# Research Papers — 2026-03 · bundle page 29 of 243 > Full-text markdown of papers #1401–1450 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/29 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/28.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/30.md) ### Water-Filling is Universally Minimax Optimal Authors: Siddhartha Banerjee, Ramiro N. Deo-Campo Vuong, Robert Kleinberg Published: 2026-03-27 Categories: cs.DS, cs.GT, cs.LG arXiv: https://arxiv.org/abs/2603.26893v1 Allocation of dynamically-arriving (i.e., online) divisible resources among a set of offline agents is a fundamental problem, with applications to online marketplaces, scheduling, portfolio selection, signal processing, and many other areas. The water-filling algorithm, which allocates an incoming resource to maximize the minimum load of compatible agents, is ubiquitous in many of these applications whenever the underlying objectives prefer more balanced solutions; however, the analysis and guarantees differ across settings. We provide a justification for the widespread use of water-filling by showing that it is a universally minimax optimal policy in a strong sense. Formally, our main result implies that water-filling is minimax optimal for a large class of objectives -- including both Schur-concave maximization and Schur-convex minimization -- under $α$-regret and competitive ratio measures. This optimality holds for every fixed tuple of agents and resource counts. Remarkably, water-filling achieves these guarantees as a myopic policy, remaining entirely agnostic to the objective function, agent count, and resource availability. Our techniques notably depart from the popular primal-dual analysis of online algorithms, and instead develop a novel way to apply the theory of majorization in online settings to achieve universality guarantees. --- ### Strategic Candidacy in Generative AI Arenas Authors: Chris Hays, Rachel Li, Bailey Flanigan, Manish Raghavan Published: 2026-03-27 Categories: cs.LG, cs.AI, cs.GT arXiv: https://arxiv.org/abs/2603.26891v1 AI arenas, which rank generative models from pairwise preferences of users, are a popular method for measuring the relative performance of models in the course of their organic use. Because rankings are computed from noisy preferences, there is a concern that model producers can exploit this randomness by submitting many models (e.g., multiple variants of essentially the same model) and thereby artificially improve the rank of their top models. This can lead to degradations in the quality, and therefore the usefulness, of the ranking. In this paper, we begin by establishing, both theoretically and in simulations calibrated to data from the platform Arena (formerly LMArena, Chatbot Arena), conditions under which producers can benefit from submitting clones when their goal is to be ranked highly. We then propose a new mechanism for ranking models from pairwise comparisons, called You-Rank-We-Rank (YRWR). It requires that producers submit rankings over their own models and uses these rankings to correct statistical estimates of model quality. We prove that this mechanism is approximately clone-robust, in the sense that a producer cannot improve their rank much by doing anything other than submitting each of their unique models exactly once. Moreover, to the extent that model producers are able to correctly rank their own models, YRWR improves overall ranking accuracy. In further simulations, we show that indeed the mechanism is approximately clone-robust and quantify improvements to ranking accuracy, even under producer misranking. --- ### Privacy-Preserving Iris Recognition: Performance Challenges and Outlook Authors: Christina Karakosta, Lian Alhedaithy, William J. Knottenbelt Published: 2026-03-27 Categories: cs.CR, cs.CV arXiv: https://arxiv.org/abs/2603.26890v1 Iris-based biometric identification is increasingly recognized for its significant accuracy and long-term stability compared to other biometric modalities such as fingerprints or facial features. However, all biometric modalities are highly sensitive data that raise serious privacy and security concerns, particularly in decentralized and untrusted environments. While Fully Homomorphic Encryption (FHE) has emerged as a promising solution for protecting sensitive data during computation, existing privacy-preserving iris recognition systems face significant performance limitations that hinder their practical deployment. This paper investigates the performance challenges of the current landscape of privacy-preserving iris recognition systems using FHE. Based on these insights, we outline a scalable privacy-preserving framework that aligns with all the requirements specified in the ISO/IEC 24745 standard. Leveraging the Open Iris library, our approach starts with robust iris segmentation, followed by normalization and feature extraction using Gabor filters to generate iris codes. We then apply binary masking to filter out unreliable regions and perform matching using Hamming distance on encrypted iris codes. The accuracy and performance of our proposed privacy-preserving framework is evaluated on the CASIA-Iris-Thousand dataset. Results show that our privacy-preserving framework yields very similar accuracy to the cleartext equivalent, but a much higher computational overhead with respect to pairwise iris template comparisons, of $\sim 120\,000 \times$. This points towards the need for the deployment of two-level schemes in the context of scalable $1-N$ template comparisons. --- ### Property-Guided Molecular Generation and Optimization via Latent Flows Authors: Alexander Arjun Lobo, Urvi Awasthi, Leonid Zhukov Published: 2026-03-27 Categories: cs.LG, cond-mat.mtrl-sci arXiv: https://arxiv.org/abs/2603.26889v1 Molecular discovery is increasingly framed as an inverse design problem: identifying molecular structures that satisfy desired property profiles under feasibility constraints. While recent generative models provide continuous latent representations of chemical space, targeted optimization within these representations often leads to degraded validity, loss of structural fidelity, or unstable behavior. We introduce MoltenFlow, a modular framework that combines property-organized