# Research Papers — 2026-03 · bundle page 155 of 243 > Full-text markdown of papers #7701–7750 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/155 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/154.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/156.md) ### Multi-Agent Collaboration for Automated Design Exploration on High Performance Computing Systems Authors: Harshitha Menon, Charles F. Jekel, Kevin Korner, M. Giselle Fernandez-Godino, Brian Gunnarson, Nathan K. Brown, Michael Stees, Walter Nissen, Meir H. Shachar, Dane M. Sterbentz, William J. Schill, Yue Hao et al. Published: 2026-03-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.11515v2 Today's scientific challenges, from climate modeling to Inertial Confinement Fusion design to novel material design, require exploring huge design spaces. In order to enable high-impact scientific discovery, we need to scale up our ability to test hypotheses, generate results, and learn from them rapidly. We present MADA (Multi-Agent Design Assistant), a Large Language Model (LLM) powered multi-agent framework that coordinates specialized agents for complex design workflows. A Job Management Agent (JMA) launches and manages ensemble simulations on HPC systems, a Geometry Agent (GA) generates meshes, and an Inverse Design Agent (IDA) proposes new designs informed by simulation outcomes. While general purpose, we focus development and validation on Richtmyer--Meshkov Instability (RMI) suppression, a critical challenge in Inertial Confinement Fusion. We evaluate on two complementary settings: running a hydrodynamics simulations on HPC systems, and using a pre-trained machine learning surrogate for rapid design exploration. Our results demonstrate that the MADA system successfully executes iterative design refinement, automatically improving designs toward optimal RMI suppression with minimal manual intervention. Our framework reduces cumbersome manual workflow setup, and enables automated design exploration at scale. More broadly, it demonstrates a reusable pattern for coupling reasoning, simulation, specialized tools, and coordinated workflows to accelerate scientific discovery. --- ### Multi-Agent Collaboration for Automated Design Exploration on High Performance Computing Systems Authors: Harshitha Menon, Charles F. Jekel, Kevin Korner, Brian Gunnarson, Nathan K. Brown, Michael Stees, M. Giselle Fernandez-Godino, Walter Nissen, Meir H. Shachar, Dane M. Sterbentz, William J. Schill, Yue Hao et al. Published: 2026-03-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.11515v1 Today's scientific challenges, from climate modeling to Inertial Confinement Fusion design to novel material design, require exploring huge design spaces. In order to enable high-impact scientific discovery, we need to scale up our ability to test hypotheses, generate results, and learn from them rapidly. We present MADA (Multi-Agent Design Assistant), a Large Language Model (LLM) powered multi-agent framework that coordinates specialized agents for complex design workflows. A Job Management Agent (JMA) launches and manages ensemble simulations on HPC systems, a Geometry Agent (GA) generates meshes, and an Inverse Design Agent (IDA) proposes new designs informed by simulation outcomes. While general purpose, we focus development and validation on Richtmyer--Meshkov Instability (RMI) suppression, a critical challenge in Inertial Confinement Fusion. We evaluate on two complementary settings: running a hydrodynamics simulations on HPC systems, and using a pre-trained machine learning surrogate for rapid design exploration. Our results demonstrate that the MADA system successfully executes iterative design refinement, automatically improving designs toward optimal RMI suppression with minimal manual intervention. Our framework reduces cumbersome manual workflow setup, and enables automated design exploration at scale. More broadly, it demonstrates a reusable pattern for coupling reasoning, simulation, specialized tools, and coordinated workflows to accelerate scientific discovery. --- ### Can Small Language Models Use What They Retrieve? An Empirical Study of Retrieval Utilization Across Model Scale Authors: Sanchit Pandey Published: 2026-03-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.11513v1 Retrieval augmented generation RAG is widely deployed to improve factual accuracy in language models yet it remains unclear whether smaller models of size 7B parameters or less can effectively utilize retrieved information. To investigate this question we evaluate five model sizes from 360M to 8B across three architecture families SmolLM2 Qwen2.5 and Llama 3.1 under four retrieval conditions including no retrieval BM25 dense retrieval using E5 large v2 and oracle retrieval where the retrieved passage is guaranteed to contain the answer. We introduce a parametric knowledge split that separates questions a model can already answer from those that require external knowledge which allows us to isolate utilization failure from retrieval quality failure. We find three main results. First even with oracle retrieval models of size 7B or smaller fail to extract the correct answer 85 to 100 percent of the time on questions they cannot answer alone which indicates a fundamental utilization bottleneck. Second adding retrieval context destroys 42 to 100 percent of answers the model previously knew suggesting a distraction effect driven by the presence of context rather than its quality. Third an error analysis of 2588 oracle failures shows that the dominant failure mode is irrelevant generation where the model ignores the provided context entirely. These patterns hold across multiple prompt templates and retrieval methods. The results indicate that for models below 7B parameters the main limitation of RAG is context utilization rather than retrieval quality and that deploying RAG at this scale can lead to a net negative trade off under standard evaluation conditions. --- ### From Pen Strokes to Sleep States: Detecting Low-Recovery Days Using Sigma-Lognormal Handwriting Features Authors: Chisa Tanaka, Andrew Vargo, Anna Scius-Bertrand, Andreas Fischer, Koichi Kise Published: 2026-03-12 Categories: cs.HC, cs.CV arXiv: https://arxiv.org/abs/2603.11512v2 While handwriting has traditionally been studied for character recognition and disease classification, its potential to reflect day-to-day physiological fluctuations in healthy individuals remains unexplored. This study examines whether daily variations in sleep-related recovery states can be inferred from online handwriting dynamics. % We propose a personalized binary classification framework that detects low-recovery days using features derived from the Sigma-Lognormal model, which captures the neuromotor generation process of pen strokes. In a 28-day in-the-wild study involving 13 university students, handwriting was recorded three times daily, and nocturnal cardiac indicators were measured using a wearable ring. For each participant, the lowest (or highest) quartile of four sleep-related metrics -- HRV, lowest heart rate, average heart rate, and total sleep duration -- defined the positive class. Leave-One-Day-Out cross-validation showed that PR-AUC significantly exceeded the baseline (0.25) for all four variables after FDR correction, with the strongest performance observed for cardiac-related variables. Importantly, classification performance did not differ significantly across task types or recording timings, indicating that recovery-related signals are embedded in general movement dynamics. These results demonstrate that subtle within-person autonomic recovery fluctuations can be detected from everyday handwriting, opening a new direction for non-invasive, device-independent health monitoring. --- ### Tiny Aya: Bridging Scale and Multilingual Depth Authors: Alejandro R. Salamanca, Diana Abagyan, Daniel D'souza, Ammar Khairi, David Mora, Saurabh Dash, Viraat Aryabumi, Sara Rajaee, Mehrnaz Mofakhami, Ananya Sahu, Thomas Euyang, Brittawnya Prince et al. Published: 2026-03-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.11510v1 Tiny Aya redefines what a small multilingual language model can achieve. Trained on 70 languages and refined through region-aware posttraining, it delivers state-of-the-art in translation quality, strong multilingual understanding, and high-quality target-language generation, all with just 3.35B parameters. The release includes a pretrained foundation model, a globally balanced instruction-tuned variant, and three region-specialized models targeting languages from Africa, South Asia, Europe, Asia-Pacific, and West Asia. This report details the training strategy, data composition, and comprehensive evaluation framework behind Tiny Aya, and presents an alternative scaling path for multilingual AI: one centered on efficiency, balanced performance across languages, and practical deployment. --- ### Manifold-Optimal Guidance: A Unified Riemannian Control View of Diffusion Guidance Authors: Zexi Jia, Pengcheng Luo, Zhengyao Fang, Jinchao Zhang, Jie Zhou Published: 2026-03-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.11509v1 Classifier-Free Guidance (CFG) serves as the de facto control mechanism for conditional diffusion, yet high guidance scales notoriously induce oversaturation, texture artifacts, and structural collapse. We attribute this failure to a geometric mismatch: standard CFG performs Euclidean extrapolation in ambient space, inadvertently driving sampling trajectories off the high-density data manifold. To resolve this, we present Manifold-Optimal Guidance (MOG), a framework that reformulates guidance as a local optimal control problem. MOG yields a closed-form, geometry-aware Riemannian update that corrects off-manifold drift without requiring retraining. Leveraging this perspective, we further introduce Auto-MOG, a dynamic energy-balancing schedule that adaptively calibrates guidance strength, effectively eliminating the need for manual hyperparameter tuning. Extensive validation demonstrates that MOG yields superior fidelity and alignment compared to baselines, with virtually no added computational overhead. --- ### Gen-Fab: A Variation-Aware Generative Model for Predicting Fabrication Variations in Nanophotonic Devices Authors: Rambod Azimi, Yuri