# Research Papers — 2026-03 · bundle page 88 of 243 > Full-text markdown of papers #4351–4400 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/88 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/87.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/89.md) ### Assessing Model-Agnostic XAI Methods against EU AI Act Explainability Requirements Authors: Francesco Sovrano, Giulia Vilone, Michael Lognoul Published: 2026-03-19 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2604.09628v2 Explainable AI (XAI) has evolved in response to expectations and regulations, such as the EU AI Act, which introduces regulatory requirements on AI-powered systems. However, a persistent gap remains between existing XAI methods and society's legal requirements, leaving practitioners without clear guidance on how to approach compliance in the EU market. To bridge this gap, we study model-agnostic XAI methods and relate their interpretability features to the requirements of the AI Act. We then propose a qualitative-to-quantitative scoring framework: qualitative expert assessments of XAI properties are aggregated into a regulation-specific compliance score. This helps practitioners identify when XAI solutions may support legal explanation requirements while highlighting technical issues that require further research and regulatory clarification. --- ### Multi-User Large Language Model Agents Authors: Shu Yang, Shenzhe Zhu, Hao Zhu, José Ramón Enríquez, Di Wang, Alex Pentland, Michiel A. Bakker, Jiaxin Pei Published: 2026-03-19 Categories: cs.CL, cs.MA arXiv: https://arxiv.org/abs/2604.08567v2 Large language models (LLMs) and LLM-based agents are increasingly deployed as assistants in planning and decision making, yet most existing systems are implicitly optimized for a single-principal interaction paradigm, in which the model is designed to satisfy the objectives of one dominant user whose instructions are treated as the sole source of authority and utility. However, as they are integrated into team workflows and organizational tools, they are increasingly required to serve multiple users simultaneously, each with distinct roles, preferences, and authority levels, leading to multi-user, multi-principal settings with unavoidable conflicts, information asymmetry, and privacy constraints. In this work, we present the first systematic study of multi-user LLM agents. We begin by formalizing multi-user interaction with LLM agents as a multi-principal decision problem, where a single agent must account for multiple users with potentially conflicting interests and associated challenges. We then introduce a unified multi-user interaction protocol and design three targeted stress-testing scenarios to evaluate current LLMs' capabilities in instruction following, privacy preservation, and coordination. Our results reveal systematic gaps: frontier LLMs frequently fail to maintain stable prioritization under conflicting user objectives, exhibit increasing privacy violations over multi-turn interactions, and suffer from efficiency bottlenecks when coordination requires iterative information gathering. --- ### A reconfigurable smart camera implementation for jet flames characterization based on an optimized segmentation model Authors: Gerardo Valente Vazquez-Garcia, Carmina Perez Guerrero, Eduardo Garduño, Miguel Gonzalez-Mendoza, Adriana Palacios, Gerardo Rodriguez-Hernandez, Vahid Foroughi, Alba Àgueda, Elsa Pastor, Gilberto Ochoa-Ruiz Published: 2026-03-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.03267v1 In this work we present a novel framework for fire safety management in industrial settings through the implementation of a smart camera platform for jet flames characterization. The approach seeks to alleviate the lack of real-time solutions for industrial early fire segmentation and characterization. As a case study, we demonstrate how a SoC FPGA, running optimized Artificial Intelligence (AI) models can be leveraged to implement a full edge processing pipeline for jet flames analysis. In this paper we extend previous work on computer-vision jet fire segmentation by creating a novel experimental set-up and system implementation for addressing this issue, which can be replicated to other fire safety applications. The proposed platform is designed to carry out image processing tasks in real-time and on device, reducing video processing overheads, and thus the overall latency. This is achieved by optimizing a UNet segmentation model to make it amenable for an SoC FPGAs implementation; the optimized model can then be efficiently mapped onto the SoC reconfigurable logic for massively parallel execution. For our experiments, we have chosen the Ultra96 platform, as it also provides the means for implementing full-fledged intelligent systems using the SoC peripherals, as well as other Operating System (OS) capabilities (i.e., multi-threading) for systems management. For optimizing the model we made use of the Vitis (Xilinx) framework, which enabled us to optimize the full precision model from 7.5 million parameters to 59,095 parameters (125x less), which translated into a reduction of the processing latency of 2.9x. Further optimization (multi-threading and batch normalization) led to an improvement of 7.5x in terms of latency, yielding a performance of 30 Frames Per Second (FPS) without sacrificing accuracy in terms of the evaluated metrics (Dice Score). --- ### Dynamic Mask Enhanced Intelligent Multi-UAV Deployment for Urban Vehicular Networks Authors: Gaoxiang Cao, Wenke Yuan, Yunpeng Hou, Huasen He, Quan Zheng, Jian Yang Published: 2026-03-19 Categories: cs.NI, cs.AI arXiv: https://arxiv.org/abs/2604.02358v1 Vehicular Ad Hoc Networks (VANETs) play a crucial role in realizing vehicle-road collaboration and intelligent transportation. However, urban VANETs often face challenges such as frequent link disconnections and subnet fragmentation, which hinder reliable connectivity. To address these issues, we dynamically deploy multiple Unmanned Aerial Vehicles (UAVs) as communication relays to enhance VANET. A novel Score based Dynamic Action Mask enhanced QMIX algorithm (Q-SDAM) is proposed for multi-UAV deployment, which maximizes vehicle connectivity while minimizing multi-UAV energy consumption. Specifically, we design a score-based dynamic action mask mechanism to guide UAV agents in exploring large action spaces, accelerate the learning process and enhance optimization performance. The practicality of Q-SDAM is validated using real-world datasets. We show that Q-SDAM improves connectivity by 18.2% while reducing energy consumption by 66.6% compared with existing algorithms. --- ### A Multi-Modal Dataset for Ground Reaction Force Estimation Using Consumer Wearable Sensors Authors: Parvin Ghaffarzadeh, Debarati Chakraborty, Koorosh Aslansefat, Ali Dostan, Yiannis Papadopoulos Published: 2026-03-19 Categories: eess.SP, cs.AI arXiv: https://arxiv.org/abs/2603.28784v1 This Data Descriptor presents a fully open, multi-modal dataset for estimating vertical ground reaction force (vGRF) from consumer-grade Apple Watch sensors with laboratory force plate ground truth. Ten healthy adults aged 26--41 years performed five activities: walking, jogging, running, heel drops, and step drops, while wearing two Apple Watches positioned at the left wrist and waist. The dataset contains 492 validated trials with time-aligned inertial measurement unit (IMU) recordings (approximately 100 Hz) and force plate vGRF (Force\_Z, 1000 Hz). The release includes raw and processed time series, trial-level metadata, quality-control flags, and machine-readable data dictionaries. Trial-level matching manifests link recordings across modalities using stable identifiers. Of the 492 validated trials, 395 are triad-complete, containing wrist, waist, and force plate data, enabling cross-sensor analyses and reproducible model evaluation. Dataset quality is characterised through a three-phase cross-sensor plausibility and consistency framework, repeatability analysis of peak vGRF (intraclass correlation coefficient 0.871--0.990), and systematic checks of force ranges and trial completeness. Monte Carlo sensitivity analysis showed that correlation-based validation metrics were robust to single-sample timing perturbations at the IMU sampling resolution. All data are released under CC BY 4.0, with analysis scripts archived alongside the dataset and mirrored on GitHub. This resource supports reproducible research in wearable biomechanics, benchmarking of machine learning models for vGRF estimation, and investigation of sensor placement effects using widely available consumer wearables. --- ### Interpretable liquid crystal phase classification via two-by-two ordinal patterns Authors: Leonardo G. J. M. Voltarelli, Natalia Osiecka-Drewniak, Marcin Piwowarczyk, Ewa Juszynska-Galazka, Rafael S. Zola, Matjaz Perc, Haroldo V. Ribeiro Published: 2026-03-19 Categories: cond-mat.soft, cs.LG arXiv: https://arxiv.org/abs/2603.26723v1 Liquid crystal textures encode rich structural information, yet mapping these images to mesophase identity remains challenging because visually similar patterns can arise from distinct structures. Here we present a simple, interpretable representation that maps textures to a 75-dimensional frequency vector of two-by-two ordinal patterns, grouped into eleven symmetry-based types to characterize a large-scale dataset spanning seven mesophases. Combined with a simple machine learning classifier, this lightweight representation yields near-perfect phase recognition, including the difficult distinction between smectic A and smectic B mesophases. Our approach generalizes to unseen compounds and accurately distinguishes between phase identity and material origin. Unlike deep learning methods, each ordinal pattern is readily interpretable, and model explanations augmented with network visualizations of pattern interactions reveal the specific types and pairwise dependencies that