latent representations with flow-matching generative priors and gradient-based guidance. This formulation supports both conditioned generation and local optimization within a single latent-space framework. We show that guided latent flows enable efficient multi-objective molecular optimization under fixed oracle budgets with controllable trade-offs, while a learned flow prior improves unconditional generation quality. --- ### TTE-CAM: Self-Explainable Class Activation Maps for Pretrained Black-Box CNNs Authors: Kerol Djoumessi, Philipp Berens Published: 2026-03-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.26885v2 Convolutional neural networks (CNNs) achieve state-of-the-art performance in medical image analysis yet remain opaque, limiting adoption in high-stakes clinical settings. Existing approaches face a fundamental trade-off: post-hoc methods provide unfaithful approximate explanations, while inherently interpretable architectures are faithful but often sacrifice predictive performance. We introduce TTE-CAM, a test-time framework that bridges this gap by converting pretrained black-box CNNs into self-explainable models via a convolution-based replacement of their classification head, initialized from the original weights. The resulting model preserves black-box predictive performance while delivering built-in faithful explanations competitive with post-hoc methods, both qualitatively and quantitatively. The code is available at https://github.com/kdjoumessi/Test-Time-Explainability --- ### LACON: Training Text-to-Image Model from Uncurated Data Authors: Zhiyang Liang, Ziyu Wan, Hongyu Liu, Dong Chen, Qiu Shen, Hao Zhu, Dongdong Chen Published: 2026-03-27 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.26866v1 The success of modern text-to-image generation is largely attributed to massive, high-quality datasets. Currently, these datasets are curated through a filter-first paradigm that aggressively discards low-quality raw data based on the assumption that it is detrimental to model performance. Is the discarded bad data truly useless, or does it hold untapped potential? In this work, we critically re-examine this question. We propose LACON (Labeling-and-Conditioning), a novel training framework that exploits the underlying uncurated data distribution. Instead of filtering, LACON re-purposes quality signals, such as aesthetic scores and watermark probabilities as explicit, quantitative condition labels. The generative model is then trained to learn the full spectrum of data quality, from bad to good. By learning the explicit boundary between high- and low-quality content, LACON achieves superior generation quality compared to baselines trained only on filtered data using the same compute budget, proving the significant value of uncurated data. --- ### A federated architecture for sector-led AI governance: lessons from India Authors: Avinash Agarwal, Manisha J. Nene Published: 2026-03-27 Categories: cs.CY, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2603.26865v1 Purpose: India has adopted a vertical, sector-led AI governance strategy. While promoting innovation, such a light-touch approach risks policy fragmentation. This paper aims to propose a cohesive "whole-of-government" architecture to mitigate these risks and connect policy goals with a practical implementation plan. Design/methodology/approach: The paper applies an established five-layer conceptual framework to the Indian context. First, it constructs a national architecture for overall governance. Second, it uses a detailed case study on AI incident management to validate and demonstrate the architecture's practical utility in designing a specific, operational system. Findings: The paper develops two actionable architectures. The primary model assigns clear governance roles to India's key institutions. The second is a detailed, federated architecture for national AI Incident Management. It addresses the data silo problem by using a common national standard that allows sector-specific data collection while facilitating cross-sectoral analysis. Practical implications: The proposed architectures offer a clear and predictable roadmap for India's policymakers, regulators and industry to accelerate the national AI governance agenda. Social implications: By providing a systematic path from policy to practice, the architecture builds public trust. This structured approach ensures accountability and aligns AI development with societal values. Originality/value: This paper proposes a detailed operational architecture for India's "whole-of-government" approach to AI. It offers a globally relevant template for any nation pursuing a sector-led governance model, providing a clear implementation plan. Furthermore, the proposed federated architecture demonstrates how adopting common standards can enable cross-border data aggregation and global sectoral risk analysis without centralising control. --- ### EZASP - Facilitating the Usage of ASP Authors: Rafael Martins, Matthias Knorr, Ricardo Gonçalves Published: 2026-03-27 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2603.26863v2 Answer Set Programming (ASP) is a declarative programming language used for modeling and solving complex combinatorial problems. It has been successfully applied to a number of different real-world problems. However, learning its usage can prove challenging as the declarative language, from a conceptual perspective, differs substantially from imperative programming, and programs are not required to adhere to any particular structure, offering arguably almost too much freedom for a beginner. Recently, a new methodology called Easy Answer Set Programming (Easy ASP) has been introduced that aims to aid in this learning process by focussing on a well-defined fragment of the ASP language and introducing additional structure to the programs. However, while this methodology can indeed be employed, to the best of our knowledge, no tool integrates its features currently. In this paper, we present EZASP, a Visual Studio Code extension designed to support the development of ASP programs following the Easy ASP methodology. It covers and extends the language fragment of Easy ASP and provides the user with warnings in