. Empirical results across diverse settings, including synthetic data, pixel-space diffusion, latent-space images and video flow matching models, demonstrate that our method consistently improves generation quality with marginal tuning cost compared to training and negligible inference overhead. --- ### FINER: MLLMs Hallucinate under Fine-grained Negative Queries Authors: Rui Xiao, Sanghwan Kim, Yongqin Xian, Zeynep Akata, Stephan Alaniz Published: 2026-03-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.17662v1 Multimodal large language models (MLLMs) struggle with hallucinations, particularly with fine-grained queries, a challenge underrepresented by existing benchmarks that focus on coarse image-related questions. We introduce FIne-grained NEgative queRies (FINER), alongside two benchmarks: FINER-CompreCap and FINER-DOCCI. Using FINER, we analyze hallucinations across four settings: multi-object, multi-attribute, multi-relation, and ``what'' questions. Our benchmarks reveal that MLLMs hallucinate when fine-grained mismatches co-occur with genuinely present elements in the image. To address this, we propose FINER-Tuning, leveraging Direct Preference Optimization (DPO) on FINER-inspired data. Finetuning four frontier MLLMs with FINER-Tuning yields up to 24.2\% gains (InternVL3.5-14B) on hallucinations from our benchmarks, while simultaneously improving performance on eight existing hallucination suites, and enhancing general multimodal capabilities across six benchmarks. Code, benchmark, and models are available at \href{https://explainableml.github.io/finer-project/}{https://explainableml.github.io/finer-project/}. --- ### Interpretable Cross-Domain Few-Shot Learning with Rectified Target-Domain Local Alignment Authors: Yaze Zhao, Yixiong Zou, Yuhua Li, Ruixuan Li Published: 2026-03-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.17655v2 Cross-Domain Few-Shot Learning (CDFSL) adapts models trained with large-scale general data (source domain) to downstream target domains with only scarce training data, where the research on vision-language models (e.g., CLIP) is still in the early stages. Typical downstream domains, such as medical diagnosis, require fine-grained visual cues for interpretable recognition, but we find that current fine-tuned CLIP models can hardly focus on these cues, albeit they can roughly focus on important regions in source domains. Although current works have demonstrated CLIP's shortcomings in capturing local subtle patterns, in this paper, we find that the domain gap and scarce training data further exacerbate such shortcomings, much more than that of holistic patterns, which we call the local misalignment problem in CLIP-based CDFSL. To address this problem, due to the lack of supervision in aligning local visual features and text semantics, we turn to self-supervision information. Inspired by the translation task, we propose the CC-CDFSL method with cycle consistency, which translates local visual features into text features and then translates them back into visual features (and vice versa), and constrains the original features close to the translated back features. To reduce the noise imported by richer information in the visual modality, we further propose a Semantic Anchor mechanism, which first augments visual features to provide a larger corpus for the text-to-image mapping, and then shrinks the image features to filter out irrelevant image-to-text mapping. Extensive experiments on various benchmarks, backbones, and fine-tuning methods show we can (1) effectively improve the local vision-language alignment, (2) enhance the interpretability of learned patterns and model decisions by visualizing patches, and (3) achieve state-of-the-art performance. --- ### VectorWorld: Efficient Streaming World Model via Diffusion Flow on Vector Graphs Authors: Chaokang Jiang, Desen Zhou, Jiuming Liu, Kevin Li Sun Published: 2026-03-18 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2603.17652v1 Closed-loop evaluation of autonomous-driving policies requires interactive simulation beyond log replay. However, existing generative world models often degrade in closed loop due to (i) history-free initialization that mismatches policy inputs, (ii) multi-step sampling latency that violates real-time budgets, and (iii) compounding kinematic infeasibility over long horizons. We propose VectorWorld, a streaming world model that incrementally generates ego-centric $64 \mathrm{m}\times 64\mathrm{m}$ lane--agent vector-graph tiles during rollout. VectorWorld aligns initialization with history-conditioned policies by producing a policy-compatible interaction state via a motion-aware gated VAE. It enables real-time outpainting via solver-free one-step masked completion with an edge-gated relational