drive each mesophase decision, providing compact, physically meaningful summaries of texture determinants. These results establish two-by-two ordinal patterns as an interpretable and scalable tool for liquid crystal image analysis, with potential applications to other complex patterned systems in materials science. --- ### Brain-inspired AI for Edge Intelligence: a systematic review Authors: Yingchao Cheng, Meijia Wang, Zhifeng Hao, Rajkumar Buyya Published: 2026-03-19 Categories: cs.NE, cs.AI, cs.AR, cs.OS arXiv: https://arxiv.org/abs/2603.26722v1 While Spiking Neural Networks (SNNs) promise to circumvent the severe Size, Weight, and Power (SWaP) constraints of edge intelligence, the field currently faces a "Deployment Paradox" where theoretical energy gains are frequently negated by the inefficiencies of mapping asynchronous, event-driven dynamics onto traditional von Neumann substrates. Transcending the reductionism of algorithm-only reviews, this survey adopts a rigorous system-level hardware-software co-design perspective to examine the 2020-2025 trajectory, specifically targeting the "last mile" technologies - from quantization methodologies to hybrid architectures - that translate biological plausibility into silicon reality. We critically dissect the interplay between training complexity (the dichotomy of direct learning vs. conversion), the "memory wall" bottlenecking stateful neuronal updates, and the critical software gap in neuromorphic compilation toolchains. Finally, we envision a roadmap to reconcile the fundamental "Sync-Async Mismatch," proposing the development of a standardized Neuromorphic OS as the foundational layer for realizing a ubiquitous, energy-autonomous Green Cognitive Substrate. --- ### Stress Classification from ECG Signals Using Vision Transformer Authors: Zeeshan Ahmad, Naimul Khan Published: 2026-03-19 Categories: eess.SP, cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.26721v1 Vision Transformers have shown tremendous success in numerous computer vision applications; however, they have not been exploited for stress assessment using physiological signals such as Electrocardiogram (ECG). In order to get the maximum benefit from the vision transformer for multilevel stress assessment, in this paper, we transform the raw ECG data into 2D spectrograms using short time Fourier transform (STFT). These spectrograms are divided into patches for feeding to the transformer encoder. We also perform experiments with 1D CNN and ResNet-18 (CNN model). We perform leave-onesubject-out cross validation (LOSOCV) experiments on WESAD and Ryerson Multimedia Lab (RML) dataset. One of the biggest challenges of LOSOCV based experiments is to tackle the problem of intersubject variability. In this research, we address the issue of intersubject variability and show our success using 2D spectrograms and the attention mechanism of transformer. Experiments show that vision transformer handles the effect of intersubject variability much better than CNN-based models and beats all previous state-of-the-art methods by a considerable margin. Moreover, our method is end-to-end, does not require handcrafted features, and can learn robust representations. The proposed method achieved 71.01% and 76.7% accuracies with RML dataset and WESAD dataset respectively for three class classification and 88.3% for binary classification on WESAD. --- ### SutureFormer: Learning Surgical Trajectories via Goal-conditioned Offline RL in Pixel Space Authors: Huanrong Liu, Chunlin Tian, Tongyu Jia, Tailai Zhou, Qin Liu, Yu Gao, Yutong Ban, Yun Gu, Guy Rosman, Xin Ma, Qingbiao Li Published: 2026-03-19 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2603.26720v3 Predicting surgical needle trajectories from endoscopic video is critical for robot-assisted suturing, enabling anticipatory planning, real-time guidance, and safer motion execution. Existing methods that directly learn motion distributions from visual observations tend to overlook the sequential dependency among adjacent motion steps. Moreover, sparse waypoint annotations often fail to provide sufficient supervision, further increasing the difficulty of supervised or imitation learning methods. To address these challenges, we formulate image-based needle trajectory prediction as a sequential decision-making problem, in which the needle tip is treated as an agent that moves step by step in pixel space. This formulation naturally captures the continuity of needle motion and enables the explicit modeling of physically plausible pixel-wise state transitions over time. From this perspective, we propose SutureFormer, a goal-conditioned offline reinforcement learning framework that leverages sparse annotations to dense reward signals via cubic spline interpolation, encouraging the policy to exploit limited expert guidance while exploring plausible future motion paths. SutureFormer encodes variable-length clips using an observation encoder to capture both local spatial cues and long-range temporal dynamics, and autoregressively predicts future waypoints through actions composed of discrete directions and continuous magnitudes. To enable stable offline policy optimization from expert demonstrations, we adopt Conservative Q-Learning with Behavioral Cloning regularization. Experiments on a new kidney wound suturing dataset containing 1,158 trajectories from 50 patients show that SutureFormer reduces Average Displacement Error by 58.6% compared with the strongest baseline, demonstrating the effectiveness of modeling needle trajectory prediction as pixel-level sequential action learning. --- ### The Efficiency Attenuation Phenomenon: A Computational Challenge to the Language of Thought Hypothesis Authors: Di Zhang Published: 2026-03-19 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.22312v1 This paper computationally investigates whether thought requires a language-like format, as posited by the Language of Thought (LoT) hypothesis. We introduce the ``AI Private Language'' thought experiment: if two artificial agents develop an efficient, inscrutable communication protocol via multi-agent reinforcement learning (MARL), and their performance declines when forced to use a human-comprehensible language, this Efficiency Attenuation Phenomenon (EAP) challenges the LoT. We formalize this in a cooperative navigation task under partial observability. Results show that agents with an emergent protocol achieve 50.5\% higher efficiency than those using a pre-defined, human-like symbolic protocol, confirming the EAP. This suggests optimal collaborative cognition in these systems is not mediated by symbolic structures but is naturally coupled with sub-symbolic computations. The work bridges philosophy, cognitive science, and AI, arguing for pluralism in cognitive architectures and highlighting implications for AI ethics. --- ### Ca2+ transient detection and segmentation with the Astronomically motivated algorithm for Background Estimation And Transient Segmentation (Astro-BEATS) Authors: Bolin Fan, Anthony Bilodeau, Frederic Beaupre, Theresa Wiesner, Christian Gagne, Flavie Lavoie-Cardinal, Renee Hlozek Published: 2026-03-19 Categories: q-bio.NC, astro-ph.IM, cs.CV arXiv: https://arxiv.org/abs/2603.22311v1 Fluorescence-based Ca$^{2+}$-imaging is a powerful tool for studying localized neuronal activity, including miniature Synaptic Calcium Transients, providing real-time insights into synaptic activity. These transients induce only subtle changes in the fluorescence signal, often barely above baseline, which poses a significant challenge for automated synaptic transient detection and segmentation. Detecting astronomical transients similarly requires efficient algorithms that will remain robust over a large field of view with varying noise properties. We leverage techniques used in astronomical transient detection for miniature Synaptic Calcium Transient detection in fluorescence microscopy. We present Astro-BEATS, an automatic miniature Synaptic Calcium Transient segmentation algorithm that incorporates image estimation and source-finding techniques used in astronomy and designed for Ca$^{2+}$-imaging videos. Astro-BEATS outperforms current threshold-based approaches for synaptic Ca$^{2+}$ transient detection and segmentation. The produced segmentation masks can be used to train a supervised deep learning algorithm for improved synaptic Ca$^{2+}$ transient detection in Ca$^{2+}$-imaging data. The speed of Astro-BEATS and its applicability to previously unseen datasets without re-optimization makes it particularly useful for generating training datasets for deep learning-based approaches. --- ### UniFluids: Unified Neural Operator Learning with Conditional Flow-matching Authors: Haosen Li, Qi Meng, Jiahao Li, Rui Zhang, Ruihua Song, Liang Ma, Zhi-Ming Ma Published: 2026-03-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.22309v1 Partial differential equation (PDE) simulation holds extensive significance in scientific research. Currently, the integration of deep neural networks to learn solution operators of PDEs has introduced great potential. In this paper, we present UniFluids, a conditional flow-matching framework that harnesses the scalability of diffusion Transformer to unify learning of solution operators across diverse PDEs with varying dimensionality and physical variables. Unlike the autoregressive PDE foundation models, UniFluids adopts flow-matching to achieve parallel sequence generation, making it the first such approach for unified operator learning. Specifically, the introduction of a unified four-dimensional spatiotemporal representation for the heterogeneous PDE datasets enables joint training and conditional encoding. Furthermore, we find the effective dimension of the PDE dataset is much lower than its patch dimension. We thus employ $x$-prediction in the flow-matching operator learning, which is verified to significantly improve prediction accuracy. We conduct a large-scale