the case of deviations from the methodology as well as the possibility to automatically reorder the program. Complementarily, it also adds syntax error highlighting, including detection of non-safe variables directly while editing, and configurability, as all features can be optionally disabled. A small user study in the context of university teaching suggests that these features are benefitial for both new and experienced users. --- ### Beyond Textual Knowledge-Leveraging Multimodal Knowledge Bases for Enhancing Vision-and-Language Navigation Authors: Dongsheng Yang, Yinfeng Yu, Liejun Wang Published: 2026-03-27 Categories: cs.CV, cs.AI, eess.IV arXiv: https://arxiv.org/abs/2603.26859v1 Vision-and-Language Navigation (VLN) requires an agent to navigate through complex unseen environments based on natural language instructions. However, existing methods often struggle to effectively capture key semantic cues and accurately align them with visual observations. To address this limitation, we propose Beyond Textual Knowledge (BTK), a VLN framework that synergistically integrates environment-specific textual knowledge with generative image knowledge bases. BTK employs Qwen3-4B to extract goal-related phrases and utilizes Flux-Schnell to construct two large-scale image knowledge bases: R2R-GP and REVERIE-GP. Additionally, we leverage BLIP-2 to construct a large-scale textual knowledge base derived from panoramic views, providing environment-specific semantic cues. These multimodal knowledge bases are effectively integrated via the Goal-Aware Augmentor and Knowledge Augmentor, significantly enhancing semantic grounding and cross-modal alignment. Extensive experiments on the R2R dataset with 7,189 trajectories and the REVERIE dataset with 21,702 instructions demonstrate that BTK significantly outperforms existing baselines. On the test unseen splits of R2R and REVERIE, SR increased by 5% and 2.07% respectively, and SPL increased by 4% and 3.69% respectively. The source code is available at https://github.com/yds3/IPM-BTK/. --- ### A Hierarchical Sheaf Spectral Embedding Framework for Single-Cell RNA-seq Analysis Authors: Xiang Xiang Wang, Guo-Wei We Published: 2026-03-27 Categories: cs.LG, math.SP, q-bio.GN, stat.ML arXiv: https://arxiv.org/abs/2603.26858v1 Single-cell RNA-seq data analysis typically requires representations that capture heterogeneous local structure across multiple scales while remaining stable and interpretable. In this work, we propose a hierarchical sheaf spectral embedding (HSSE) framework that constructs informative cell-level features based on persistent sheaf Laplacian analysis. Starting from scale-dependent low-dimensional embeddings, we define cell-centered local neighborhoods at multiple resolutions. For each local neighborhood, we construct a data-driven cellular sheaf that encodes local relationships among cells. We then compute persistent sheaf Laplacians over sampled filtration intervals and extract spectral statistics that summarize the evolution of local relational structure across scales. These spectral descriptors are aggregated into a unified feature vector for each cell and can be directly used in downstream learning tasks without additional model training. We evaluate HSSE on twelve benchmark single-cell RNA-seq datasets covering diverse biological systems and data scales. Under a consistent classification protocol, HSSE achieves competitive or improved performance compared with existing multiscale and classical embedding-based methods across multiple evaluation metrics. The results demonstrate that sheaf spectral representations provide a robust and interpretable approach for single-cell RNA-seq data representation learning. --- ### AFSS: Artifact-Focused Self-Synthesis for Mitigating Bias in Audio Deepfake Detection Authors: Hai-Son Nguyen-Le, Hung-Cuong Nguyen-Thanh, Nhien-An Le-Khac, Dinh-Thuc Nguyen, Hong-Hanh Nguyen-Le Published: 2026-03-27 Categories: cs.SD, cs.AI, eess.AS arXiv: https://arxiv.org/abs/2603.26856v1 The rapid advancement of generative models has enabled highly realistic audio deepfakes, yet current detectors suffer from a critical bias problem, leading to poor generalization across unseen datasets. This paper proposes Artifact-Focused Self-Synthesis (AFSS), a method designed to mitigate this bias by generating pseudo-fake samples from real audio via two mechanisms: self-conversion and self-reconstruction. The core insight of AFSS lies in enforcing same-speaker constraints, ensuring that real and pseudo-fake samples share identical speaker identity and semantic content. This forces the detector to focus exclusively on generation artifacts rather than irrelevant confounding factors. Furthermore, we introduce a learnable reweighting loss to dynamically emphasize synthetic samples during training. Extensive experiments across 7 datasets demonstrate that AFSS achieves state-of-the-art performance with an average EER of 5.45\%, including a significant reduction to 1.23\% on WaveFake and 2.70\% on In-the-Wild, all while eliminating the dependency on pre-collected fake datasets. Our code is publicly available at https://github.com/NguyenLeHaiSonGit/AFSS. --- ### Stringological sequence prediction I: efficient algorithms for predicting highly repetitive sequences Authors: Vanessa Kosoy Published: 2026-03-27 Categories: cs.FL, cs.DS, cs.LG arXiv: https://arxiv.org/abs/2603.26852v2 We propose novel algorithms for sequence prediction based on ideas from stringology. These algorithms are time and space efficient and satisfy mistake bounds related to particular stringological complexity measures of the sequence. In this work (the first in a series) we focus on two such measures: (i) the size of the smallest straight-line program that produces the sequence, and (ii) the number of states in the minimal automaton that can compute any symbol in the sequence when given its position in base k as input. These measures are interesting because multiple rich classes of sequences studied in combinatorics of words (automatic sequences, morphic sequences, characteristic words) have low complexity and hence high predictability in this sense. --- ### Stringological sequence prediction I: efficient algorithms for predicting highly