DiT trained with interval-conditioned MeanFlow and JVP-based large-step supervision. To stabilize long-horizon rollouts, we introduce $Δ$Sim, a physics-aligned non-ego (NPC) policy with hybrid discrete--continuous actions and differentiable kinematic logit shaping. On Waymo open motion and nuPlan, VectorWorld improves map-structure fidelity and initialization validity, and supports stable, real-time $1\mathrm{km}+$ closed-loop rollouts (\href{https://github.com/jiangchaokang/VectorWorld}{code}). --- ### Anchoring and Rescaling Attention for Semantically Coherent Inbetweening Authors: Tae Eun Choi, Sumin Shim, Junhyeok Kim, Seong Jae Hwang Published: 2026-03-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.17651v1 Generative inbetweening (GI) seeks to synthesize realistic intermediate frames between the first and last keyframes beyond mere interpolation. As sequences become sparser and motions larger, previous GI models struggle with inconsistent frames with unstable pacing and semantic misalignment. Since GI involves fixed endpoints and numerous plausible paths, this task requires additional guidance gained from the keyframes and text to specify the intended path. Thus, we give semantic and temporal guidance from the keyframes and text onto each intermediate frame through Keyframe-anchored Attention Bias. We also better enforce frame consistency with Rescaled Temporal RoPE, which allows self-attention to attend to keyframes more faithfully. TGI-Bench, the first benchmark specifically designed for text-conditioned GI evaluation, enables challenge-targeted evaluation to analyze GI models. Without additional training, our method achieves state-of-the-art frame consistency, semantic fidelity, and pace stability for both short and long sequences across diverse challenges. --- ### Part-Aware Open-Vocabulary 3D Affordance Grounding via Prototypical Semantic and Geometric Alignment Authors: Dongqiang Gou, Xuming He Published: 2026-03-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17647v1 Grounding natural language questions to functionally relevant regions in 3D objects -- termed language-driven 3D affordance grounding -- is essential for embodied intelligence and human-AI interaction. Existing methods, while progressing from label-based to language-driven approaches, still face challenges in open-vocabulary generalization, fine-grained geometric alignment, and part-level semantic consistency. To address these issues, we propose a novel two-stage cross-modal framework that enhances both semantic and geometric representations for open-vocabulary 3D affordance grounding. In the first stage, large language models generate part-aware instructions to recover missing semantics, enabling the model to link semantically similar affordances. In the second stage, we introduce two key components: Affordance Prototype Aggregation (APA), which captures cross-object geometric consistency for each affordance, and Intra-Object Relational Modeling (IORM), which refines geometric differentiation within objects to support precise semantic alignment. We validate the effectiveness of our method through extensive experiments on a newly introduced benchmark, as well as two existing benchmarks, demonstrating superior performance in comparison with existing methods. --- ### Automated Grammar-based Algebraic Multigrid Design With Evolutionary Algorithms Authors: Dinesh Parthasarathy, Wayne Mitchell, Arjun Gambhir, Harald Köstler, Ulrich Rüde Published: 2026-03-18 Categories: cs.CE, cs.AI, math.NA arXiv: https://arxiv.org/abs/2603.17641v1 Although multigrid is asymptotically optimal for solving many important partial differential equations, its efficiency relies heavily on the careful selection of the individual algorithmic components. In contrast to recent approaches that can optimize certain multigrid components using deep learning techniques, we adopt a complementary strategy, employing evolutionary algorithms to construct efficient multigrid cycles from proven algorithmic building blocks. Here, we will present its application to generate efficient algebraic multigrid methods with so-called \emph{flexible cycling}, that is, level-specific smoothing sequences and non-recursive cycling patterns. The search space with such non-standard cycles is intractable to navigate manually, and is generated using genetic programming (GP) guided by context-free grammars. Numerical experiments with the linear algebra library, \emph{hypre}, demonstrate the potential of these non-standard GP cycles to improve multigrid performance both as a solver and a preconditioner. --- ### VeriGrey: Greybox Agent Validation Authors: Yuntong Zhang, Sungmin Kang, Ruijie Meng, Marcel Böhme, Abhik Roychoudhury Published: 2026-03-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.17639v1 