evaluation of UniFluids on several PDE datasets covering spatial dimensions 1D, 2D and 3D. Experimental results show that UniFluids achieves strong prediction accuracy and demonstrates good scalability and cross-scenario generalization capability. The code will be released later. --- ### GIP-RAG: An Evidence-Grounded Retrieval-Augmented Framework for Interpretable Gene Interaction and Pathway Impact Analysis Authors: Fujian Jia, Jiwen Gu, Cheng Lu, Dezhi Zhao, Mengjiang Huang, Yuanzhi Lu, Xin Liu, Kang Liu Published: 2026-03-19 Categories: q-bio.MN, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.20321v1 Understanding mechanistic relationships among genes and their impacts on biological pathways is essential for elucidating disease mechanisms and advancing precision medicine. Despite the availability of extensive molecular interaction and pathway data in public databases, integrating heterogeneous knowledge sources and enabling interpretable multi-step reasoning across biological networks remain challenging. We present GIP-RAG (Gene Interaction Prediction through Retrieval-Augmented Generation), a computational framework that combines biomedical knowledge graphs with large language models (LLMs) to infer and interpret gene interactions. The framework constructs a unified gene interaction knowledge graph by integrating curated data from KEGG, WikiPathways, SIGNOR, Pathway Commons, and PubChem. Given user-specified genes, a query-driven module retrieves relevant subgraphs, which are incorporated into structured prompts to guide LLM-based stepwise reasoning. This enables identification of direct and indirect regulatory relationships and generation of mechanistic explanations supported by biological evidence. Beyond pairwise interactions, GIP-RAG includes a pathway-level functional impact module that simulates propagation of gene perturbations through signaling networks and evaluates potential pathway state changes. Evaluation across diverse biological scenarios demonstrates that the framework generates consistent, interpretable, and evidence-supported insights into gene regulatory mechanisms. Overall, GIP-RAG provides a general and interpretable approach for integrating knowledge graphs with retrieval-augmented LLMs to support mechanistic reasoning in complex molecular systems. --- ### The Causal Impact of Tool Affordance on Safety Alignment in LLM Agents Authors: Shasha Yu, Fiona Carroll, Barry L. Bentley Published: 2026-03-19 Categories: cs.SE, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.20320v1 Large language models (LLMs) are increasingly deployed as agents with access to executable tools, enabling direct interaction with external systems. However, most safety evaluations remain text-centric and assume that compliant language implies safe behavior, an assumption that becomes unreliable once models are allowed to act. In this work, we empirically examine how executable tool affordance alters safety alignment in LLM agents using a paired evaluation framework that compares text-only chatbot behavior with tool-enabled agent behavior under identical prompts and policies. Experiments are conducted in a deterministic financial transaction environment with binary safety constraints across 1,500 procedurally generated scenarios. To separate intent from outcome, we distinguish between attempted and realized violations using dual enforcement regimes that either block or permit unsafe actions. Both evaluated models maintain perfect compliance in text-only settings, yet exhibit sharp increases in violations after tool access is introduced, reaching rates up to 85% despite unchanged rules. We observe substantial gaps between attempted and executed violations, indicating that external guardrails can suppress visible harm while masking persistent misalignment. Agents also develop spontaneous constraint circumvention strategies without adversarial prompting. These results demonstrate that tool affordance acts as a primary driver of safety misalignment and that text-based evaluation alone is insufficient for assessing agentic systems. --- ### Which Workloads Belong in Orbit? A Workload-First Framework for Orbital Data Centers Using Semantic Abstraction Authors: Durgendra Narayan Singh Published: 2026-03-19 Categories: cs.CV, cs.DC, cs.NI arXiv: https://arxiv.org/abs/2603.20317v2 Space-based compute is becoming plausible as launch costs fall and data-intensive AI workloads grow. This paper proposes a workload-centric framework for deciding which tasks belong in orbit versus terrestrial cloud, along with a phased adoption model tied to orbital data center maturity. We ground the framework with in-orbit semantic-reduction prototypes. An Earth-observation pipeline on Sentinel-2 imagery from Seattle and Bengaluru (formerly Bangalore) achieves 99.7-99.99% payload reduction by converting raw imagery to compact semantic artifacts. A multi-pass stereo reconstruction prototype reduces ~306 MB to ~1.57 MB of derived 3D representations (99.49% reduction). These results support a workload-first view in which semantic abstraction, not raw compute scale, drives early workload suitability. --- ### Bypassing Document Ingestion: An MCP Approach to Financial Q&A Authors: Sasan Mansouri, Edoardo Pilla, Mark Wahrenburg, Fabian Woebbeking Published: 2026-03-19 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2603.20316v1 Answering financial questions is often treated as an information retrieval problem. In practice, however, much of the relevant information is already available in curated vendor systems, especially for quantitative analysis. We study whether, and under which conditions, Model Context Protocol (MCP) offers a more reliable alternative to standard retrieval-augmented generation (RAG) by allowing large language models (LLMs) to interact directly with data rather than relying on document ingestion and chunk retrieval. We test this by building a custom MCP server that exposes LSEG APIs as tools and evaluating it on the FinDER benchmark. The approach performs particularly well on the Financials subset, achieving up to 80.4% accuracy on multi-step numerical questions when relevant context is retrieved. The paper thus provides both a baseline for MCP-based financial question answering (QA) and evidence on where this approach breaks down, such as for questions requiring qualitative or document-specific context. Overall, direct access to curated data is a lightweight and effective alternative to document-centric RAG for quantitative financial QA, but not a substitute for all financial QA tasks. --- ### Rolling-Origin Validation Reverses Model Rankings in Multi-Step PM10 Forecasting: XGBoost, SARIMA, and Persistence Authors: Federico Garcia Crespi, Eduardo Yubero Funes, Marina Alfosea Simon Published: 2026-03-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.20315v1 (a) Many air quality forecasting studies report gains from machine learning, but evaluations often use static chronological splits and omit persistence baselines, so the operational added value under routine updating is unclear. (b) Using 2,350 daily PM10 observations from 2017 to 2024 at an urban background monitoring station in southern Europe, we compare XGBoost and SARIMA against persistence under a static split and a rolling-origin protocol with monthly updates. We report horizon-specific skill and the predictability horizon, defined as the maximum horizon with positive persistence-relative skill. Static evaluation suggests XGBoost performs well from one to seven days ahead, but rolling-origin evaluation reverses rankings: XGBoost is not consistently better than persistence at short and intermediate horizons, whereas SARIMA remains positively skilled across the full range. (c) For researchers, static splits can overstate operational usefulness and change rankings. For practitioners, rolling-origin, persistence-referenced skill profiles show which methods stay reliable at each lead time. --- ### VGS-Decoding: Visual Grounding Score Guided Decoding for Hallucination Mitigation in Medical VLMs Authors: Govinda Kolli, Adinath Madhavrao Dukre, Behzad Bozorgtabar, Dwarikanath Mahapatra, Imran Razzak Published: 2026-03-19 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.20314v1 Medical Vision-Language Models (VLMs) often hallucinate by generating responses based on language priors rather than visual evidence, posing risks in clinical applications. We propose Visual Grounding Score Guided Decoding (VGS-Decoding), a training-free method to mitigate hallucinations during inference. Our key insight is that hallucinated tokens maintain or increase their probability when visual information is degraded, while visually grounded tokens decrease in probability. We introduce the Visual Grounding Score (VGS), which measures each token's visual dependency by comparing distributions from original and distorted images. During decoding, we reweight probabilities by amplifying visually grounded tokens while suppressing hallucinations. Unlike fixed-weight contrastive methods, VGS-Decoding provides per-token adaptive control. Experiments on MIMIC-Diff-VQA and VQA-RAD across LLaVA-Med, CheXagent, and MedGemma demonstrate consistent improvements, with up to +9.12% overall gain and $+8.98\%$ in open-ended recall, while introducing only $2\times$ inference overhead and no additional training, making it practical for clinical deployment. Upon acceptance, code will be released publicly to facilitate reproducibility. --- ### Semantic Tool Discovery for Large Language Models: A Vector-Based Approach to MCP Tool Selection Authors: Sarat Mudunuri, Jian Wan, Ally Qin, Srinivasan Manoharan Published: 2026-03-19 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2603.20313v1 Large Language Models (LLMs) with tool-calling capabilities have demonstrated remarkable potential in executing complex tasks through external tool integration. The Model Context Protocol (MCP) has emerged as a standardized framework