repetitive sequences Authors: Vanessa Kosoy Published: 2026-03-27 Categories: cs.FL, cs.DS, cs.LG arXiv: https://arxiv.org/abs/2603.26852v1 We propose novel algorithms for sequence prediction based on ideas from stringology. These algorithms are time and space efficient and satisfy mistake bounds related to particular stringological complexity measures of the sequence. In this work (the first in a series) we focus on two such measures: (i) the size of the smallest straight-line program that produces the sequence, and (ii) the number of states in the minimal automaton that can compute any symbol in the sequence when given its position in base k as input. These measures are interesting because multiple rich classes of sequences studied in combinatorics of words (automatic sequences, morphic sequences, Sturmian words) have low complexity and hence high predictability in this sense. --- ### Dual-View Optical Flow for 4D Micro-Expression Recognition - A Multi-Stream Fusion Attention Approach Authors: Luu Tu Nguyen, Thi Bich Phuong Man, Vu Tram Anh Khuong, Thanh Ha Le, Thi Duyen Ngo Published: 2026-03-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.26849v1 Micro-expression recognition is vital for affective computing but remains challenging due to the extremely brief, low-intensity facial motions involved and the high-dimensional nature of 4D mesh data. To address these challenges, we introduce a dual-view optical flow approach that simplifies mesh processing by capturing each micro-expression sequence from two synchronized viewpoints and computing optical flow to represent motion. Our pipeline begins with view separation and sequence-wise face cropping to ensure spatial consistency, followed by automatic apex-frame detection based on peak motion intensity in both views. We decompose each sequence into onset-apex and apex-offset phases, extracting horizontal, vertical, and magnitude flow channels for each phase. These are fed into our Triple-Stream MicroAttNet, which employs a fusion attention module to adaptively weight modality-specific features and a squeeze-and-excitation block to enhance magnitude representations. Training uses focal loss to mitigate class imbalance and the Adam optimizer with early stopping. Evaluated on the multi-label 4DME dataset, comprising 24 subjects and five emotion categories, in the 4DMR IJCAI Workshop Challenge 2025, our method achieves a macro-UF1 score of 0.536, outperforming the official baseline by over 50\% and securing first place. Ablation studies confirm that both the fusion attention and SE components each contribute up to 3.6 points of UF1 gain. These results demonstrate that dual-view, phase-aware optical flow combined with multi-stream fusion yields a robust and interpretable solution for 4D micro-expression recognition. --- ### Stable Reasoning, Unstable Responses: Mitigating LLM Deception via Stability Asymmetry Authors: Guoxi Zhang, Jiawei Chen, Tianzhuo Yang, Lang Qin, Juntao Dai, Yaodong Yang, Jingwei Yi Published: 2026-03-27 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.26846v2 As Large Language Models (LLMs) expand in capability and application scope, their trustworthiness becomes critical. A vital risk is intrinsic deception, wherein models strategically mislead users to achieve their own objectives. Existing alignment approaches based on chain-of-thought (CoT) monitoring supervise explicit reasoning traces. However, under optimization pressure, models are incentivized to conceal deceptive reasoning, rendering semantic supervision fundamentally unreliable. Grounded in cognitive psychology, we hypothesize that a deceptive LLM maintains a stable internal belief in its CoT while its external response remains fragile under perturbation. We term this phenomenon stability asymmetry and quantify it by measuring the contrast between internal CoT stability and external response stability under perturbation. Building on this structural signature, we propose the Stability Asymmetry Regularization (SAR), a novel alignment objective that penalizes this distributional asymmetry during reinforcement learning. Unlike CoT monitoring, SAR targets the statistical structure of model outputs, rendering it robust to semantic concealment. Extensive experiments confirm that stability asymmetry reliably identifies deceptive behavior, and that SAR effectively suppresses intrinsic deception without degrading general model capability. --- ### GISclaw: A Comprehensive Open-Source LLM Agent System for Realistic Multi-Step Geospatial Analysis Authors: Jinzhen Han, JinByeong Lee, Yuri Shim, Jisung Kim, Jae-Joon Lee Published: 2026-03-27 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2603.26845v2 Most LLM-driven GIS assistants solve narrow single-step tasks tightly coupled to proprietary platforms such as ArcGIS or QGIS, limiting their use for the multi-step, cross-format pipelines that define professional geospatial analysis. We present GISclaw, a comprehensive open-source agent system that performs realistic GIS analysis end to end - spatial joins, raster algebra, kriging interpolation, machine-learning classification, network analysis, choropleth cartography - directly through Python with no commercial GIS dependency. GISclaw couples an LLM reasoning core with a persistent Python sandbox pre-loaded with the open-source geospatial stack, three engineered prompt rules (Schema Analysis, Package Constraint, Domain Knowledge Injection), and an Error-Memory module for self-correction. A single backend-agnostic architecture supports both cloud-API and locally deployed open-weight LLM backends, enabling air-gapped deployment without loss of capability. On GeoAnalystBench - 50 expert-curated multi-step tasks averaging 5.8 analytical steps across vector, raster, and tabular data - GISclaw reaches up to 100% task success and 97% mean success over three independent runs. We further conduct 1,800 controlled experiments (50 tasks x 6 backends x 2 architectures x 3 repeats) with bootstrap 95% CIs, paired Wilcoxon tests, and a composite-score sensitivity analysis (Kendall's tau median = 0.94), and introduce a three-layer evaluation protocol combining code structure, reasoning process, and type-specific output verification. The Single-Agent