Agentic AI has been a topic of great interest recently. A Large Language Model (LLM) agent involves one or more LLMs in the back-end. In the front end, it conducts autonomous decision-making by combining the LLM outputs with results obtained by invoking several external tools. The autonomous interactions with the external environment introduce critical security risks. In this paper, we present a grey-box approach to explore diverse behaviors and uncover security risks in LLM agents. Our approach VeriGrey uses the sequence of tools invoked as a feedback function to drive the testing process. This helps uncover infrequent but dangerous tool invocations that cause unexpected agent behavior. As mutation operators in the testing process, we mutate prompts to design pernicious injection prompts. This is carefully accomplished by linking the task of the agent to an injection task, so that the injection task becomes a necessary step of completing the agent functionality. Comparing our approach with a black-box baseline on the well-known AgentDojo benchmark, VeriGrey achieves 33% additional efficacy in finding indirect prompt injection vulnerabilities with a GPT-4.1 back-end. We also conduct real-world case studies with the widely used coding agent Gemini CLI, and the well-known OpenClaw personal assistant. VeriGrey finds prompts inducing several attack scenarios that could not be identified by black-box approaches. In OpenClaw, by constructing a conversation agent which employs mutational fuzz testing as needed, VeriGrey is able to discover malicious skill variants from 10 malicious skills (with 10/10= 100% success rate on the Kimi-K2.5 LLM backend, and 9/10= 90% success rate on Opus 4.6 LLM backend). This demonstrates the value of a dynamic approach like VeriGrey to test agents, and to eventually lead to an agent assurance framework. --- ### DSS-GAN: Directional State Space GAN with Mamba backbone for Class-Conditional Image Synthesis Authors: Aleksander Ogonowski, Konrad Klimaszewski, Przemysław Rokita Published: 2026-03-18 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2603.17637v1 We present DSS-GAN, the first generative adversarial network to employ Mamba as a hierarchical generator backbone for noise-to-image synthesis. The central contribution is Directional Latent Routing (DLR), a novel conditioning mechanism that decomposes the latent vector into direction-specific subvectors, each jointly projected with a class embedding to produce a feature-wise affine modulation of the corresponding Mamba scan. Unlike conventional class conditioning that injects a global signal, DLR couples class identity and latent structure along distinct spatial axes of the feature map, applied consistently across all generative scales. DSS-GAN achieves improved FID, KID, and precision-recall scores compared to StyleGAN2-ADA across multiple tested datasets. Analysis of the latent space reveals that directional subvectors exhibit measurable specialization: perturbations along individual components produce structured, direction-correlated changes in the synthesized image. --- ### Atomic Trajectory Modeling with State Space Models for Biomolecular Dynamics Authors: Liang Shi, Jiarui Lu, Junqi Liu, Chence Shi, Zhi Yang, Jian Tang Published: 2026-03-18 Categories: q-bio.BM, cs.LG arXiv: https://arxiv.org/abs/2603.17633v1 Understanding the dynamic behavior of biomolecules is fundamental to elucidating biological function and facilitating drug discovery. While Molecular Dynamics (MD) simulations provide a rigorous physical basis for studying these dynamics, they remain computationally expensive for long timescales. Conversely, recent deep generative models accelerate conformation generation but are typically either failing to model temporal relationship or built only for monomeric proteins. To bridge this gap, we introduce ATMOS, a novel generative framework based on State Space Models (SSM) designed to generate atom-level MD trajectories for biomolecular systems. ATMOS integrates a Pairformer-based state transition mechanism to capture long-range temporal dependencies, with a diffusion-based module to decode trajectory frames in an autoregressive manner. ATMOS is trained across crystal structures from PDB and conformation trajectory from large-scale MD simulation datasets including mdCATH and MISATO. We demonstrate that ATMOS achieves state-of-the-art performance in generating conformation trajectories for both protein monomers and complex protein-ligand systems. By enabling efficient inference of atomic trajectory of motions, this work establishes a promising foundation for modeling biomolecular dynamics. --- ### Benchmarking Reinforcement Learning via Stochastic Converse Optimality: Generating Systems with Known Optimal