for connecting LLMs to diverse toolsets, with individual MCP servers potentially exposing dozens to hundreds of tools. However, current implementations face a critical scalability challenge: providing all available tools to the LLM context results in substantial token overhead, increased costs, reduced accuracy, and context window constraints. We present a semantic tool discovery architecture that addresses these challenges through vector-based retrieval. Our approach indexes MCP tools using dense embeddings that capture semantic relationships between tool capabilities and user intent, dynamically selecting only the most relevant tools (typically 3-5) rather than exposing the entire tool catalog (50-100+). Experimental results demonstrate a 99.6% reduction in tool-related token consumption with a hit rate of 97.1% at K=3 and an MRR of 0.91 on a benchmark of 140 queries across 121 tools from 5 MCP servers, with sub-100ms retrieval latency. Contributions include: (1) a semantic indexing framework for MCP tools, (2) a dynamic tool selection algorithm based on query-tool similarity, (3) comprehensive evaluation demonstrating significant efficiency and accuracy improvements, and (4) extensibility to multi-agent and cross-organizational tool discovery. --- ### kRAIG: A Natural Language-Driven Agent for Automated DataOps Pipeline Generation Authors: Rohan Siva, Kai Cheung, Lichi Li, Ganesh Sundaram Published: 2026-03-19 Categories: cs.SE, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.20311v1 Modern machine learning systems rely on complex data engineering workflows to extract, transform, and load (ELT) data into production pipelines. However, constructing these pipelines remains time-consuming and requires substantial expertise in data infrastructure and orchestration frameworks. Recent advances in large language model (LLM) agents offer a potential path toward automating these workflows, but existing approaches struggle with under-specified user intent, unreliable tool generation, and limited guarantees of executable outputs. We introduce kRAIG, an AI agent that translates natural language specifications into production-ready Kubeflow Pipelines (KFP). To resolve ambiguity in user intent, we propose ReQuesAct (Reason, Question, Act), an interaction framework that explicitly clarifies intent prior to pipeline synthesis. The system orchestrates end-to-end data movement from diverse sources and generates task-specific transformation components through a retrieval-augmented tool synthesis process. To ensure data quality and safety, kRAIG incorporates LLM-based validation stages that verify pipeline integrity prior to execution. Our framework achieves a 3x improvement in extraction and loading success and a 25 percent increase in transformation accuracy compared to state-of-the-art agentic baselines. These improvements demonstrate that structured agent workflows with explicit intent clarification and validation significantly enhance the reliability and executability of automated data engineering pipelines. --- ### GraphiContact: Pose-aware Human-Scene Robust Contact Perception for Interactive Systems Authors: Xiaojian Lin, Yaomin Shen, Junyuan Ma, Yujie Sun, Chengqing Bu, Wenxin Zhang, Zongzheng Zhang, Hao Fei, Lei Jin, Hao Zhao Published: 2026-03-19 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2603.20310v1 Monocular vertex-level human-scene contact prediction is a fundamental capability for interactive systems such as assistive monitoring, embodied AI, and rehabilitation analysis. In this work, we study this task jointly with single-image 3D human mesh reconstruction, using reconstructed body geometry as a scaffold for contact reasoning. Existing approaches either focus on contact prediction without sufficiently exploiting explicit 3D human priors, or emphasize pose/mesh reconstruction without directly optimizing robust vertex-level contact inference under occlusion and perceptual noise. To address this gap, we propose GraphiContact, a pose-aware framework that transfers complementary human priors from two pretrained Transformer encoders and predicts per-vertex human-scene contact on the reconstructed mesh. To improve robustness in real-world scenarios, we further introduce a Single-Image Multi-Infer Uncertainty (SIMU) training strategy with token-level adaptive routing, which simulates occlusion and noisy observations during training while preserving efficient single-branch inference at test time. Experiments on five benchmark datasets show that GraphiContact achieves consistent gains on both contact prediction and 3D human reconstruction. Our code, based on the GraphiContact method, provides comprehensive 3D human reconstruction and interaction analysis, and will be publicly available at https://github.com/Aveiro-Lin/GraphiContact. --- ### Reason-to-Transmit: Deliberative Adaptive Communication for Cooperative Perception Authors: Aayam Bansal, Ishaan Gangwani Published: 2026-03-19 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2603.20308v1 Cooperative perception among autonomous agents overcomes the limitations of single-agent sensing, but bandwidth constraints in vehicle-to-everything (V2X) networks require efficient communication policies. Existing approaches rely on reactive mechanisms, such as confidence maps, learned gating, or sparse masks, to decide what to transmit, without reasoning about why a message benefits the receiver. We introduce Reason-to-Transmit (R2T), a framework that equips each agent with a lightweight transformer-based module that reasons over local scene context, estimated neighbor information gaps, and bandwidth budget to make per-region transmission decisions. Trained end-to-end with a bandwidth-aware objective, R2T is evaluated against nine baselines in a multi-agent bird's-eye-view perception environment. Any communication improves performance by about 58% AP over no communication. At low bandwidth, all selective methods perform similarly, but R2T shows clear gains under high occlusion, where information asymmetry is greatest, approaching oracle performance. All methods degrade gracefully under packet drops up to 50%, showing robustness to communication failures. These results indicate that while fusion design dominates performance, deliberative communication provides additional gains in challenging scenarios. R2T introduces a reasoning-based approach to communication, enabling more efficient and context-aware information sharing in cooperative perception. --- ### EARTalking: End-to-end GPT-style Autoregressive Talking Head Synthesis with Frame-wise Control Authors: Yuzhe Weng, Haotian Wang, Yuanhong Yu, Jun Du, Shan He, Xiaoyan Wu, Haoran Xu Published: 2026-03-19 Categories: cs.CV, cs.AI, cs.MM, cs.SD arXiv: https://arxiv.org/abs/2603.20307v1 Audio-driven talking head generation aims to create vivid and realistic videos from a static portrait and speech. Existing AR-based methods rely on intermediate facial representations, which limit their expressiveness and realism. Meanwhile, diffusion-based methods generate clip-by-clip, lacking fine-grained control and causing inherent latency due to overall denoising across the window. To address these limitations, we propose EARTalking, a novel end-to-end, GPT-style autoregressive model for interactive audio-driven talking head generation. Our method introduces a novel frame-by-frame, in-context, audio-driven streaming generation paradigm. For inherently supporting variable-length video generation with identity consistency, we propose the Sink Frame Window Attention (SFA) mechanism. Furthermore, to avoid the complex, separate networks that prior works required for diverse control signals, we propose a streaming Frame Condition In-Context (FCIC) scheme. This scheme efficiently injects diverse control signals in a streaming, in-context manner, enabling interactive control at every frame and at arbitrary moments. Experiments demonstrate that EARTalking outperforms existing autoregressive methods and achieves performance comparable to diffusion-based methods. Our work demonstrates the feasibility of in-context streaming autoregressive control, unlocking a scalable direction for flexible, efficient generation. The code will be released for reproducibility. --- ### The Global-Local loop: what is missing in bridging the gap between geospatial data from numerous communities? Authors: Clément Mallet, Ana-Maria Raimond Published: 2026-03-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.20305v1 We face a unprecedented amount of geospatial data, describing directly or indirectly the Earth Surface at multiple spatial, temporal, and semantic scales, and stemming from numerous contributors, from satellites to citizens. The main challenge in all the geospatial-related communities lies in suitably leveraging a combination of some of the sources for either a generic or a thematic application. Certain data fusion schemes are predominantly exploited: they correspond to popular tasks with mainstream data sources, e.g., free archives of Sentinel images coupled with OpenStreetMap data under an open and widespread deep-learning backbone for land-cover mapping purposes. Most of these approaches unfortunately operate under a "master-slave" paradigm, where one source is basically integrated to help processing the "main" source, without mutual advantages (e.g., large-scale estimation of a given biophysical variable using in-situ observations) and under a specific community bias. We argue that numerous key data fusion configurations, and in particular the effort in symmetrizing the exploitation of multiple data sources, are insufficiently addressed while being highly beneficial for generic or thematic applications. Bridges and retroactions between scales, communities and their respective sources are lacking, neglecting the utmost potential of such a "global-local loop". In this paper, we propose to establish the most relevant interaction schemes through illustrative use