Grinberg, Dan-Xia Xu, Odile Liboiron-Ladouceur Published: 2026-03-12 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.11505v1 Silicon photonic devices often exhibit fabrication-induced variations such as over-etching, underetching, and corner rounding, which can significantly alter device performance. These variations are non-uniform and are influenced by feature size and shape. Accurate digital twins are therefore needed to predict the range of possible fabricated outcomes for a given design. In this paper, we introduce Gen-Fab, a conditional generative adversarial network (cGAN) based on Pix2Pix to predict and model uncertainty in photonic fabrication outcomes. The proposed method takes a design layout (in GDS format) as input and produces diverse high-resolution predictions similar to scanning electron microscope (SEM) images of fabricated devices, capturing the range of process variations at the nanometer scale. To enable one-to-many mapping, we inject a latent noise vector at the model bottleneck. We compare Gen-Fab against three baselines: (1) a deterministic U-Net predictor, (2) an inference-time Monte Carlo Dropout U-Net, and (3) an ensemble of varied U-Nets. Evaluations on an out-of-distribution dataset of fabricated photonic test structures demonstrate that Gen-Fab outperforms all baselines in both accuracy and uncertainty modeling. An additional distribution shift analysis further confirms its strong generalization to unseen fabrication geometries. Gen-Fab achieves the highest intersection-over-union (IoU) score of 89.8%, outperforming the deterministic U-Net (85.3%), the MC-Dropout U-Net (83.4%), and varying U-Nets (85.8%). It also better aligns with the distribution of real fabrication outcomes, achieving lower Kullback-Leibler divergence and Wasserstein distance. --- ### LongFlow: Efficient KV Cache Compression for Reasoning Models Authors: Yi Su, Zhenxu Tian, Dan Qiao, Yuechi Zhou, Juntao Li, Min Zhang Published: 2026-03-12 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2603.11504v2 Recent reasoning models such as OpenAI-o1 and DeepSeek-R1 have shown strong performance on complex tasks including mathematical reasoning and code generation. However, this performance gain comes with substantially longer output sequences, leading to significantly increased deployment costs. In particular, long outputs require large KV caches, resulting in high memory consumption and severe bandwidth pressure during attention computation. Most existing KV cache optimization methods are designed for long-input, short-output scenarios and are ineffective for the long-output setting of reasoning models. Moreover, importance estimation in prior work is computationally expensive and becomes prohibitive when continuous re-evaluation is required during long generation. To address these challenges, we propose LongFlow, a KV cache compression method with an efficient importance estimation metric derived from an intermediate result of attention computation using only the current query. This design introduces negligible computational overhead and requires no auxiliary storage. We further develop a custom kernel that fuses FlashAttention, importance estimation, and token eviction into a single optimized operator, improving system-level efficiency. Experiments show that LongFlow achieves up to an 11.8 times throughput improvement with 80% KV cache compression with minimal impact on model accuracy. --- ### Sharpness-Aware Minimization for Generalized Embedding Learning in Federated Recommendation Authors: Fengyuan Yu, Xiaohua Feng, Yuyuan Li, Changwang Zhang, Jun Wang, Chaochao Chen Published: 2026-03-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.11503v1 Federated recommender systems enable collaborative model training while keeping user interaction data local and sharing only essential model parameters, thereby mitigating privacy risks. However, existing methods overlook a critical issue, i.e., the stable learning of a generalized item embedding throughout the federated recommender system training process. Item embedding plays a central role in facilitating knowledge sharing across clients. Yet, under the cross-device setting, local data distributions exhibit significant heterogeneity and sparsity, exacerbating the difficulty of learning generalized embeddings. These factors make the stable learning of generalized item embeddings both indispensable for effective federated recommendation and inherently difficult to achieve. To fill this gap, we propose a new federated recommendation framework, named Federated Recommendation with Generalized Embedding Learning (FedRecGEL). We reformulate the federated recommendation problem from an item-centered perspective and cast it as a multi-task learning problem, aiming to learn generalized embeddings throughout the training procedure. Based on theoretical analysis, we employ sharpness-aware minimization to address the generalization problem, thereby stabilizing the training process and enhancing recommendation performance. Extensive experiments on four datasets demonstrate the effectiveness of FedRecGEL in significantly improving federated recommendation performance. Our code is available at https://github.com/anonymifish/FedRecGEL. --- ### KEPo: Knowledge Evolution Poison on Graph-based Retrieval-Augmented Generation Authors: Qizhi Chen, Chao Qi, Yihong Huang, Muquan Li, Rongzheng Wang, Dongyang Zhang, Ke Qin, Shuang Liang Published: 2026-03-12 Categories: cs.LG, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2603.11501v2 Graph-based Retrieval-Augmented Generation (GraphRAG) constructs the Knowledge Graph (KG) from external databases to enhance the timeliness and accuracy of Large Language Model (LLM) generations. However, this reliance on external data introduces new attack surfaces. Attackers can inject poisoned texts into databases to manipulate LLMs into producing harmful target responses for attacker-chosen queries. Existing research primarily focuses on attacking conventional RAG systems. However, such methods are ineffective against GraphRAG. This robustness derives from the KG abstraction of GraphRAG, which reorganizes injected text into a graph before retrieval, thereby enabling the LLM to reason based on the restructured context instead of raw poisoned passages. To expose latent security vulnerabilities in GraphRAG, we propose Knowledge Evolution Poison (KEPo), a novel poisoning attack method specifically designed for GraphRAG. For each target query, KEPo first generates a toxic event containing poisoned knowledge based on the target answer. By fabricating event backgrounds and forging knowledge evolution paths from original facts to the toxic event, it then poisons the KG and misleads the LLM into treating the poisoned knowledge as the final result. In multi-target attack scenarios, KEPo further connects multiple attack corpora, enabling their poisoned knowledge to mutually reinforce while expanding the scale of poisoned communities, thereby amplifying attack effectiveness. Experimental results across multiple datasets demonstrate that KEPo achieves state-of-the-art attack success rates for both single-target and multi-target attacks, significantly outperforming previous methods. --- ### ActiveFreq: Integrating Active Learning and Frequency Domain Analysis for Interactive Segmentation Authors: Lijun Guo, Qian Zhou, Zidi Shi, Hua Zou, Gang Ke Published: 2026-03-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.11498v1 Interactive segmentation is commonly used in medical image analysis to obtain precise, pixel-level labeling, typically involving iterative user input to correct mislabeled regions. However, existing approaches often fail to fully utilize user knowledge from interactive inputs and achieve comprehensive feature extraction. Specifically, these methods tend to treat all mislabeled regions equally, selecting them randomly for refinement without evaluating each region's potential impact on segmentation quality. Additionally, most models rely solely on spatial domain features, overlooking frequency domain information that could enhance feature extraction and improve performance. To address these limitations, we propose ActiveFreq, a novel interactive segmentation framework that integrates active learning and frequency domain analysis to minimize human intervention while achieving high-quality labeling. ActiveFreq introduces AcSelect, an autonomous module that prioritizes the most informative mislabeled regions, ensuring maximum performance gain from each click. Moreover, we develop FreqFormer, a segmentation backbone incorporating a Fourier transform module to map features from the spatial to the frequency domain, enabling richer feature extraction. Evaluations on the ISIC-2017 and OAI-ZIB datasets demonstrate that ActiveFreq achieves high performance with reduced user interaction, achieving 3.74 NoC@90 on ISIC-2017 and 9.27 NoC@90 on OAI-ZIB, with 23.5% and 12.8% improvements over previous best results, respectively. Under minimal input conditions, such as two clicks, ActiveFreq reaches mIoU scores of 85.29% and 75.76% on ISIC-2017 and OAI-ZIB, highlighting its efficiency and accuracy in interactive medical segmentation. --- ### Try, Check and Retry: A Divide-and-Conquer Framework for Boosting Long-context Tool-Calling Performance of LLMs Authors: Kunfeng Chen, Qihuang Zhong, Juhua Liu, Bo Du, Dacheng Tao Published: 2026-03-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.11495v1 Tool-calling empowers Large Language Models (LLMs) to interact with external environments. However, current methods often struggle to handle massive and noisy candidate tools in long-context tool-calling tasks, limiting their real-world application. To this end, we propose Tool-DC, a Divide-and-Conquer framework for boosting tool-calling performance of LLMs. The core of Tool-DC is to reduce the reasoning difficulty and make full use of self-reflection ability of LLMs via a "Try-Check-Retry" paradigm. Specifically, Tool-DC involves two variants: 1) the training-free Tool-DC (TF), which is plug-and-play and flexible; 2) the training-based Tool-DC (TB), which is more inference-efficient. Extensive experiments show that both Tool-DC methods outperform their counterparts by a clear margin. Tool-DC (TF) brings up