ReAct loop reliably outperforms the Dual-Agent Plan-Execute-Replan pipeline on every cloud backend (Cliff's delta = 0.15-0.41); only the locally deployed 14B model gains from multi-agent orchestration, suggesting architectural complexity should match model capability rather than be added by default. --- ### Uncertainty-Aware Mapping from 3D Keypoints to Anatomical Landmarks for Markerless Biomechanics Authors: Cesare Davide Pace, Alessandro Marco De Nunzio, Claudio De Stefano, Francesco Fontanella, Mario Molinara Published: 2026-03-27 Categories: eess.IV, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2603.26844v1 Markerless biomechanics increasingly relies on 3D skeletal keypoints extracted from video, yet downstream biomechanical mappings typically treat these estimates as deterministic, providing no principled mechanism for frame-wise quality control. In this work, we investigate predictive uncertainty as a quantitative measure of confidence for mapping 3D pose keypoints to 3D anatomical landmarks, a critical step preceding inverse kinematics and musculoskeletal analysis. Within a temporal learning framework, we model both uncertainty arising from observation noise and uncertainty related to model limitations. Using synchronized motion capture ground truth on AMASS, we evaluate uncertainty at frame and joint level through error--uncertainty rank correlation, risk--coverage analysis, and catastrophic outlier detection. Across experiments, uncertainty estimates, particularly those associated with model uncertainty, exhibit a strong monotonic association with landmark error (Spearman $ρ\approx 0.63$), enabling selective retention of reliable frames (error reduced to $\approx 16.8$ mm at 10% coverage) and accurate detection of severe failures (ROC-AUC $\approx 0.92$ for errors $>50$ mm). Reliability ranking remains stable under controlled input degradation, including Gaussian noise and simulated missing joints. In contrast, uncertainty attributable to observation noise provides limited additional benefit in this setting, suggesting that dominant failures in keypoint-to-landmark mapping are driven primarily by model uncertainty. Our results establish predictive uncertainty as a practical, frame-wise tool for automatic quality control in markerless biomechanical pipelines. --- ### VAN-AD: Visual Masked Autoencoder with Normalizing Flow For Time Series Anomaly Detection Authors: PengYu Chen, Shang Wan, Xiaohou Shi, Yuan Chang, Yan Sun, Sajal K. Das Published: 2026-03-27 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2603.26842v3 Time series anomaly detection (TSAD) is essential for maintaining the reliability and security of IoT-enabled service systems. Existing methods require training one specific model for each dataset, which exhibits limited generalization capability across different target datasets, hindering anomaly detection performance in various scenarios with scarce training data. To address this limitation, foundation models have emerged as a promising direction. However, existing approaches either repurpose large language models (LLMs) or construct largescale time series datasets to develop general anomaly detection foundation models, and still face challenges caused by severe cross-modal gaps or in-domain heterogeneity. In this paper, we investigate the applicability of large-scale vision models to TSAD. Specifically, we adapt a visual Masked Autoencoder (MAE) pretrained on ImageNet to the TSAD task. However, directly transferring MAE to TSAD introduces two key challenges: overgeneralization and limited local perception. To address these challenges, we propose VAN-AD, a novel MAE-based framework for TSAD. To alleviate the over-generalization issue, we design an Adaptive Distribution Mapping Module (ADMM), which maps the reconstruction results before and after MAE into a unified statistical space to amplify discrepancies caused by abnormal patterns. To overcome the limitation of local perception, we further develop a Normalizing Flow Module (NFM), which combines MAE with normalizing flow to estimate the probability density of the current window under the global distribution. Extensive experiments on nine real-world datasets demonstrate that VAN-AD consistently outperforms existing state-of-the-art methods across multiple evaluation metrics.We make our code and datasets available at https://github.com/PenyChen/VAN-AD. --- ### FatigueFormer: Static-Temporal Feature Fusion for Robust sEMG-Based Muscle Fatigue Recognition Authors: Tong Zhang, Hong Guo, Shuangzhou Yan, Dongkai Weng, Jian Wang, Hongxin Zhang Published: 2026-03-27 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.26841v1 We present FatigueFormer, a semi-end-to-end framework that deliberately combines saliency-guided feature separation with deep temporal modeling to learn interpretable and generalizable muscle fatigue dynamics from surface electromyography (sEMG). Unlike prior approaches that struggle to maintain robustness across varying Maximum Voluntary Contraction (MVC) levels due to signal variability and low SNR, FatigueFormer employs parallel Transformer-based sequence encoders to separately capture static and temporal feature dynamics, fusing their complementary representations to improve performance stability across low- and high-MVC conditions. Evaluated on a self-collected dataset spanning 30 participants across four MVC levels (20-80%), it achieves state-of-the-art accuracy and strong generalization under mild-fatigue conditions. Beyond performance, FatigueFormer enables attention-based visualization of fatigue dynamics, revealing how feature groups and time windows contribute differently across varying MVC levels, offering interpretable insight into fatigue progression. --- ### Dual-branch Graph Domain Adaptation for Cross-scenario Multi-modal Emotion Recognition Authors: Yuntao Shou, Jun Zhou, Tao Meng, Wei Ai, Keqin Li Published: 2026-03-27 Categories: eess.AS, cs.AI arXiv: https://arxiv.org/abs/2603.26840v1 Multimodal Emotion Recognition in Conversations (MERC) aims to predict speakers' emotional states in multi-turn dialogues through text, audio, and visual cues. In real-world settings, conversation scenarios differ significantly in speakers, topics, styles, and