cases. We subsequently discuss under-explored research directions that could take advantage of leveraging available data through multiples extents and communities. --- ### Transferable Multi-Bit Watermarking Across Frozen Diffusion Models via Latent Consistency Bridges Authors: Hong-Hanh Nguyen-Le, Van-Tuan Tran, Thuc D. Nguyen, Nhien-An Le-Khac Published: 2026-03-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.20304v2 As generative AI advances, global governance frameworks increasingly mandate verifiable content provenance. However, existing watermarking techniques face a critical policy-to-technology disconnect: sampling-based methods require computationally prohibitive inversion, while fine-tuning approaches are tethered to specific model checkpoints, hindering standardized, cross-model oversight. To bridge this gap, we introduce DiffMark, a plug-and-play multi-bit watermarking framework. DiffMark embeds a persistent, learned perturbation into every denoising step of a frozen diffusion model, accumulating a recoverable signal in the final latent space. To enable efficient training through the frozen network, we utilize Latent Consistency Models (LCMs) as a differentiable training bridge. DiffMark achieves 64-bit extraction in a single 16.4 ms forward pass, which is a $45\times$ speed-up over inversion baselines. By enabling per-image key flexibility and cross-architecture transferability without retraining, DiffMark provides the practical, scalable technical tooling necessary to operationalize user accountability and enforce emerging AI governance mandates. --- ### InjectFlow: Weak Guides Strong via Orthogonal Injection for Flow Matching Authors: Dayu Wang, Jiaye Yang, Weikang Li, Jiahui Liang, Yang Li Published: 2026-03-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.20303v1 Flow Matching (FM) has recently emerged as a leading approach for high-fidelity visual generation, offering a robust continuous-time alternative to ordinary differential equation (ODE) based models. However, despite their success, FM models are highly sensitive to dataset biases, which cause severe semantic degradation when generating out-of-distribution or minority-class samples. In this paper, we provide a rigorous mathematical formalization of the ``Bias Manifold'' within the FM framework. We identify that this performance drop is driven by conditional expectation smoothing, a mechanism that inevitably leads to trajectory lock-in during inference. To resolve this, we introduce InjectFlow, a novel, training-free method by injecting orthogonal semantics during the initial velocity field computation, without requiring any changes to the random seeds. This design effectively prevents the latent drift toward majority modes while maintaining high generative quality. Extensive experiments demonstrate the effectiveness of our approach. Notably, on the GenEval dataset, InjectFlow successfully fixes 75% of the prompts that standard flow matching models fail to generate correctly. Ultimately, our theoretical analysis and algorithm provide a ready-to-use solution for building more fair and robust visual foundation models. --- ### Voice Privacy from an Attribute-based Perspective Authors: Mehtab Ur Rahman, Martha Larson, Cristian Tejedor-Garcia Published: 2026-03-19 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2603.20301v3 Voice privacy approaches that preserve the anonymity of speakers modify speech in an attempt to break the link with the true identity of the speaker. Current benchmarks measure speaker protection based on signal-to-signal comparisons. In this paper, we introduce an attribute-based perspective, where we measure privacy protection in terms of comparisons between sets of speaker attributes. First, we analyze privacy impact by calculating speaker uniqueness for ground truth attributes, attributes inferred on the original speech, and attributes inferred on speech protected with standard anonymization. Next, we examine a threat scenario involving only a single utterance per speaker and calculate attack error rates. Overall, we observe that inferred attributes still present a risk despite attribute inference errors. Our research points to the importance of considering both attribute-related threats and protection mechanisms in future voice privacy research. --- ### From Human Interfaces to Agent Interfaces: Rethinking Software Design in the Age of AI-Native Systems Authors: Shaolin Wang, Yi Mei, Haoyang Che, He Jiang, Shui Yu, Ying Gu Published: 2026-03-19 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2603.20300v1 Software systems have traditionally been designed for human interaction, emphasizing graphical user interfaces, usability, and cognitive alignment with end users. However, recent advances in large language model (LLM)-based agents are changing the primary consumers of software systems. Increasingly, software is no longer only used by humans, but also invoked autonomously by AI agents through structured interfaces. In this paper, we argue that software engineering is undergoing a paradigm shift from human-oriented interfaces to agent-oriented invocation systems. We formalize the notion of agent interfaces, introduce invocable capabilities as the fundamental building blocks of AI-oriented software, and outline design principles for such systems, including machine interpretability, composability, and invocation reliability. We then discuss architectural and organizational implications of this shift, highlighting a transition from monolithic applications to capability-based systems that can be dynamically composed by AI agents. The paper aims to provide a conceptual foundation for the emerging paradigm of AI-native software design. --- ### HCAG: Hierarchical Abstraction and Retrieval-Augmented Generation on Theoretical Repositories with LLMs Authors: Yusen Wu, Xiaotie Deng Published: 2026-03-19 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2603.20299v1 Existing Retrieval-Augmented Generation (RAG) methods for code struggle to capture the high-level architectural patterns and cross-file dependencies inherent in complex, theory-driven codebases, such as those in algorithmic game theory (AGT), leading to a persistent semantic and structural gap between abstract concepts and executable implementations. To address this challenge, we propose Hierarchical Code/Architecture-guided Agent Generation (HCAG), a framework that reformulates repository-level code generation as a structured, planning-oriented process over hierarchical knowledge. HCAG adopts a two-phase design: an offline hierarchical abstraction phase that recursively parses code repositories and aligned theoretical texts to construct a multi-resolution semantic knowledge base explicitly linking theory, architecture, and implementation; and an online hierarchical retrieval and scaffolded generation phase that performs top-down, level-wise retrieval to guide LLMs in an architecture-then-module generation paradigm. To further improve robustness and consistency, HCAG integrates a multi-agent discussion inspired by cooperative game. We provide a theoretical analysis showing that hierarchical abstraction with adaptive node compression achieves cost-optimality compared to flat and iterative RAG baselines. Extensive experiments on diverse game-theoretic system generation tasks demonstrate that HCAG substantially outperforms representative repository-level methods in code quality, architectural coherence, and requirement pass rate. In addition, HCAG produces a large-scale, aligned theory-implementation dataset that effectively enhances domain-specific LLMs through post-training. Although demonstrated in AGT, HCAG paradigm also offers a general blueprint for mining, reusing, and generating complex systems from structured codebases in other domains. --- ### Transformer-Based Predictive Maintenance for Risk-Aware Instrument Calibration Authors: Adithya Parthasarathy, Aswathnarayan Muthukrishnan Kirubakaran, Akshay Deshpande, Ram Sekhar Bodala, Suhas Malempati, Nachiappan Chockalingam, Vinoth Punniyamoorthy, Seema Gangaiah Aarella Published: 2026-03-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.20297v1 Accurate calibration is essential for instruments whose measurements must remain traceable, reliable, and compliant over long operating periods. Fixed-interval programs are easy to administer, but they ignore that instruments drift at different rates under different conditions. This paper studies calibration scheduling as a predictive maintenance problem: given recent sensor histories, estimate time-to-drift (TTD) and intervene before a violation occurs. We adapt the NASA C-MAPSS benchmark into a calibration setting by selecting drift-sensitive sensors, defining virtual calibration thresholds, and inserting synthetic reset events that emulate repeated recalibration. We then compare classical regressors, recurrent and convolutional sequence models, and a compact Transformer for TTD prediction. The Transformer provides the strongest point forecasts on the primary FD001 split and remains competitive on the harder FD002--FD004 splits, while a quantile-based uncertainty model supports conservative scheduling when drift behavior is noisier. Under a violation-aware cost model, predictive scheduling lowers cost relative to reactive and fixed policies, and uncertainty-aware triggers sharply reduce violations when point forecasts are less reliable. The results show that condition-based calibration can be framed as a joint forecasting and decision problem, and that combining sequence models with risk-aware policies is a practical route toward smarter calibration planning. --- ### Collaborative Adaptive Curriculum for Progressive Knowledge Distillation Authors: Jing Liu, Zhenchao Ma, Han Yu, Bobo Ju, Wenliang Yang, Chengfang Li, Bo Hu, Liang Song Published: 2026-03-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.20296v1 Recent advances in collaborative knowledge distillation