to +25.10% average gains against the baseline on BFCL and ACEBench benchmarks, while Tool-DC (TB) enables Qwen2.5-7B to achieve comparable or even better performance than proprietary LLMs, e.g., OpenAI o3 and Claude-Haiku-4.5. --- ### OrthoEraser: Coupled-Neuron Orthogonal Projection for Concept Erasure Authors: Chuancheng Shi, Wenhua Wu, Fei Shen, Xiaogang Zhu, Kun Hu, Zhiyong Wang Published: 2026-03-12 Categories: cs.CV, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2603.11493v1 Text-to-image (T2I) models face significant safety risks from adversarial induction, yet current concept erasure methods often cause collateral damage to benign attributes when suppressing selected neurons entirely. This occurs because sensitive and benign semantics exhibit non-orthogonal superposition, sharing activation subspaces where their respective vectors are inherently entangled. To address this issue, we propose OrthoEraser, which leverages sparse autoencoders (SAE) to achieve high-resolution feature disentanglement and subsequently redefines erasure as an analytical orthogonalization projection that preserves the benign manifold's invariance. OrthoEraser first employs SAE to decompose dense activations and segregate sensitive neurons. It then uses coupled neuron detection to identify non-sensitive features vulnerable to intervention. The key novelty lies in an analytical gradient orthogonalization strategy that projects erasure vectors onto the null space of the coupled neurons. This orthogonally decouples the sensitive concepts from the identified critical benign subspace, effectively preserving non-sensitive semantics. Experimental results on safety demonstrate that OrthoEraser achieves high erasure precision, effectively removing harmful content while preserving the integrity of the generative manifold, and significantly outperforming SOTA baselines. This paper contains results of unsafe models. --- ### SPEGC: Continual Test-Time Adaptation via Semantic-Prompt-Enhanced Graph Clustering for Medical Image Segmentation Authors: Xiaogang Du, Jiawei Zhang, Tongfei Liu, Tao Lei, Yingbo Wang Published: 2026-03-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.11492v1 In medical image segmentation tasks, the domain gap caused by the difference in data collection between training and testing data seriously hinders the deployment of pre-trained models in clinical practice. Continual Test-Time Adaptation (CTTA) aims to enable pre-trained models to adapt to continuously changing unlabeled domains, providing an effective approach to solving this problem. However, existing CTTA methods often rely on unreliable supervisory signals, igniting a self-reinforcing cycle of error accumulation that culminates in catastrophic performance degradation. To overcome these challenges, we propose a CTTA via Semantic-Prompt-Enhanced Graph Clustering (SPEGC) for medical image segmentation. First, we design a semantic prompt feature enhancement mechanism that utilizes decoupled commonality and heterogeneity prompt pools to inject global contextual information into local features, alleviating their susceptibility to noise interference under domain shift. Second, based on these enhanced features, we design a differentiable graph clustering solver. This solver reframes global edge sparsification as an optimal transport problem, allowing it to distill a raw similarity matrix into a refined and high-order structural representation in an end-to-end manner. Finally, this robust structural representation is used to guide model adaptation, ensuring predictions are consistent at a cluster-level and dynamically adjusting decision boundaries. Extensive experiments demonstrate that SPEGC outperforms other state-of-the-art CTTA methods on two medical image segmentation benchmarks. The source code is available at https://github.com/Jwei-Z/SPEGC-for-MIS. --- ### Attention Sinks Are Provably Necessary in Softmax Transformers: Evidence from Trigger-Conditional Tasks Authors: Yuval Ran-Milo Published: 2026-03-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.11487v5 Transformers often display an attention sink: probability mass concentrates on a fixed, content-agnostic position. Are sinks a byproduct of the optimization/training regime? Or are they sometimes functionally necessary in softmax Transformers? We prove that, in some settings, it is the latter: computing a simple trigger-conditional behavior necessarily induces a sink in softmax self-attention models. Our results formalize a familiar intuition: normalization over a probability simplex must force attention to collapse onto a stable anchor to realize a default state (e.g., when the model needs to ignore the input). We instantiate this with a concrete task: when a designated trigger token appears, the model must return the average of all preceding token representations, and otherwise output zero, a task which mirrors the functionality of attention heads in the wild (Barbero et al., 2025; Guo et al., 2024). We also prove that non-normalized ReLU attention can solve the same task without any sink, confirming that the normalization constraint is the fundamental driver of sink behavior. Experiments validate our predictions and demonstrate they extend beyond the theoretically analyzed setting: softmax models develop strong sinks while ReLU attention eliminates them in both single-head and multi-head variants. --- ### AnimeScore: A Preference-Based Dataset and Framework for Evaluating Anime-Like Speech Style Authors: Joonyong Park, Jerry Li Published: 2026-03-12 Categories: cs.SD, cs.CL, eess.AS arXiv: https://arxiv.org/abs/2603.11482v2 Evaluating 'anime-like' voices currently relies on costly subjective judgments, yet no standardized objective metric exists. A key challenge is that anime-likeness, unlike naturalness, lacks a shared absolute scale, making conventional Mean Opinion Score (MOS) protocols unreliable. To address this gap, we propose AnimeScore, a preference-based framework for automatic anime-likeness evaluation via pairwise ranking. We collect 15,000 pairwise judgments from 187 evaluators with free-form descriptions, and acoustic analysis reveals that perceived anime-likeness is driven by controlled resonance shaping, prosodic continuity, and deliberate articulation rather than simple heuristics such as high pitch. We show that handcrafted acoustic features reach a 69.3% AUC ceiling, while SSL-based ranking models achieve up to 90.8% AUC, providing a practical metric that can also serve as a reward signal for preference-based optimization of generative speech models. --- ### INFACT: A Diagnostic Benchmark for Induced Faithfulness and Factuality Hallucinations in Video-LLMs Authors: Junqi Yang, Yuecong Min, Jie Zhang, Shiguang Shan, Xilin Chen Published: 2026-03-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.11481v1 Despite rapid progress, Video Large Language Models (Video-LLMs) remain unreliable due to hallucinations, which are outputs that contradict either video evidence (faithfulness) or verifiable world knowledge (factuality). Existing benchmarks provide limited coverage of factuality hallucinations and predominantly evaluate models only in clean settings. We introduce \textsc{INFACT}, a diagnostic benchmark comprising 9{,}800 QA instances with fine-grained taxonomies for faithfulness and factuality, spanning real and synthetic videos. \textsc{INFACT} evaluates models in four modes: Base (clean), Visual Degradation, Evidence Corruption, and Temporal Intervention for order-sensitive items. Reliability under induced modes is quantified using Resist Rate (RR) and Temporal Sensitivity Score (TSS). Experiments on 14 representative Video-LLMs reveal that higher Base-mode accuracy does not reliably translate to higher reliability in the induced modes, with evidence corruption reducing stability and temporal intervention yielding the largest degradation. Notably, many open-source baselines exhibit near-zero TSS on factuality, indicating pronounced temporal inertia on order-sensitive questions. --- ### Grammar of the Wave: Towards Explainable Multivariate Time Series Event Detection via Neuro-Symbolic VLM Agents Authors: Sky Chenwei Wan, Yifei Y. Wang, Tianjun Hou, Xiqing Chang, Aymeric Jan Published: 2026-03-12 Categories: cs.LG, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2603.11479v4 Time Series Event Detection (TSED) aims to localize semantically meaningful events in time series data, with critical applications in high-stakes domains. Unlike statistical anomalies, events are often defined by natural-language descriptions with internal temporal-logic structures across multiple physical channels. However, in real-world settings, dense event annotations are expensive to obtain, making purely supervised learning difficult. We introduce Language-guided TSED, a setting where a model is given textual event descriptions and must ground them to intervals in multivariate signals with little or no labeled data. To address this problem, we propose Event Logic Tree (ELT), a knowledge representation framework that converts linguistic descriptions into structured temporal logic over signal primitives. Building on ELT, we present SELA, a neuro-symbolic VLM agent framework that iteratively grounds primitives from signal visualizations and composes them under ELT constraints, producing both event intervals and faithful tree-structured explanations. We further release a real-world benchmark across energy and climate domains with expert knowledge and annotations. Experiments show that SELA improves over supervised fine-tuning and existing zero/few-shot time series reasoning baselines. --- ### Grammar of the Wave: Towards Explainable Multivariate Time Series Event Detection via Neuro-Symbolic VLM Agents Authors: Sky Chenwei Wan, Yifei Y. Wang, Tianjun Hou, Xiqing Chang, Aymeric Jan Published: 2026-03-12 Categories: cs.LG, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2603.11479v3 Time Series Event Detection (TSED) aims to localize semantically meaningful events in time series data, with critical applications in high-stakes domains. Unlike statistical anomalies, events are often defined by natural-language descriptions with internal temporal-logic structures across multiple physical channels. However, in real-world settings, dense event