noise levels. Existing MERC methods generally neglect these cross-scenario variations, limiting their ability to transfer models trained on a source domain to unseen target domains. To address this issue, we propose a Dual-branch Graph Domain Adaptation framework (DGDA) for multimodal emotion recognition under cross-scenario conditions. We first construct an emotion interaction graph to characterize complex emotional dependencies among utterances. A dual-branch encoder, consisting of a hypergraph neural network (HGNN) and a path neural network (PathNN), is then designed to explicitly model multivariate relationships and implicitly capture global dependencies. To enable out-of-domain generalization, a domain adversarial discriminator is introduced to learn invariant representations across domains. Furthermore, a regularization loss is incorporated to suppress the negative influence of noisy labels. To the best of our knowledge, DGDA is the first MERC framework that jointly addresses domain shift and label noise. Theoretical analysis provides tighter generalization bounds, and extensive experiments on IEMOCAP and MELD demonstrate that DGDA consistently outperforms strong baselines and better adapts to cross-scenario conversations. Our code is available at https://github.com/Xudmm1239439/DGDA-Net. --- ### From Pixels to BFS: High Maze Accuracy Does Not Imply Visual Planning Authors: Alberto G. Rodriguez Salgado Published: 2026-03-27 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2603.26839v2 How do multimodal models solve visual spatial tasks -- through genuine planning, or through brute-force search in token space? We introduce \textsc{MazeBench}, a benchmark of 110 procedurally generated maze images across nine controlled groups, and evaluate 16 model configurations from OpenAI, Anthropic, Google, and Alibaba. GPT-5.4 solves 91\% and Gemini 3.1 Pro 79\%, but these scores are misleading: models typically translate images into text grids and then enumerate paths step by step, consuming 1,710--22,818 tokens per solve for a task humans do quickly. Without added reasoning budgets, all configurations score only 2--12\%; on 20$\times$20 ultra-hard mazes, they hit token limits and fail. Qualitative traces reveal a common two-stage strategy: image-to-grid translation followed by token-level search, effectively BFS in prose. A text-grid ablation shows Claude Sonnet 4.6 rising from 6\% on images to 80\% when given the correct grid, isolating weak visual extraction from downstream search. When explicitly instructed not to construct a grid or perform graph search, models still revert to the same enumeration strategy. \textsc{MazeBench} therefore shows that high accuracy on visual planning tasks does not imply human-like spatial understanding. --- ### Concerning Uncertainty -- A Systematic Survey of Uncertainty-Aware XAI Authors: Helena Löfström, Tuwe Löfström, Anders Hjort, Fatima Rabia Yapicioglu Published: 2026-03-27 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.26838v1 This paper surveys uncertainty-aware explainable artificial intelligence (UAXAI), examining how uncertainty is incorporated into explanatory pipelines and how such methods are evaluated. Across the literature, three recurring approaches to uncertainty quantification emerge (Bayesian, Monte Carlo, and Conformal methods), alongside distinct strategies for integrating uncertainty into explanations: assessing trustworthiness, constraining models or explanations, and explicitly communicating uncertainty. Evaluation practices remain fragmented and largely model centered, with limited attention to users and inconsistent reporting of reliability properties (e.g., calibration, coverage, explanation stability). Recent work leans towards calibration, distribution free techniques and recognizes explainer variability as a central concern. We argue that progress in UAXAI requires unified evaluation principles that link uncertainty propagation, robustness, and human decision-making, and highlight counterfactual and calibration approaches as promising avenues for aligning interpretability with reliability. --- ### SpatialAnt: Autonomous Zero-Shot Robot Navigation via Active Scene Reconstruction and Visual Anticipation Authors: Jiwen Zhang, Xiangyu Shi, Siyuan Wang, Zerui Li, Zhongyu Wei, Qi Wu Published: 2026-03-27 Categories: cs.RO, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2603.26837v1 Vision-and-Language Navigation (VLN) has recently benefited from Multimodal Large Language Models (MLLMs), enabling zero-shot navigation. While recent exploration-based zero-shot methods have shown promising results by leveraging global scene priors, they rely on high-quality human-crafted scene reconstructions, which are impractical for real-world robot deployment. When encountering an unseen environment, a robot should build its own priors through pre-exploration. However, these self-built reconstructions are inevitably incomplete and noisy, which severely degrade methods that depend on high-quality scene reconstructions. To address these issues, we propose SpatialAnt, a zero-shot navigation framework designed to bridge the gap between imperfect self-reconstructions and robust execution. SpatialAnt introduces a physical grounding strategy to recover the absolute metric scale for monocular-based reconstructions. Furthermore, rather than treating the noisy self-reconstructed scenes as absolute spatial references, we propose a novel visual anticipation mechanism. This mechanism leverages the noisy point clouds to render future observations, enabling the agent to perform counterfactual reasoning and prune paths that contradict human instructions. Extensive experiments in both simulated and real-world environments demonstrate that SpatialAnt significantly outperforms existing zero-shot methods. We achieve a 66% Success Rate (SR) on R2R-CE and 50.8% SR on RxR-CE benchmarks. Physical deployment on a Hello Robot further confirms the efficiency and efficacy of our framework, achieving a 52% SR in challenging real-world settings. --- ### Reliability-Aware Weighted Multi-Scale Spatio-Temporal Maps for Heart Rate Monitoring Authors: Arpan Bairagi, Rakesh Dey, Siladittya Manna, Umapada Pal Published: 2026-03-27 