have demonstrated cutting-edge performance for resource-constrained distributed multimedia learning scenarios. However, achieving such competitiveness requires addressing a fundamental mismatch: high-dimensional teacher knowledge complexity versus heterogeneous client learning capacities, which currently prohibits deployment in edge-based visual analytics systems. Drawing inspiration from curriculum learning principles, we introduce Federated Adaptive Progressive Distillation (FAPD), a consensus-driven framework that orchestrates adaptive knowledge transfer. FAPD hierarchically decomposes teacher features via PCA-based structuring, extracting principal components ordered by variance contribution to establish a natural visual knowledge hierarchy. Clients progressively receive knowledge of increasing complexity through dimension-adaptive projection matrices. Meanwhile, the server monitors network-wide learning stability by tracking global accuracy fluctuations across a temporal consensus window, advancing curriculum dimensionality only when collective consensus emerges. Consequently, FAPD provably adapts knowledge transfer pace while achieving superior convergence over fixed-complexity approaches. Extensive experiments on three datasets validate FAPD's effectiveness: it attains 3.64% accuracy improvement over FedAvg on CIFAR-10, demonstrates 2x faster convergence, and maintains robust performance under extreme data heterogeneity (α=0.1), outperforming baselines by over 4.5%. --- ### MARLIN: Multi-Agent Reinforcement Learning for Incremental DAG Discovery Authors: Dong Li, Zhengzhang Chen, Xujiang Zhao, Linlin Yu, Zhong Chen, Yi He, Haifeng Chen, Chen Zhao Published: 2026-03-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.20295v1 Uncovering causal structures from observational data is crucial for understanding complex systems and making informed decisions. While reinforcement learning (RL) has shown promise in identifying these structures in the form of a directed acyclic graph (DAG), existing methods often lack efficiency, making them unsuitable for online applications. In this paper, we propose MARLIN, an efficient multi agent RL based approach for incremental DAG learning. MARLIN uses a DAG generation policy that maps a continuous real valued space to the DAG space as an intra batch strategy, then incorporates two RL agents state specific and state invariant to uncover causal relationships and integrates these agents into an incremental learning framework. Furthermore, the framework leverages a factored action space to enhance parallelization efficiency. Extensive experiments on synthetic and real datasets demonstrate that MARLIN outperforms state of the art methods in terms of both efficiency and effectiveness. --- ### LLM-Enhanced Energy Contrastive Learning for Out-of-Distribution Detection in Text-Attributed Graphs Authors: Xiaoxu Ma, Dong Li, Minglai Shao, Xintao Wu, Chen Zhao Published: 2026-03-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.20293v1 Text-attributed graphs, where nodes are enriched with textual attributes, have become a powerful tool for modeling real-world networks such as citation, social, and transaction networks. However, existing methods for learning from these graphs often assume that the distributions of training and testing data are consistent. This assumption leads to significant performance degradation when faced with out-of-distribution (OOD) data. In this paper, we address the challenge of node-level OOD detection in text-attributed graphs, with the goal of maintaining accurate node classification while simultaneously identifying OOD nodes. We propose a novel approach, LLM-Enhanced Energy Contrastive Learning for Out-of-Distribution Detection in Text-Attributed Graphs (LECT), which integrates large language models (LLMs) and energy-based contrastive learning. The proposed method involves generating high-quality OOD samples by leveraging the semantic understanding and contextual knowledge of LLMs to create dependency-aware pseudo-OOD nodes, and applying contrastive learning based on energy functions to distinguish between in-distribution (IND) and OOD nodes. The effectiveness of our method is demonstrated through extensive experiments on six benchmark datasets, where our method consistently outperforms state-of-the-art baselines, achieving both high classification accuracy and robust OOD detection capabilities. --- ### HSI Image Enhancement Classification Based on Knowledge Distillation: A Study on Forgetting Authors: Songfeng Zhu Published: 2026-03-19 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.20292v1 In incremental classification tasks for hyperspectral images, catastrophic forgetting is an unavoidable challenge. While memory recall methods can mitigate this issue, they heavily rely on samples from old categories. This paper proposes a teacher-based knowledge retention method for incremental image classification. It alleviates model forgetting of old category samples by utilizing incremental category samples, without depending on old category samples. Additionally, this paper introduces a mask-based partial category knowledge distillation algorithm. By decoupling knowledge distillation, this approach filters out potentially misleading information that could misguide the student model, thereby enhancing overall accuracy. Comparative and ablation experiments demonstrate the proposed method's robust performance. --- ### dinov3.seg: Open-Vocabulary Semantic Segmentation with DINOv3 Authors: Saikat Dutta, Biplab Banerjee, Hamid Rezatofighi Published: 2026-03-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.19531v1 Open-Vocabulary Semantic Segmentation (OVSS) assigns pixel-level labels from an open set of text-defined categories, demanding reliable generalization to unseen classes at inference. Although modern vision-language models (VLMs) support strong open-vocabulary recognition, their representations learned through global contrastive objectives remain suboptimal for dense prediction, prompting many OVSS methods to depend on limited adaptation or refinement of image-text similarity maps. This, in turn, restricts spatial precision and robustness in complex, cluttered scenes. We introduce dinov3.seg, extending dinov3.txt into a dedicated framework for OVSS. Our contributions are four-fold. First, we design a task-specific architecture tailored to this backbone, systematically adapting established design principles from prior open-vocabulary segmentation work. Second, we jointly leverage text embeddings aligned with both the global (CLS) token and local patch-level visual features from ViT-based encoder, effectively combining semantic discrimination with fine-grained spatial locality. Third, unlike prior approaches that rely primarily on post hoc similarity refinement, we perform early refinement of visual representations prior to image-text interaction, followed by late refinement of the resulting image-text correlation features, enabling more accurate and robust dense predictions in cluttered scenes. Finally, we propose a high-resolution local-global inference strategy based on sliding-window aggregation, which preserves spatial detail while maintaining global context. We conduct extensive experiments on five widely adopted OVSS benchmarks to evaluate our approach. The results demonstrate its effectiveness and robustness, consistently outperforming current state-of-the-art methods. --- ### SurfaceXR: Fusing Smartwatch IMUs and Egocentric Hand Pose for Seamless Surface Interactions Authors: Vasco Xu, Brian Chen, Eric J. Gonzalez, Andrea Colaço, Henry Hoffmann, Mar Gonzalez-Franco, Karan Ahuja Published: 2026-03-19 Categories: cs.CV, cs.HC, cs.LG arXiv: https://arxiv.org/abs/2603.19529v1 Mid-air gestures in Extended Reality (XR) often cause fatigue and imprecision. Surface-based interactions offer improved accuracy and comfort, but current egocentric vision methods struggle due to hand tracking challenges and unreliable surface plane estimation. We introduce SurfaceXR, a sensor fusion approach combining headset-based hand tracking with smartwatch IMU data to enable robust inputs on everyday surfaces. Our insight is that these modalities are complementary: hand tracking provides 3D positional data while IMUs capture high-frequency motion. A 21-participant study validates SurfaceXR's effectiveness for touch tracking and 8-class gesture recognition, demonstrating significant improvements over single-modality approaches. --- ### Depictions of Depression in Generative AI Video Models: A Preliminary Study of OpenAI's Sora 2 Authors: Matthew Flathers, Griffin Smith, Julian Herpertz, Zhitong Zhou, John Torous Published: 2026-03-19 Categories: cs.CY, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2603.19527v1 Generative video models are increasingly capable of producing complex depictions of mental health experiences, yet little is known about how these systems represent conditions like depression. This study characterizes how OpenAI's Sora 2 generative video model depicts depression and examines whether depictions differ between the consumer App and developer API access points. We generated 100 videos using the single-word prompt "Depression" across two access points: the consumer App (n=50) and developer API (n=50). Two trained coders independently coded narrative structure, visual environments, objects, figure demographics, and figure states. Computational features across visual aesthetics, audio, semantic content, and temporal dynamics were extracted and compared between modalities. App-generated videos exhibited a pronounced recovery bias: 78% (39/50) featured narrative arcs progressing from depressive states toward resolution, compared with 14% (7/50) of API outputs. App videos brightened over time (slope = 2.90 brightness units/second vs. -0.18 for API; d = 1.59, q < .001) and contained three times more motion (d = 2.07, q < .001). Across both modalities, videos