annotations are expensive to obtain, making purely supervised learning difficult. We introduce Language-guided TSED, a setting where a model is given textual event descriptions and must ground them to intervals in multivariate signals with little or no labeled data. To address this problem, we propose Event Logic Tree (ELT), a knowledge representation framework that converts linguistic descriptions into structured temporal logic over signal primitives. Building on ELT, we present SELA, a neuro-symbolic VLM agent framework that iteratively grounds primitives from signal visualizations and composes them under ELT constraints, producing both event intervals and faithful tree-structured explanations. We further release a real-world benchmark across energy and climate domains with expert knowledge and annotations. Experiments show that SELA improves over supervised fine-tuning and existing zero/few-shot time series reasoning baselines. --- ### Leveraging Phytolith Research using Artificial Intelligence Authors: Andrés G. Mejía Ramón, Kate Dudgeon, Nina Witteveen, Dolores Piperno, Michael Kloster, Luigi Palopoli, Mónica Moraes R., José M. Capriles, Umberto Lombardo Published: 2026-03-12 Categories: cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2603.11476v1 Phytolith analysis is a crucial tool for reconstructing past vegetation and human activities, but traditional methods are severely limited by labour-intensive, time-consuming manual microscopy. To address this bottleneck, we present Sorometry: a comprehensive end-to-end artificial intelligence pipeline for the high-throughput digitisation, inference, and interpretation of phytoliths. Our workflow processes z-stacked optical microscope scans to automatically generate synchronised 2D orthoimages and 3D point clouds of individual microscopic particles. We developed a multimodal fusion model that combines ConvNeXt for 2D image analysis and PointNet++ for 3D point cloud analysis, supported by a graphical user interface for expert annotation and review. Tested on reference collections and archaeological samples from the Bolivian Amazon, our fusion model achieved a global classification accuracy of 77.9\% across 24 diagnostic morphotypes and 84.5% for segmentation quality. Crucially, the integration of 3D data proved essential for distinguishing complex morphotypes (such as grass silica short cell phytoliths) whose diagnostic features are often obscured by their orientation in 2D projections. Beyond individual object classification, Sorometry incorporates Bayesian finite mixture modelling to predict overall plant source contributions at the assemblage level, successfully identifying specific plants like maize and palms in complex mixed samples. This integrated platform transforms phytolith research into an "omics"-scale discipline, dramatically expanding analytical capacity, standardising expert judgements, and enabling reproducible, population-level characterisations of archaeological and paleoecological assemblages. --- ### Deep Learning Network-Temporal Models For Traffic Prediction Authors: Yufeng Xin, Ethan Fan Published: 2026-03-12 Categories: cs.LG, cs.NI arXiv: https://arxiv.org/abs/2603.11475v2 Accurate prediction of multivariate time series is essential for emerging network intelligent control, observability, and management functions. Existing statistical-based and shallow machine learning models have shown limited prediction capabilities on multivariate time series. They prioritize improvements in average prediction accuracy, while overlooking heterogeneous dependency structures and performance variability across individual time series. Recent advances in large language models have introduced new directions for multivariate time series forecasting; however, their application in conjunction with explicit structural dependency modeling remains relatively underexplored, especially in networked environments. In this paper, we present a topology-aware learning framework for large-scale network traffic prediction that explicitly models both temporal dynamics and structural dependencies in multivariate network time series. We first investigate a graph attention model designed to capture topology-induced correlations among network traffic time series. We then evaluate a fine-tuned large language model-based representations for improved generalization across heterogeneous traffic patterns. To further address the diversity of cross-correlations in high-dimensional traffic data, we introduce a clustering-based preprocessing stage that groups traffic flows with similar dependency characteristics prior to model training, reducing input complexity and improving learning stability. Experiments on real backbone traffic data show consistent improvements over statistical and recurrent neural network baselines. In addition to average accuracy, we evaluate performance across individual time series and observe reduced variability in prediction quality. --- ### Slack More, Predict Better: Proximal Relaxation for Probabilistic Latent Variable Model-based Soft Sensors Authors: Zehua Zou, Yiran Ma, Yulong Zhang, Zhengnan Li, Zeyu Yang, Jinhao Xie, Xiaoyu Jiang, Zhichao Chen Published: 2026-03-12 Categories: cs.LG, eess.SY, math.OC arXiv: https://arxiv.org/abs/2603.11473v2 Nonlinear Probabilistic Latent Variable Models (NPLVMs) are a cornerstone of soft sensor modeling due to their capacity for uncertainty delineation. However, conventional NPLVMs are trained using amortized variational inference, where neural networks parameterize the variational posterior. While facilitating model implementation, this parameterization converts the distributional optimization problem within an infinite-dimensional function space to parameter optimization within a finite-dimensional parameter space, which introduces an approximation error gap, thereby degrading soft sensor modeling accuracy. To alleviate this issue, we introduce KProxNPLVM, a novel NPLVM that pivots to relaxing the objective itself and improving the NPLVM's performance. Specifically, we first prove the approximation error induced by the conventional approach. Based on this, we design the Wasserstein distance as the proximal operator to relax the learning objective, yielding a new variational inference strategy derived from solving this relaxed optimization problem. Based on this foundation, we provide a rigorous derivation of KProxNPLVM's optimization implementation, prove the convergence of our algorithm can finally sidestep the approximation error, and propose the KProxNPLVM by summarizing the abovementioned content. Finally, extensive experiments on synthetic and real-world industrial datasets are conducted to demonstrate the efficacy of the proposed KProxNPLVM. --- ### HawkesRank: Event-Driven Centrality for Real-Time Importance Ranking Authors: Didier Sornette, Yishan Luo, Sandro Claudio Lera Published: 2026-03-12 Categories: cs.SI, cs.LG, physics.soc-ph arXiv: https://arxiv.org/abs/2603.11472v1 Quantifying influence in networks is important across science, economics, and public health, yet widely used centrality measures remain limited: they rely on static representations, heuristic network constructions, and purely endogenous notions of importance, while offering little semantic connection to observable activity. We introduce HawkesRank, a dynamic framework grounded in multivariate Hawkes point processes that models exogenous drivers (intrinsic contributions) and endogenous amplification (self- and cross-excitation). This yields a principled, empirically calibrated, and adaptive importance measure. Classical indices such as Katz centrality and PageRank emerge as mean-field limits of the framework, clarifying both their validity and their limitations. Unlike static averages, HawkesRank measures importance through instantaneous event intensities, enabling prediction, transparent endo-exo decomposition, and adaptability to shocks. Using both simulations and empirical analysis of emotion dynamics in online communication platforms, we show that HawkesRank closely tracks system activity and consistently outperforms static centrality metrics. --- ### Stage-Adaptive Reliability Modeling for Continuous Valence-Arousal Estimation Authors: Yubeen Lee, Sangeun Lee, Junyeop Cha, Eunil Park Published: 2026-03-12 Categories: cs.MM, cs.AI, cs.SD arXiv: https://arxiv.org/abs/2603.11468v1 Continuous valence-arousal estimation in real-world environments is challenging due to inconsistent modality reliability and interaction-dependent variability in audio-visual signals. Existing approaches primarily focus on modeling temporal dynamics, often overlooking the fact that modality reliability can vary substantially across interaction stages. To address this issue, we propose SAGE, a Stage-Adaptive reliability modeling framework that explicitly estimates and calibrates modality-wise confidence during multimodal integration. SAGE introduces a reliability-aware fusion mechanism that dynamically rebalances audio and visual representations according to their stage-dependent informativeness, preventing unreliable signals from dominating the prediction process. By separating reliability estimation from feature representation, the proposed framework enables more stable emotion estimation under cross-modal noise, occlusion, and varying interaction conditions. Extensive experiments on the Aff-Wild2 benchmark demonstrate that SAGE consistently improves concordance correlation coefficient scores compared with existing multimodal fusion approaches, highlighting the effectiveness of reliability-driven modeling for continuous affect prediction. --- ### Bridging Discrete Marks and Continuous Dynamics: Dual-Path Cross-Interaction for Marked Temporal Point Processes Authors: Yuxiang Liu, Qiao Liu, Tong Luo, Yanglei Gan, Peng He, Yao LIu Published: 2026-03-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.11462v1 Predicting irregularly spaced event sequences with discrete marks poses significant challenges due to the complex, asynchronous dependencies embedded within continuous-time data streams.Existing sequential approaches capture dependencies among event tokens but ignore the continuous evolution between events, while Neural Ordinary Differential Equation (Neural ODE) methods model smooth dynamics yet