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2603.26836v1 Remote photoplethysmography (rPPG) allows for the contactless estimation of physiological signals from facial videos by analyzing subtle skin color changes. However, rPPG signals are extremely susceptible to illumination changes, motion, shadows, and specular reflections, resulting in low-quality signals in unconstrained environments. To overcome these issues, we present a Reliability-Aware Weighted Multi-Scale Spatio-Temporal (WMST) map that models pixel reliability through the suppression of environmental noises. These noises are modeled using different weighting strategies to focus on more physiologically valid areas. Leveraging the WMST map, we develop an SSL contrastive learning approach based on Swin-Unet, where positive pairs are generated from conventional rPPG signals and temporally expanded WMST maps. Moreover, we introduce a new High-High-High (HHH) wavelet map as a negative example that maintains motion and structural details while filtering out physiological information. Here, our aim is to estimate heart rate (HR), and the experiments on public rPPG benchmarks show that our approach enhances motion and illumination robustness with lower HR estimation error and higher Pearson correlation than existing Self-Supervised Learning (SSL) based rPPG methods. --- ### ANVIL: Accelerator-Native Video Interpolation via Codec Motion Vector Priors Authors: Shibo Liu Published: 2026-03-27 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2603.26835v3 Real-time 30-to-60 fps video frame interpolation on mobile neural processing units (NPUs) requires each synthesized frame within 33.3 ms. We show that mainstream flow-based video frame interpolation faces three structural deployment barriers on mobile NPUs: spatial sampling operators exceed the frame budget or lack hardware support, iterative flow refinement collapses under 8-bit integer post-training quantization, and memory-bound operators dominate the inference graph. ANVIL addresses these barriers by reusing motion vectors from the H.264/AVC decoder to prealign input frames, removing learned optical flow, spatial sampling, and iterative accumulation from the accelerator graph. The remaining residual is refined by a convolution-dominated network composed almost entirely of compute-bound operators. On a Snapdragon 8 Gen 3 device, ANVIL achieves 12.8 ms 1080p inference at 8-bit integer precision; an open-source Android player sustains 28.4 ms median end-to-end latency over 30-minute continuous playback. Per-operator causal analysis identifies quantized accumulation on recurrent flow states as a key mechanism behind integer quantization failure in iterative methods. The current design targets H.264/AVC playback with decoder-exposed motion vectors. --- ### Hybrid Diffusion Model for Breast Ultrasound Image Augmentation Authors: Farhan Fuad Abir, Sanjeda Sara Jennifer, Niloofar Yousefi, Laura J. Brattain Published: 2026-03-27 Categories: eess.IV, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2603.26834v1 We propose a hybrid diffusion-based augmentation framework to overcome the critical challenge of ultrasound data augmentation in breast ultrasound (BUS) datasets. Unlike conventional diffusion-based augmentations, our approach improves visual fidelity and preserves ultrasound texture by combining text-to-image generation with image-to-image (img2img) refinement, as well as fine-tuning with low-rank adaptation (LoRA) and textual inversion (TI). Our method generated realistic, class-consistent images on an open-source Kaggle breast ultrasound image dataset (BUSI). Compared to the Stable Diffusion v1.5 baseline, incorporating TI and img2img refinement reduced the Frechet Inception Distance (FID) from 45.97 to 33.29, demonstrating a substantial gain in fidelity while maintaining comparable downstream classification performance. Overall, the proposed framework effectively mitigates the low-fidelity limitations of synthetic ultrasound images and enhances the quality of augmentation for robust diagnostic modeling. --- ### External Benchmarking of Lung Ultrasound Models for Pneumothorax-Related Signs: A Manifest-Based Multi-Source Study Authors: Takehiro Ishikawa Published: 2026-03-27 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2603.26832v1 Background and Aims: Reproducible external benchmarks for pneumothorax-related lung ultrasound (LUS) AI are scarce, and binary lung-sliding classification may obscure clinically important signs. We therefore developed a manifest-based external benchmark and used it to test both cross-domain generalization and task validity. Methods: We curated 280 clips from 190 publicly accessible LUS source videos and released a reconstruction manifest containing URLs, timestamps, crop coordinates, labels, and probe shape. Labels were normal lung sliding, absent lung sliding, lung point, and lung pulse. A previously published single-site binary classifier was evaluated on this benchmark; challenge-state analysis examined lung point and lung pulse using the predicted probability of absent sliding, P(absent). Results: The single-site comparator achieved ROC-AUC 0.9625 in-domain but 0.7050 on the heterogeneous external benchmark; restricting external evaluation to linear clips still yielded ROC-AUC 0.7212. In challenge-state analysis, mean P(absent) ranked absent (0.504) > lung point (0.313) > normal (0.186) > lung pulse (0.143). Lung pulse differed from absent clips (p=0.000470) but not from normal clips (p=0.813), indicating that the binary model treated pulse as normal-like despite absent sliding. Lung point differed from both absent (p=0.000468) and normal (p=0.000026), supporting its interpretation as an intermediate ambiguity state rather than a clean binary class. Conclusion: A manifest-based, multi-source benchmark can support reproducible external evaluation without redistributing source videos. Binary lung-sliding classification is an incomplete proxy for pneumothorax reasoning because it obscures blind-spot and ambiguity states such as lung pulse and lung point. --- ### Envisioning global urban development with satellite imagery and generative AI Authors: Kailai Sun, Yuebing Liang, Mingyi He, Yunhan Zheng, Alok