converged on a narrow visual vocabulary and featured recurring objects including hoodies (n=194), windows (n=148), and rain (n=83). Figures were predominantly young adults (88% aged 20-30) and nearly always alone (98%). Gender varied by access point: App outputs skewed male (68%), API outputs skewed female (59%). Sora 2 does not invent new visual grammars for depression but compresses and recombines cultural iconographies, while platform-level constraints substantially shape which narratives reach users. Clinicians should be aware that AI-generated mental health video content reflects training data and platform design rather than clinical knowledge, and that patients may encounter such content during vulnerable periods. --- ### Recognising BSL Fingerspelling in Continuous Signing Sequences Authors: Alyssa Chan, Taein Kwon, Andrew Zisserman Published: 2026-03-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.19523v2 Fingerspelling is a critical component of British Sign Language (BSL), used to spell proper names, technical terms, and words that lack established lexical signs. Fingerspelling recognition is challenging due to the rapid pace of signing and common letter omissions by native signers, while existing BSL fingerspelling datasets are either small in scale or temporally and letter-wise inaccurate. In this work, we introduce a new large-scale BSL fingerspelling dataset, FS23K, constructed using an iterative annotation framework. In addition, we propose a fingerspelling recognition model that explicitly accounts for bi-manual interactions and mouthing cues. As a result, with refined annotations, our approach halves the character error rate (CER) compared to the prior state of the art on fingerspelling recognition. These findings demonstrate the effectiveness of our method and highlight its potential to support future research in sign language understanding and scalable, automated annotation pipelines. The project page can be found at https://taeinkwon.com/projects/fs23k/. --- ### Recognising BSL Fingerspelling in Continuous Signing Sequences Authors: Alyssa Chan, Taein Kwon, Andrew Zisserman Published: 2026-03-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.19523v1 Fingerspelling is a critical component of British Sign Language (BSL), used to spell proper names, technical terms, and words that lack established lexical signs. Fingerspelling recognition is challenging due to the rapid pace of signing and common letter omissions by native signers, while existing BSL fingerspelling datasets are either small in scale or temporally and letter-wise inaccurate. In this work, we introduce a new large-scale BSL fingerspelling dataset, FS23K, constructed using an iterative annotation framework. In addition, we propose a fingerspelling recognition model that explicitly accounts for bi-manual interactions and mouthing cues. As a result, with refined annotations, our approach halves the character error rate (CER) compared to the prior state of the art on fingerspelling recognition. These findings demonstrate the effectiveness of our method and highlight its potential to support future research in sign language understanding and scalable, automated annotation pipelines. The project page can be found at https://taeinkwon.com/projects/fs23k/. --- ### Inducing Sustained Creativity and Diversity in Large Language Models Authors: Queenie Luo, Gary King, Michael Puett, Michael D. Smith Published: 2026-03-19 Categories: cs.CL, cs.AI, cs.CY, cs.IR arXiv: https://arxiv.org/abs/2603.19519v2 We address a not-widely-recognized subset of exploratory search, where a user sets out on a typically long "search quest" for the perfect wedding dress, overlooked research topic, killer company idea, etc. The first few outputs of current large language models (LLMs) may be helpful but only as a start, since the quest requires learning the search space and evaluating many diverse and creative alternatives along the way. Although LLMs encode an impressive fraction of the world's knowledge, common decoding methods are narrowly optimized for prompts with correct answers and thus return mostly homogeneous and conventional results. Other approaches, including those designed to increase diversity across a small set of answers, start to repeat themselves long before search quest users learn enough to make final choices, or offer a uniform type of "creativity" to every user asking similar questions. We develop a novel, easy-to-implement decoding scheme that induces sustained creativity and diversity in LLMs, producing as many conceptually unique results as desired, even without access to the inner workings of an LLM's vector space. The algorithm unlocks an LLM's vast knowledge, both orthodox and heterodox, well beyond modal decoding paths. With this approach, search quest users can more quickly explore the search space and find satisfying answers. --- ### ReXInTheWild: A Unified Benchmark for Medical Photograph Understanding Authors: Oishi Banerjee, Sung Eun Kim, Alexandra N. Willauer, Julius M. Kernbach, Abeer Rihan Alomaish, Reema Abdulwahab S. Alghamdi, Hassan Rayhan Alomaish, Mohammed Baharoon, Xiaoman Zhang, Julian Nicolas Acosta, Christine Zhou, Pranav Rajpurkar Published: 2026-03-19 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.19517v1 Everyday photographs taken with ordinary cameras are already widely used in telemedicine and other online health conversations, yet no comprehensive benchmark evaluates whether vision-language models can interpret their medical content. Analyzing these images requires both fine-grained natural image understanding and domain-specific medical reasoning, a combination that challenges both general-purpose and specialized models. We introduce ReXInTheWild, a benchmark of 955 clinician-verified multiple-choice questions spanning seven clinical topics across 484 photographs sourced from the biomedical literature. When evaluated on ReXInTheWild, leading multimodal large language models show substantial performance variation: Gemini-3 achieves 78% accuracy, followed by Claude Opus 4.5 (72%) and GPT-5 (68%), while the medical specialist model MedGemma reaches only 37%. A systematic error analysis also reveals four categories of common errors, ranging from low-level geometric errors to high-level reasoning failures and requiring different mitigation strategies. ReXInTheWild provides a challenging, clinically grounded benchmark at the intersection of natural image understanding and medical reasoning. The dataset is available on HuggingFace. --- ### Gastric-X: A Multimodal Multi-Phase Benchmark Dataset for Advancing Vision-Language Models in Gastric Cancer Analysis Authors: Sheng Lu, Hao Chen, Rui Yin, Juyan Ba, Yu Zhang, Yuanzhe Li Published: 2026-03-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.19516v2 Recent vision-language models (VLMs) have shown strong generalization and multimodal reasoning abilities in natural domains. However, their application to medical diagnosis remains limited by the lack of comprehensive and structured datasets that capture real clinical workflows. To advance the development of VLMs for clinical applications, particularly in gastric cancer, we introduce Gastric-X, a large-scale multimodal benchmark for gastric cancer analysis providing 1.7K cases. Each case in Gastric-X includes paired resting and dynamic CT scans, endoscopic image, a set of structured biochemical indicators, expert-authored diagnostic notes, and bounding box annotations of tumor regions, reflecting realistic clinical conditions. We systematically examine the capability of recent VLMs on five core tasks: Visual Question Answering (VQA), report generation, cross-modal retrieval, disease classification, and lesion localization. These tasks simulate critical stages of clinical workflow, from visual understanding and reasoning to multimodal decision support. Through this evaluation, we aim not only to assess model performance but also to probe the nature of VLM understanding: Can current VLMs meaningfully correlate biochemical signals with spatial tumor features and textual reports? We envision Gastric-X as a step toward aligning machine intelligence with the cognitive and evidential reasoning processes of physicians, and as a resource to inspire the development of next-generation medical VLMs. --- ### ItinBench: Benchmarking Planning Across Multiple Cognitive Dimensions with Large Language Models Authors: Tianlong Wang, Pinqiao Wang, Weili Shi, Sheng li Published: 2026-03-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.19515v1 Large language models (LLMs) with advanced cognitive capabilities are emerging as agents for various reasoning and planning tasks. Traditional evaluations often focus on specific reasoning or planning questions within controlled environments. Recent studies have explored travel planning as a medium to integrate various verbal reasoning tasks into real-world contexts. However, reasoning tasks extend beyond verbal reasoning alone, and a comprehensive evaluation of LLMs requires a testbed that incorporates tasks from multiple cognitive domains. To address this gap, we introduce ItinBench, a benchmark that features one task of spatial reasoning, i.e., route optimization, into trip itinerary planning while keeping the traditional verbal reasoning tasks. ItinBench evaluates various LLMs across diverse tasks simultaneously, including Llama 3.1 8B, Mistral Large, Gemini 1.5 Pro, and GPT family. Our findings reveal that LLMs struggle to maintain high and consistent performance when concurrently handling multiple cognitive dimensions. By incorporating tasks from distinct human-level cognitive domains, ItinBench provides new insights into building more comprehensive reasoning testbeds that better reflect real-world challenges. The code and dataset: https://ethanwtl.github.io/IBweb/ --- ### Learning to Disprove: Formal Counterexample Generation with Large Language Models Authors: Zenan Li, Zhaoyu Li, Kaiyu