Policies Authors: Sinan Ibrahim, Grégoire Ouerdane, Hadi Salloum, Henni Ouerdane, Stefan Streif, Pavel Osinenko Published: 2026-03-18 Categories: cs.LG, cs.AI, eess.SY, math.OC arXiv: https://arxiv.org/abs/2603.17631v1 The objective comparison of Reinforcement Learning (RL) algorithms is notoriously complex as outcomes and benchmarking of performances of different RL approaches are critically sensitive to environmental design, reward structures, and stochasticity inherent in both algorithmic learning and environmental dynamics. To manage this complexity, we introduce a rigorous benchmarking framework by extending converse optimality to discrete-time, control-affine, nonlinear systems with noise. Our framework provides necessary and sufficient conditions, under which a prescribed value function and policy are optimal for constructed systems, enabling the systematic generation of benchmark families via homotopy variations and randomized parameters. We validate it by automatically constructing diverse environments, demonstrating our framework's capacity for a controlled and comprehensive evaluation across algorithms. By assessing standard methods against a ground-truth optimum, our work delivers a reproducible foundation for precise and rigorous RL benchmarking. --- ### rSDNet: Unified Robust Neural Learning against Label Noise and Adversarial Attacks Authors: Suryasis Jana, Abhik Ghosh Published: 2026-03-18 Categories: stat.ML, cs.AI, cs.LG, stat.ME arXiv: https://arxiv.org/abs/2603.17628v1 Neural networks are central to modern artificial intelligence, yet their training remains highly sensitive to data contamination. Standard neural classifiers are trained by minimizing the categorical cross-entropy loss, corresponding to maximum likelihood estimation under a multinomial model. While statistically efficient under ideal conditions, this approach is highly vulnerable to contaminated observations including label noises corrupting supervision in the output space, and adversarial perturbations inducing worst-case deviations in the input space. In this paper, we propose a unified and statistically grounded framework for robust neural classification that addresses both forms of contamination within a single learning objective. We formulate neural network training as a minimum-divergence estimation problem and introduce rSDNet, a robust learning algorithm based on the general class of $S$-divergences. The resulting training objective inherits robustness properties from classical statistical estimation, automatically down-weighting aberrant observations through model probabilities. We establish essential population-level properties of rSDNet, including Fisher consistency, classification calibration implying Bayes optimality, and robustness guarantees under uniform label noise and infinitesimal feature contamination. Experiments on three benchmark image classification datasets show that rSDNet improves robustness to label corruption and adversarial attacks while maintaining competitive accuracy on clean data, Our results highlight minimum-divergence learning as a principled and effective framework for robust neural classification under heterogeneous data contamination. --- ### A Multi-Agent System for Building-Age Cohort Mapping to Support Urban Energy Planning Authors: Kundan Thota, Thorsten Schlachter, Veit Hagenmeyer Published: 2026-03-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17626v1 Determining the age distribution of the urban building stock is crucial for sustainable municipal heat planning and upgrade prioritization. However, existing approaches often rely on datasets gathered via sensors or remote sensing techniques, leaving inconsistencies and gaps in data. We present a multi-agent LLM system comprising three key agents, the Zensus agent, the OSM agent, and the Monument agent, that fuse data from heterogeneous sources. A data orchestrator and harmonizer geocodes and deduplicates building imprints. Using this fused ground truth, we introduce BuildingAgeCNN, a satellite-only classifier based on a ConvNeXt backbone augmented with a Feature Pyramid Network (FPN), CoordConv spatial channels, and Squeeze-and-Excitation (SE) blocks. Under spatial cross validation, BuildingAgeCNN attains an overall accuracy of 90.69% but a modest macro-F1 of 67.25%, reflecting strong class imbalance and persistent confusions between adjacent historical cohorts. To mitigate risk for planning applications, the address-to prediction pipeline includes calibrated confidence estimates and flags low-confidence cases for manual review. This multi-agent LLM system not only assists in gathering structured data but also helps energy demand planners optimize district-heating networks and target low-carbon sustainable energy systems. ---