fail to account for how event types influence future timing.To overcome these limitations, we propose NEXTPP, a dual-channel framework that unifies discrete and continuous representations via Event-granular Neural Evolution with Cross-Interaction for Marked Temporal Point Processes. Specifically, NEXTPP encodes discrete event marks via a self-attention mechanism, simultaneously evolving a latent continuous-time state using a Neural ODE. These parallel streams are then fused through a crossattention module to enable explicit bidirectional interaction between continuous and discrete representations. The fused representations drive the conditional intensity function of the neural Hawkes process, while an iterative thinning sampler is employed to generate future events. Extensive evaluations on five real-world datasets demonstrate that NEXTPP consistently outperforms state-of-the-art models. The source code can be found at https://github.com/AONE-NLP/NEXTPP. --- ### Follow the Saliency: Supervised Saliency for Retrieval-augmented Dense Video Captioning Authors: Seung hee Choi, MinJu Jeon, Hyunwoo Oh, Jihwan Lee, Dong-Jin Kim Published: 2026-03-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.11460v2 Existing retrieval-augmented approaches for Dense Video Captioning (DVC) often fail to achieve accurate temporal segmentation aligned with true event boundaries, as they rely on heuristic strategies that overlook ground truth event boundaries. The proposed framework, \textbf{STaRC}, overcomes this limitation by supervising frame-level saliency through a highlight detection module. Note that the highlight detection module is trained on binary labels derived directly from DVC ground truth annotations without the need for additional annotation. We also propose to utilize the saliency scores as a unified temporal signal that drives retrieval via saliency-guided segmentation and informs caption generation through explicit Saliency Prompts injected into the decoder. By enforcing saliency-constrained segmentation, our method produces temporally coherent segments that align closely with actual event transitions, leading to more accurate retrieval and contextually grounded caption generation. We conduct comprehensive evaluations on the YouCook2 and ViTT benchmarks, where STaRC achieves state-of-the-art performance across most of the metrics. Our code is available at https://github.com/ermitaju1/STaRC --- ### UniHetCO: A Unified Heterogeneous Representation for Multi-Problem Learning in Unsupervised Neural Combinatorial Optimization Authors: Kien X. Nguyen, Ilya Safro Published: 2026-03-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.11456v1 Unsupervised neural combinatorial optimization (NCO) offers an appealing alternative to supervised approaches by training learning-based solvers without ground-truth solutions, directly minimizing instance objectives and constraint violations. Yet for graph node subset-selection problems (e.g., Maximum Clique and Maximum Independent Set), existing unsupervised methods are typically specialized to a single problem class and rely on problem-specific surrogate losses, which hinders learning across classes within a unified framework. In this work, we propose UniHetCO, a unified heterogeneous graph representation for constrained quadratic programming-based combinatorial optimization that encodes problem structure, objective terms, and linear constraints in a single input. This formulation enables training a single model across multiple problem classes with a unified label-free objective. To improve stability under multi-problem learning, we employ a gradient-norm-based dynamic weighting scheme that alleviates gradient imbalance among classes. Experiments on multiple datasets and four constrained problem classes demonstrate competitive performance with state-of-the-art unsupervised NCO baselines, strong cross-problem adaptation potential, and effective warm starts for a commercial classical solver under tight time limits. --- ### Examining Users' Behavioural Intention to Use OpenClaw Through the Cognition--Affect--Conation Framework Authors: Yiran Du Published: 2026-03-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.11455v2 This study examines users' behavioural intention to use OpenClaw through the Cognition--Affect--Conation (CAC) framework. The research investigates how cognitive perceptions of the system influence affective responses and subsequently shape behavioural intention. Enabling factors include perceived personalisation, perceived intelligence, and relative advantage, while inhibiting factors include privacy concern, algorithmic opacity, and perceived risk. Survey data from 436 OpenClaw users were analysed using structural equation modelling. The results show that positive perceptions strengthen users' attitudes toward OpenClaw, which increase behavioural intention, whereas negative perceptions increase distrust and reduce intention to use the system. The study provides insights into the psychological mechanisms influencing the adoption of autonomous AI agents. --- ### LLM-Assisted Causal Structure Disambiguation and Factor Extraction for Legal Judgment Prediction Authors: Yuzhi Liang, Lixiang Ma, Xinrong Zhu Published: 2026-03-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.11446v1 Mainstream methods for Legal Judgment Prediction (LJP) based on Pre-trained Language Models (PLMs) heavily rely on the statistical correlation between case facts and judgment results. This paradigm lacks explicit modeling of legal constituent elements and underlying causal logic, making models prone to learning spurious correlations and suffering from poor robustness. While introducing causal inference can mitigate this issue, existing causal LJP methods face two critical bottlenecks in real-world legal texts: inaccurate legal factor extraction with severe noise, and significant uncertainty in causal structure discovery due to Markov equivalence under sparse features. To address these challenges, we propose an enhanced causal inference framework that integrates Large Language Model (LLM) priors with statistical causal discovery. First, we design a coarse-to-fine hybrid extraction mechanism combining statistical sampling and LLM semantic reasoning to accurately identify and purify standard legal constituent elements. Second, to resolve structural uncertainty, we introduce an LLM-assisted causal structure disambiguation mechanism. By utilizing the LLM as a constrained prior knowledge base, we conduct probabilistic evaluation and pruning on ambiguous causal directions to generate legally compliant candidate causal graphs. Finally, a causal-aware judgment prediction model is constructed by explicitly constraining text attention intensity via the generated causal graphs. Extensive experiments on multiple benchmark datasets, including LEVEN , QA, and CAIL, demonstrate that our proposed method significantly outperforms state-of-the-art baselines in both predictive accuracy and robustness, particularly in distinguishing confusing charges. --- ### Verified Multi-Agent Orchestration: A Plan-Execute-Verify-Replan Framework for Complex Query Resolution Authors: Xing Zhang, Yanwei Cui, Guanghui Wang, Wei Qiu, Ziyuan Li, Fangwei Han, Yajing Huang, Hengzhi Qiu, Bing Zhu, Peiyang He Published: 2026-03-12 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2603.11445v2 We present Verified Multi-Agent Orchestration (VMAO), a framework that coordinates specialized LLM-based agents through a verification-driven iterative loop. Given a complex query, our system decomposes it into a directed acyclic graph (DAG) of sub-questions, executes them through domain-specific agents in parallel, verifies result completeness via LLM-based evaluation, and adaptively replans to address gaps. The key contributions are: (1) dependency-aware parallel execution over a DAG of sub-questions with automatic context propagation, (2) verification-driven adaptive replanning that uses an LLM-based verifier as an orchestration-level coordination signal, and (3) configurable stop conditions that balance answer quality against resource usage. On 25 expert-curated market research queries, VMAO improves answer completeness from 3.1 to 4.2 and source quality from 2.6 to 4.1 (1-5 scale) compared to a single-agent baseline, demonstrating that orchestration-level verification is an effective mechanism for multi-agent quality assurance. --- ### GPT4o-Receipt: A Dataset and Human Study for AI-Generated Document Forensics Authors: Yan Zhang, Simiao Ren, Ankit Raj, En Wei, Dennis Ng, Alex Shen, Jiayu Xue, Yuxin Zhang, Evelyn Marotta Published: 2026-03-12 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2603.11442v2 Can humans detect AI-generated financial documents better than machines? We present GPT4o-Receipt, a benchmark of 1,235 receipt images pairing GPT-4o-generated receipts with authentic ones from established datasets, evaluated by five state-of-the-art multimodal LLMs and a 30-annotator crowdsourced perceptual study. Our findings reveal a striking paradox: humans are better at seeing AI artifacts, yet worse at detecting AI documents. Human annotators exhibit the largest visual discrimination gap of any evaluator, yet their binary detection F1 falls well below Claude Sonnet 4 and below Gemini 2.5 Flash. This paradox resolves once the mechanism is understood: the dominant forensic signals in AI-generated receipts are arithmetic errors -- invisible to visual inspection but systematically verifiable by LLMs. Humans cannot perceive that a subtotal is incorrect; LLMs verify it in milliseconds. Beyond the human--LLM comparison, our five-model evaluation reveals dramatic performance disparities and calibration differences that render simple accuracy metrics insufficient for detector selection. GPT4o-Receipt, the evaluation framework, and all results are released publicly to support future research in AI document forensics. --- ### Detect Anything in Real Time: From Single-Prompt Segmentation to Multi-Class Detection Authors: Mehmet Kerem Turkcan Published: 2026-03-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.11441v1 Recent advances in vision-language modeling have produced promptable detection and segmentation systems that accept arbitrary natural language queries at inference