Yang, Xiaoxing Ma, Zhendong Su Published: 2026-03-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.19514v1 Mathematical reasoning demands two critical, complementary skills: constructing rigorous proofs for true statements and discovering counterexamples that disprove false ones. However, current AI efforts in mathematics focus almost exclusively on proof construction, often neglecting the equally important task of finding counterexamples. In this paper, we address this gap by fine-tuning large language models (LLMs) to reason about and generate counterexamples. We formalize this task as formal counterexample generation, which requires LLMs not only to propose candidate counterexamples but also to produce formal proofs that can be automatically verified in the Lean 4 theorem prover. To enable effective learning, we introduce a symbolic mutation strategy that synthesizes diverse training data by systematically extracting theorems and discarding selected hypotheses, thereby producing diverse counterexample instances. Together with curated datasets, this strategy enables a multi-reward expert iteration framework that substantially enhances both the effectiveness and efficiency of training LLMs for counterexample generation and theorem proving. Experiments on three newly collected benchmarks validate the advantages of our approach, showing that the mutation strategy and training framework yield significant performance gains. --- ### FedAgain: A Trust-Based and Robust Federated Learning Strategy for an Automated Kidney Stone Identification in Ureteroscopy Authors: Ivan Reyes-Amezcua, Francisco Lopez-Tiro, Clément Larose, Christian Daul, Andres Mendez-Vazquez, Gilberto Ochoa-Ruiz Published: 2026-03-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.19512v1 The reliability of artificial intelligence (AI) in medical imaging critically depends on its robustness to heterogeneous and corrupted images acquired with diverse devices across different hospitals which is highly challenging. Therefore, this paper introduces FedAgain, a trust-based Federated Learning (Federated Learning) strategy designed to enhance robustness and generalization for automated kidney stone identification from endoscopic images. FedAgain integrates a dual trust mechanism that combines benchmark reliability and model divergence to dynamically weight client contributions, mitigating the impact of noisy or adversarial updates during aggregation. The framework enables the training of collaborative models across multiple institutions while preserving data privacy and promoting stable convergence under real-world conditions. Extensive experiments across five datasets, including two canonical benchmarks (MNIST and CIFAR-10), two private multi-institutional kidney stone datasets, and one public dataset (MyStone), demonstrate that FedAgain consistently outperforms standard Federated Learning baselines under non-identically and independently distributed (non-IID) data and corrupted-client scenarios. By maintaining diagnostic accuracy and performance stability under varying conditions, FedAgain represents a practical advance toward reliable, privacy-preserving, and clinically deployable federated AI for medical imaging. --- ### Linear Social Choice with Few Queries: A Moment-Based Approach Authors: Luise Ge, Daniel Halpern, Gregory Kehne, Yevgeniy Vorobeychik Published: 2026-03-19 Categories: cs.GT, cs.AI arXiv: https://arxiv.org/abs/2603.19510v1 Most social choice rules assume access to full rankings, while current alignment practice -- despite aiming for diversity -- typically treats voters as anonymous and comparisons as independent, effectively extracting only about one bit per voter. Motivated by this gap, we study social choice under an extreme communication budget in the linear social choice model, where each voter's utility is the inner product between a latent voter type and the embedding of the context and candidate. The candidate and voter spaces may be very large or even infinite. Our core idea is to model the electorate as an unknown distribution over voter types and to recover its moments as informative summary statistics for candidate selection. We show that one pairwise comparison per voter already suffices to select a candidate that maximizes social welfare, but this elicitation cannot identify the second moment and therefore cannot support objectives that account for inequality. We prove that two pairwise comparisons per voter, or alternatively a single graded comparison, identify the second moment; moreover, these richer queries suffice to identify all moments, and hence the entire voter-type distribution. These results enable principled solutions to a range of social choice objectives including inequality-aware welfare criteria such as taking into account the spread of voter utilities and choosing a representative subset. --- ### Beyond the Desk: Barriers and Future Opportunities for AI to Assist Scientists in Embodied Physical Tasks Authors: Irene Hou, Alexander Qin, Lauren Cheng, Philip J. Guo Published: 2026-03-19 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2603.19504v1 More scientists are now using AI, but prior studies have examined only how they use it 'at the desk' for computer-based work. However, given that scientific work often happens 'beyond the desk' at lab and field sites, we conducted the first study of how scientific practitioners use AI for embodied physical tasks. We interviewed 12 scientific practitioners doing hands-on lab and fieldwork in domains like nuclear fusion, primate cognition, and biochemistry, and found three barriers to AI adoption in these settings: 1) experimental setups are too high-stakes to risk AI errors, 2) constrained environments make it hard to use AI, and 3) AI cannot match the tacit knowledge of humans. Participants then developed speculative designs for future AI assistants to 1) monitor task status, 2) organize lab-wide knowledge, 3) monitor scientists' health, 4) do field scouting, 5) do hands-on chores. Our findings point toward AI as background infrastructure to support physical work rather than replacing human expertise. --- ### Vision Tiny Recursion Model (ViTRM): Parameter-Efficient Image Classification via Recursive State Refinement Authors: Ange-Clément Akazan, Abdoulaye Koroko, Verlon Roel Mbingui, Choukouriyah Arinloye, Hassan Fifen, Rose Bandolo Published: 2026-03-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.19503v2 The success of deep learning in computer vision has been driven by models of increasing scale, from deep Convolutional Neural Networks (CNN) to large Vision Transformers (ViT). While effective, these architectures are parameter-intensive and demand significant computational resources, limiting deployment in resource-constrained environments. Inspired by Tiny Recursive Models (TRM), which show that small recursive networks can solve complex reasoning tasks through iterative state refinement, we introduce the \textbf{Vision Tiny Recursion Model (ViTRM)}: a parameter-efficient architecture that replaces the $L$-layer ViT encoder with a single tiny $k$-layer block ($k{=}3$) applied recursively $N$ times. Despite using up to $6 \times $ and $84 \times$ fewer parameters than CNN based models and ViT respectively, ViTRM maintains competitive performance on CIFAR-10 and CIFAR-100. This demonstrates that recursive computation is a viable, parameter-efficient alternative to architectural depth in vision. --- ### Stochastic Sequential Decision Making over Expanding Networks with Graph Filtering Authors: Zhan Gao, Bishwadeep Das, Elvin Isufi Published: 2026-03-19 Categories: cs.LG, eess.SP arXiv: https://arxiv.org/abs/2603.19501v1 Graph filters leverage topological information to process networked data with existing methods mainly studying fixed graphs, ignoring that graphs often expand as nodes continually attach with an unknown pattern. The latter requires developing filter-based decision-making paradigms that take evolution and uncertainty into account. Existing approaches rely on either pre-designed filters or online learning, limited to a myopic view considering only past or present information. To account for future impacts, we propose a stochastic sequential decision-making framework for filtering networked data with a policy that adapts filtering to expanding graphs. By representing filter shifts as agents, we model the filter as a multi-agent system and train the policy following multi-agent reinforcement learning. This accounts for long-term rewards and captures expansion dynamics through sequential decision-making. Moreover, we develop a context-aware graph neural network to parameterize the policy, which tunes filter parameters based on information of both the graph and agents. Experiments on synthetic and real datasets from cold-start recommendation to COVID prediction highlight the benefits of using a sequential decision-making perspective over batch and online filtering alternatives. --- ### Teaching an Agent to Sketch One Part at a Time Authors: Xiaodan Du, Ruize Xu, David Yunis, Yael Vinker, Greg Shakhnarovich Published: 2026-03-19 Categories: cs.AI, cs.CV, cs.GR, cs.LG arXiv: https://arxiv.org/abs/2603.19500v2 We develop a method for producing vector sketches one part at a time. To do this, we train a multi-modal language model-based agent using a novel multi-turn process-reward reinforcement learning following supervised fine-tuning. Our approach is enabled by a new dataset we call ControlSketch-Part, containing rich part-level annotations for sketches, obtained using a novel, generic automatic annotation pipeline that segments vector sketches into semantic parts and assigns paths to parts with a structured multi-stage labeling process. Our results indicate that incorporating structured part-level data and providing agent with the visual feedback through the process enables interpretable, controllable, and locally editable text-to-vector sketch generation. ---