time. Among these, SAM3 achieves state-of-the-art accuracy by combining a ViT-H/14 backbone with cross-modal transformer decoding and learned object queries. However, SAM3 processes a single text prompt per forward pass. Detecting N categories requires N independent executions, each dominated by the 439M-parameter backbone. We present Detect Anything in Real Time (DART), a training-free framework that converts SAM3 into a real-time multi-class detector by exploiting a structural invariant: the visual backbone is class-agnostic, producing image features independent of the text prompt. This allows the backbone computation to be shared between all classes, reducing its cost from O(N) to O(1). Combined with batched multi-class decoding, detection-only inference, and TensorRT FP16 deployment, these optimizations yield 5.6x cumulative speedup at 3 classes, scaling to 25x at 80 classes, without modifying any model weight. On COCO val2017 (5,000 images, 80 classes), DART achieves 55.8 AP at 15.8 FPS (4 classes, 1008x1008) on a single RTX 4080, surpassing purpose-built open-vocabulary detectors trained on millions of box annotations. For extreme latency targets, adapter distillation with a frozen encoder-decoder achieves 38.7 AP with a 13.9 ms backbone. Code and models are available at https://github.com/mkturkcan/DART. --- ### Stay in your Lane: Role Specific Queries with Overlap Suppression Loss for Dense Video Captioning Authors: Seung Hyup Baek, Jimin Lee, Hyeongkeun Lee, Jae Won Cho Published: 2026-03-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.11439v1 Dense Video Captioning (DVC) is a challenging multimodal task that involves temporally localizing multiple events within a video and describing them with natural language. While query-based frameworks enable the simultaneous, end-to-end processing of localization and captioning, their reliance on shared queries often leads to significant multi-task interference between the two tasks, as well as temporal redundancy in localization. In this paper, we propose utilizing role-specific queries that separate localization and captioning into independent components, allowing each to exclusively learn its role. We then employ contrastive alignment to enforce semantic consistency between the corresponding outputs, ensuring coherent behavior across the separated queries. Furthermore, we design a novel suppression mechanism in which mutual temporal overlaps across queries are penalized to tackle temporal redundancy, supervising the model to learn distinct, non-overlapping event regions for more precise localization. Additionally, we introduce a lightweight module that captures core event concepts to further enhance semantic richness in captions through concept-level representations. We demonstrate the effectiveness of our method through extensive experiments on major DVC benchmarks YouCook2 and ActivityNet Captions. --- ### ZTab: Domain-based Zero-shot Annotation for Table Columns Authors: Ehsan Hoseinzade, Ke Wang Published: 2026-03-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.11436v1 This study addresses the challenge of automatically detecting semantic column types in relational tables, a key task in many real-world applications. Zero-shot modeling eliminates the need for user-provided labeled training data, making it ideal for scenarios where data collection is costly or restricted due to privacy concerns. However, existing zero-shot models suffer from poor performance when the number of semantic column types is large, limited understanding of tabular structure, and privacy risks arising from dependence on high-performance closed-source LLMs. We introduce ZTab, a domain-based zero-shot framework that addresses both performance and zero-shot requirements. Given a domain configuration consisting of a set of predefined semantic types and sample table schemas, ZTab generates pseudo-tables for the sample schemas and fine-tunes an annotation LLM on them. ZTab is domain-based zero-shot in that it does not depend on user-specific labeled training data; therefore, no retraining is needed for a test table from a similar domain. We describe three cases of domain-based zero-shot. The domain configuration of ZTab provides a trade-off between the extent of zero-shot and annotation performance: a "universal domain" that contains all semantic types approaches "pure" zero-shot, while a "specialized domain" that contains semantic types for a specific application enables better zero-shot performance within that domain. Source code and datasets are available at https://github.com/hoseinzadeehsan/ZTab --- ### Adversarial Reinforcement Learning for Detecting False Data Injection Attacks in Vehicular Routing Authors: Taha Eghtesad, Yevgeniy Vorobeychik, Aron Laszka Published: 2026-03-12 Categories: cs.AI, cs.CR arXiv: https://arxiv.org/abs/2603.11433v1 In modern transportation networks, adversaries can manipulate routing algorithms using false data injection attacks, such as simulating heavy traffic with multiple devices running crowdsourced navigation applications, to mislead vehicles toward suboptimal routes and increase congestion. To address these threats, we formulate a strategically zero-sum game between an attacker, who injects such perturbations, and a defender, who detects anomalies based on the observed travel times of network edges. We propose a computational method based on multi-agent reinforcement learning to compute a Nash equilibrium of this game, providing an optimal detection strategy, which ensures that total travel time remains within a worst-case bound, even in the presence of an attack. We present an extensive experimental evaluation that demonstrates the robustness and practical benefits of our approach, providing a powerful framework to improve the resilience of transportation networks against false data injection. In particular, we show that our approach yields approximate equilibrium policies and significantly outperforms baselines for both the attacker and the defender. --- ### A Stable Neural Statistical Dependence Estimator for Autoencoder Feature Analysis Authors: Bo Hu, Jose C Principe Published: 2026-03-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.11428v2 Statistical dependence measures like mutual information is ideal for analyzing autoencoders, but it can be ill-posed for deterministic, static, noise-free networks. We adopt the variational (Gaussian) formulation that makes dependence among inputs, latents, and reconstructions measurable, and we propose a stable neural dependence estimator based on an orthonormal density-ratio decomposition. Unlike MINE, our method avoids input concatenation and product-of-marginals re-pairing, reducing computational cost and improving stability. We introduce an efficient NMF-like scalar cost and demonstrate empirically that assuming Gaussian noise to form an auxiliary variable enables meaningful dependence measurements and supports quantitative feature analysis, with a sequential convergence of singular values. --- ### Beyond Single-Sample: Reliable Multi-Sample Distillation for Video Understanding Authors: Songlin Li, Xin Zhu, Zechao Guan, Peipeng Chen, Jian Yao Published: 2026-03-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.11423v1 Traditional black-box distillation for Large Vision-Language Models (LVLMs) typically relies on a single teacher response per input, which often yields high-variance responses and format inconsistencies in multimodal or temporal scenarios. To mitigate this unreliable supervision, we propose R-MSD (Reliable Multi-Sample Distillation), a framework that explicitly models teacher sampling variance to enhance distillation stability. Rather than relying on a single teacher response, our approach leverages a task-adaptive teacher pool to provide robust supervision tailored to both closed-ended and open-ended reasoning. By integrating quality-aware signal matching with an adversarial distillation objective, our approach effectively filters teacher noise while maximizing knowledge transfer. Extensive evaluations across comprehensive video understanding benchmarks demonstrate that R-MSD consistently outperforms single sample distillation methods. We additionally include an original SFT+RL 4B baseline under the same training budget, which shows only marginal gains, while our method achieves significant improvements. With a 4B student model, our approach delivers gains on VideoMME (+1.5%), Video-MMMU (+3.2%), and MathVerse (+3.6%). --- ### ShotVerse: Advancing Cinematic Camera Control for Text-Driven Multi-Shot Video Creation Authors: Songlin Yang, Zhe Wang, Xuyi Yang, Songchun Zhang, Xianghao Kong, Taiyi Wu, Xiaotong Zhao, Ran Zhang, Alan Zhao, Anyi Rao Published: 2026-03-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.11421v2 Text-driven video generation has democratized film creation, but camera control in cinematic multi-shot scenarios remains a significant block. Implicit textual prompts lack precision, while explicit trajectory conditioning imposes prohibitive manual overhead and often triggers execution failures in current models. To overcome this bottleneck, we propose a data-centric paradigm shift, positing that aligned (Caption, Trajectory, Video) triplets form an inherent joint distribution that can connect automated plotting and precise execution. Guided by this insight, we present ShotVerse, a ``Plan-then-Control'' framework that decouples generation into two collaborative agents: a VLM (Vision-Language Model)-based Planner that leverages spatial priors to obtain cinematic, globally aligned trajectories from text, and a Controller that renders these trajectories into multi-shot video content via a camera adapter. Central to our approach is the construction of a data foundation: we design an automated multi-shot camera calibration pipeline aligns disjoint single-shot trajectories into a unified global coordinate system. This facilitates the curation of ShotVerse-Bench, a high-fidelity cinematic dataset with a three-track evaluation protocol that serves as the bedrock for our framework. Extensive experiments demonstrate that ShotVerse effectively bridges the gap between unreliable textual control and labor-intensive manual plotting, achieving superior cinematic aesthetics and generating multi-shot videos that are both camera-accurate and cross-shot consistent. --- ### ShotVerse: Advancing Cinematic Camera Control for Text-Driven Multi-Shot Video Creation Authors: Songlin Yang, Zhe Wang, Xuyi Yang, Songchun Zhang, Xianghao Kong, Taiyi Wu, Xiaotong Zhao, Ran Zhang, Alan Zhao, Anyi Rao Published: 2026-03-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.11421v1 Text-driven video generation has democratized film creation, but camera control in cinematic multi-shot scenarios remains a significant block. Implicit textual prompts lack precision, while explicit trajectory conditioning imposes prohibitive manual overhead and often triggers execution failures in current models. To overcome this bottleneck, we propose a data-centric paradigm shift, positing that aligned (Caption, Trajectory, Video) triplets form an inherent joint distribution that can connect automated plotting and precise execution. Guided by this insight, we present ShotVerse, a "Plan-then-Control" framework that decouples generation into two collaborative agents: a VLM (Vision-Language Model)-based Planner that leverages spatial priors to obtain cinematic, globally aligned trajectories from text, and a Controller that renders these trajectories into multi-shot video content via a camera adapter. Central to our approach is the construction of a data foundation: we design an automated multi-shot camera calibration pipeline aligns disjoint single-shot trajectories into a unified global coordinate system. This facilitates the curation of ShotVerse-Bench, a high-fidelity cinematic dataset with a three-track evaluation protocol that serves as the bedrock for our framework. Extensive experiments demonstrate that ShotVerse effectively bridges the gap between unreliable textual control and labor-intensive manual plotting, achieving superior cinematic aesthetics and generating multi-shot videos that are both camera-accurate and cross-shot consistent. --- ### Zero-Shot Cross-City Generalization in End-to-End Autonomous Driving: Self-Supervised versus Supervised Representations Authors: Fatemeh Naeinian, Ali Hamza, Haoran Zhu, Anna Choromanska Published: 2026-03-12 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.11417v2 End-to-end autonomous driving models are typically trained on multi-city datasets using supervised ImageNet-pretrained backbones, yet their ability to generalize to unseen cities remains largely unexamined. When training and evaluation data are geographically mixed, models may implicitly rely on city-specific cues, masking failure modes that would occur under real-world domain shifts when generalizing to new locations. In this work, we formulate zero-shot cross-city transfer as a controlled representation-level stress test for end-to-end autonomous driving and ask how visual pretraining affects transfer behavior under geographic domain shift. We conduct a comprehensive study by integrating self-supervised backbones I-JEPA, DINOv2, and MAE into planning frameworks. We evaluate performance under strict geographic splits on nuScenes in the open-loop setting and on NAVSIM in the closed-loop evaluation protocol. Our experiments reveal a substantial generalization gap when transferring models across cities with different road topologies, traffic conventions, and visual environments. In open-loop evaluation, a supervised backbone exhibits severe degradation when transferring between cities, yet some domain-specific self-supervised methods can substantially reduce both displacement and collision degradation. In closed-loop evaluation, self-supervised pretraining improves average out-of-distribution PDMS in several single-city training settings. Our results provide empirical evidence that representation learning influences the robustness of cross-city planning and motivate zero-shot geographic transfer as an important stress test for evaluating end-to-end autonomous driving systems. --- ### BLooP: Zero-Shot Abstractive Summarization using Large Language Models with Bigram Lookahead Promotion Authors: Varun Iyer, Cornelia Caragea Published: 2026-03-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.11415v1 Abstractive summarization requires models to generate summaries that convey information in the source document. While large language models can generate summaries without fine-tuning, they often miss key details and include extraneous information. We propose BLooP (Bigram Lookahead Promotion), a simple training-free decoding intervention that encourages large language models (LLMs) to generate tokens that form bigrams from the source document. BLooP operates through a hash table lookup at each decoding step, requiring no training, fine-tuning, or model modification. We demonstrate improvements in ROUGE and BARTScore for Llama-3.1-8B-Instruct, Mistral-Nemo-Instruct-2407, and Gemma-2-9b-it on CNN/DM, CCSum, Multi-News, and SciTLDR. Human evaluation shows that BLooP significantly improves faithfulness without reducing readability. We make the code available at https://github.com/varuniyer/BLooP --- ### MaterialFigBENCH: benchmark dataset with figures for evaluating college-level materials science problem-solving abilities of multimodal large language models Authors: Michiko Yoshitake, Yuta Suzuki, Ryo Igarashi, Yoshitaka Ushiku, Keisuke Nagato Published: 2026-03-12 Categories: cs.CL, cond-mat.mtrl-sci arXiv: https://arxiv.org/abs/2603.11414v1 We present MaterialFigBench, a benchmark dataset designed to evaluate the ability of multimodal large language models (LLMs) to solve university-level materials science problems that require accurate interpretation of figures. Unlike existing benchmarks that primarily rely on textual representations, MaterialFigBench focuses on problems in which figures such as phase diagrams, stress-strain curves, Arrhenius plots, diffraction patterns, and microstructural schematics are indispensable for deriving correct answers. The dataset consists of 137 free-response problems adapted from standard materials science textbooks, covering a broad range of topics including crystal structures, mechanical properties, diffusion, phase diagrams, phase transformations, and electronic properties of materials. To address unavoidable ambiguity in reading numerical values from images, expert-defined answer ranges are provided where appropriate. We evaluate several state-of-the-art multimodal LLMs, including ChatGPT and GPT models accessed via OpenAI APIs, and analyze their performance across problem categories and model versions. The results reveal that, although overall accuracy improves with model updates, current LLMs still struggle with genuine visual understanding and quantitative interpretation of materials science figures. In many cases, correct answers are obtained by relying on memorized domain knowledge rather than by reading the provided images. MaterialFigBench highlights persistent weaknesses in visual reasoning, numerical precision, and significant-digit handling, while also identifying problem types where performance has improved. This benchmark provides a systematic and domain-specific foundation for advancing multimodal reasoning capabilities in materials science and for guiding the development of future LLMs with stronger figure-based understanding. --- ### Evaluation format, not model capability, drives triage failure in the assessment of consumer health AI Authors: David Fraile Navarro, Farah Magrabi, Enrico Coiera Published: 2026-03-12 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2603.11413v3 Ramaswamy et al. reported in Nature Medicine that ChatGPT Health under-triages 51.6% of emergencies, concluding that consumer-facing AI triage poses safety risks. However, their evaluation used an exam-style protocol -- forced A/B/C/D output, knowledge suppression, and suppression of clarifying questions -- that differs fundamentally from how consumers use health chatbots. We tested five frontier LLMs (GPT-5.2, Claude Sonnet 4.6, Claude Opus 4.6, Gemini 3 Flash, Gemini 3.1 Pro) on a 17-scenario partial replication bank under constrained (exam-style, 1,275 trials) and naturalistic (patient-style messages, 850 trials) conditions, with targeted ablations and prompt-faithful checks using the authors' released prompts. Naturalistic interaction improved triage accuracy by 6.4 percentage points ($p = 0.015$). Diabetic ketoacidosis was correctly triaged in 100% of trials across all models and conditions. Asthma triage improved from 48% to 80%. The forced A/B/C/D format was the dominant failure mechanism: three models scored 0--24% with forced choice but 100% with free text (all $p < 10^{-8}$), consistently recommending emergency care in their own words while the forced-choice format registered under-triage. Prompt-faithful checks on the authors' exact released prompts confirmed the scaffold produces model-dependent, case-dependent results. Our results suggest that the headline under-triage rate is highly contingent on evaluation format and may not generalize as a stable estimate of deployed triage behavior. Valid evaluation of consumer health AI requires testing under conditions that reflect actual use. --- ### Algorithmic Consequences of Particle Filters for Sentence Processing: Amplified Garden-Paths and Digging-In Effects Authors: Amani Maina-Kilaas, Roger Levy Published: 2026-03-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.11412v2 Under surprisal theory, linguistic representations affect processing difficulty only through the bottleneck of surprisal. Our best estimates of surprisal come from large language models, which have no explicit representation of structural ambiguity. While LLM surprisal robustly predicts reading times across languages, it systematically underpredicts difficulty when structural expectations are violated -- suggesting that representations of ambiguity are causally implicated in sentence processing. Particle filter models offer an alternative where structural hypotheses are explicitly represented as a finite set of particles. We prove several algorithmic consequences of particle filter models, including the amplification of garden-path effects. Most critically, we demonstrate that resampling, a common practice with these models, inherently produces real-time digging-in effects -- where disambiguation difficulty increases with ambiguous region length. Digging-in magnitude scales inversely with particle count: fully parallel models predict no such effect. --- ### Seeing Isn't Orienting: A Cognitively Grounded Benchmark Reveals Systematic Orientation Failures in MLLMs Supplementary Authors: Nazia Tasnim, Keanu Nichols, Yuting Yang, Nicholas Ikechukwu, Elva Zou, Deepti Ghadiyaram, Bryan A. Plummer Published: 2026-03-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.11410v2 Humans learn object orientation progressively, from recognizing which way an object faces, to mentally rotating it, to reasoning about orientations between objects. Current vision-language benchmarks largely conflate orientation with position and general scene understanding. We introduce Discriminative Orientation Reasoning Intelligence (DORI), a cognitively grounded hierarchical benchmark that makes object orientation the primary target. Inspired by stages of human orientation cognition, DORI decomposes orientation into four dimensions, each evaluated at coarse (categorical) and granular (metric) levels. Composed from 13,652 images across 14 sources, DORI provides 33,656 multiple-choice questions covering 67 object categories in real-world and synthetic settings. Its coarse-to-granular design isolates orientation from confounds such as object recognition difficulty, scene clutter, and linguistic ambiguity via bounding-box isolation, standardized spatial reference frames, and structured prompts. Evaluating 24 state-of-the-art vision-language models shows a clear pattern: models that perform well on general spatial benchmarks are near-random on object-centric orientation tasks. The best models reach only 54.2% on coarse and 45.0% on granular judgments, with largest failures on compound rotations and shifts in inter-object reference frames. Large coarse-to-granular gaps reveal reliance on categorical heuristics rather than geometric reasoning, a limitation hidden by existing benchmarks. These results identify orientation understanding as an unsolved challenge for multimodal systems, with implications for robotic manipulation, 3D scene reconstruction, and human-AI interaction. --- ### Speak or Stay Silent: Context-Aware Turn-Taking in Multi-Party Dialogue Authors: Kratika Bhagtani, Mrinal Anand, Yu Chen Xu, Amit Kumar Singh Yadav Published: 2026-03-12 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.11409v1 Existing voice AI assistants treat every detected pause as an invitation to speak. This works in dyadic dialogue, but in multi-party settings, where an AI assistant participates alongside multiple speakers, pauses are abundant and ambiguous. An assistant that speaks on every pause becomes disruptive rather than useful. In this work, we formulate context-aware turn-taking: at every detected pause, given the full conversation context, our method decides whether the assistant should speak or stay silent. We introduce a benchmark of over 120K labeled conversations spanning three multi-party corpora. Evaluating eight recent large language models, we find that they consistently fail at context-aware turn-taking under zero-shot prompting. We then propose a supervised fine-tuning approach with reasoning traces, improving balanced accuracy by up to 23 percentage points. Our findings suggest that context-aware turn-taking is not an emergent capability; it must be explicitly trained. --- ### Beyond Polarity: Multi-Dimensional LLM Sentiment Signals for WTI Crude Oil Futures Return Prediction Authors: Dehao Dai, Ding Ma, Dou Liu, Kerui Geng, Yiqing Wang Published: 2026-03-12 Categories: q-fin.ST, cs.CL arXiv: https://arxiv.org/abs/2603.11408v2 Forecasting crude oil prices remains challenging because market-relevant information is embedded in large volumes of unstructured news and is not fully captured by traditional polarity-based sentiment measures. This paper examines whether multi-dimensional sentiment signals extracted by large language models improve the prediction of weekly WTI crude oil futures returns. Using energy-sector news articles from 2020 to 2025, we construct five sentiment dimensions covering relevance, polarity, intensity, uncertainty, and forwardness based on GPT-4o, Llama 3.2-3b, and two benchmark models, FinBERT and AlphaVantage. We aggregate article-level signals to the weekly level and evaluate their predictive performance in a classification framework. The best results are achieved by combining GPT-4o and FinBERT, suggesting that LLM-based and conventional financial sentiment models provide complementary predictive information. SHAP analysis further shows that intensity- and uncertainty-related features are among the most important predictors, indicating that the predictive value of news sentiment extends beyond simple polarity. Overall, the results suggest that multi-dimensional LLM-based sentiment measures can improve commodity return forecasting and support energy-market risk monitoring. --- ### Real-time Rendering-based Surgical Instrument Tracking via Evolutionary Optimization Authors: Hanyang Hu, Zekai Liang, Florian Richter, Michael C. Yip Published: 2026-03-12 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2603.11404v3 Accurate and efficient tracking of surgical instruments is fundamental for Robot-Assisted Minimally Invasive Surgery. Although vision-based robot pose estimation has enabled markerless calibration without tedious physical setups, reliable tool tracking for surgical robots still remains challenging due to partial visibility and specialized articulation design of surgical instruments. Previous works in the field are usually prone to unreliable feature detections under degraded visual quality and data scarcity, whereas rendering-based methods often struggle with computational costs and suboptimal convergence. In this work, we incorporate CMA-ES, an evolutionary optimization strategy, into a versatile tracking pipeline that jointly estimates surgical instrument pose and joint configurations. Using batch rendering to efficiently evaluate multiple pose candidates in parallel, the method significantly reduces inference time and improves convergence robustness. The proposed framework further generalizes to joint angle-free and bi-manual tracking settings, making it suitable for both vision feedback control and online surgery video calibration. Extensive experiments on synthetic and real-world datasets demonstrate that the proposed method significantly outperforms prior approaches in both accuracy and runtime. Source code and data are available at https://github.com/hanyang-hu/online_dvrk_tracking. --- ### DeepHistoViT: An Interpretable Vision Transformer Framework for Histopathological Cancer Classification Authors: Ravi Mosalpuri, Mohammed Abdelsamea, Ahmed Karam Eldaly Published: 2026-03-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.11403v1 Histopathology remains the gold standard for cancer diagnosis because it provides detailed cellular-level assessment of tissue morphology. However, manual histopathological examination is time-consuming, labour-intensive, and subject to inter-observer variability, creating a demand for reliable computer-assisted diagnostic tools. Recent advances in deep learning, particularly transformer-based architectures, have shown strong potential for modelling complex spatial dependencies in medical images. In this work, we propose DeepHistoViT, a transformer-based framework for automated classification of histopathological images. The model employs a customized Vision Transformer architecture with an integrated attention mechanism designed to capture fine-grained cellular structures while improving interpretability through attention-based localization of diagnostically relevant regions. The framework is evaluated on three publicly available histopathology datasets covering lung cancer, colon cancer, and acute lymphoblastic leukaemia. Experimental results demonstrate state-of-the-art performance across all datasets, with classification accuracy, precision, recall, F1-score, and ROC-AUC reaching 100 percent on the lung and colon cancer datasets, and 99.85 percent, 99.84 percent, 99.86 percent, 99.85 percent, and 99.99 percent respectively on the acute lymphoblastic leukaemia dataset. All performance metrics are reported with 95 percent confidence intervals. These results highlight the effectiveness of transformer-based architectures for histopathological image analysis and demonstrate the potential of DeepHistoViT as an interpretable computer-assisted diagnostic tool to support pathologists in clinical decision-making. --- ### Deployment-Time Reliability of Learned Robot Policies Authors: Christopher Agia Published: 2026-03-12 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.11400v1 Recent advances in learning-based robot manipulation have produced policies with remarkable capabilities. Yet, reliability at deployment remains a fundamental barrier to real-world use, where distribution shift, compounding errors, and complex task dependencies collectively undermine system performance. This dissertation investigates how the reliability of learned robot policies can be improved at deployment time through mechanisms that operate around them. We develop three complementary classes of deployment-time mechanisms. First, we introduce runtime monitoring methods that detect impending failures by identifying inconsistencies in closed-loop policy behavior and deviations in task progress, without requiring failure data or task-specific supervision. Second, we propose a data-centric framework for policy interpretability that traces deployment-time successes and failures to influential training demonstrations using influence functions, enabling principled diagnosis and dataset curation. Third, we address reliable long-horizon task execution by formulating policy coordination as the problem of estimating and maximizing the success probability of behavior sequences, and we extend this formulation to open-ended, language-specified tasks through feasibility-aware task planning. By centering on core challenges of deployment, these contributions advance practical foundations for the reliable, real-world use of learned robot policies. Continued progress on these foundations will be essential for enabling trustworthy and scalable robot autonomy in the future. ---