Prakash, Shenhao Wang, Jinhua Zhao, Alex "Sandy'' Pentland Published: 2026-03-27 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.26831v1 Urban development has been a defining force in human history, shaping cities for centuries. However, past studies mostly analyze such development as predictive tasks, failing to reflect its generative nature. Therefore, this study designs a multimodal generative AI framework to envision sustainable urban development at a global scale. By integrating prompts and geospatial controls, our framework can generate high-fidelity, diverse, and realistic urban satellite imagery across the 500 largest metropolitan areas worldwide. It enables users to specify urban development goals, creating new images that align with them while offering diverse scenarios whose appearance can be controlled with text prompts and geospatial constraints. It also facilitates urban redevelopment practices by learning from the surrounding environment. Beyond visual synthesis, we find that it encodes and interprets latent representations of urban form for global cross-city learning, successfully transferring styles of urban environments across a global spatial network. The latent representations can also enhance downstream prediction tasks such as carbon emission prediction. Further, human expert evaluation confirms that our generated urban images are comparable to real urban images. Overall, this study presents innovative approaches for accelerated urban planning and supports scenario-based planning processes for worldwide cities. --- ### A Regression Framework for Understanding Prompt Component Impact on LLM Performance Authors: Andrew Lauziere, Jonathan Daugherty, Taisa Kushner Published: 2026-03-27 Categories: cs.LG, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2603.26830v1 As large language models (LLMs) continue to improve and see further integration into software systems, so does the need to understand the conditions in which they will perform. We contribute a statistical framework for understanding the impact of specific prompt features on LLM performance. The approach extends previous explainable artificial intelligence (XAI) methods specifically to inspect LLMs by fitting regression models relating portions of the prompt to LLM evaluation. We apply our method to compare how two open-source models, Mistral-7B and GPT-OSS-20B, leverage the prompt to perform a simple arithmetic problem. Regression models of individual prompt portions explain 72% and 77% of variation in model performances, respectively. We find misinformation in the form of incorrect example query-answer pairs impedes both models from solving the arithmetic query, though positive examples do not find significant variability in the impact of positive and negative instructions - these prompts have contradictory effects on model performance. The framework serves as a tool for decision makers in critical scenarios to gain granular insight into how the prompt influences an LLM to solve a task. --- ### Squish and Release: Exposing Hidden Hallucinations by Making Them Surface as Safety Signals Authors: Nathaniel Oh, Paul Attie Published: 2026-03-27 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.26829v1 Language models detect false premises when asked directly but absorb them under conversational pressure, producing authoritative professional output built on errors they already identified. This failure - order-gap hallucination - is invisible to output inspection because the error migrates into the activation space of the safety circuit, suppressed but not erased. We introduce Squish and Release (S&R), an activation-patching architecture with two components: a fixed detector body (layers 24-31, the localized safety evaluation circuit) and a swappable detector core (an activation vector controlling perception direction). A safety core shifts the model from compliance toward detection; an absorb core reverses it. We evaluate on OLMo-2 7B using the Order-Gap Benchmark - 500 chains across 500 domains, all manually graded. Key findings: cascade collapse is near-total (99.8% compliance at O5); the detector body is binary and localized (layers 24-31 shift 93.6%, layers 0-23 contribute zero, p<10^-189); a synthetically engineered core releases 76.6% of collapsed chains; detection is the more stable attractor (83% restore vs 58% suppress); and epistemic specificity is confirmed (false-premise core releases 45.4%, true-premise core releases 0.0%). The contribution is the framework - body/core architecture, benchmark, and core engineering methodology - which is model-agnostic by design. --- ### Arithmetic OOD Failure Unfolds in Stages in Minimal GPTs Authors: Seine A. Shintani Published: 2026-03-27 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.26828v1 Arithmetic benchmarks are often reduced to a single held-out score, but that score can conflate qualitatively different failures. We study a controlled minimal GPT trained on exhaustive 2-digit addition, where all local digit transitions are already present in training, and ask why 3-digit generalization still fails. The failure is staged. First, there is a layout barrier: a learned absolute-position model collapses under a pure 3-digit layout shift, and mixed-layout exposure is the only intervention that materially weakens this barrier. Second, after layout repair, the hundreds position behaves like a carry flag rather than a semantic hundreds digit; targeted carry probes reverse the relevant logit margin, whereas a matched extra-data control does not. Third, after carry repair, the main remaining bottleneck is conditional recomposition: high-conditioned tail data outperforms a matched control, high-only data, and tail-only data on all true-3-digit suites, and the same ordering reappears in a larger 2-layer bridge experiment. The residual errors after recomposition are then overwhelmingly tens-only, and a separate 10-seed late-stage study shows that a sign-aware tens repair raises exact match on the hardest thousands-carry suite from 0.664 to 0.822. We therefore provide an experimentally testable decomposition of arithmetic OOD failure into layout, carry-semantics, recomposition, and late tens-residual stages. --- ### Central-to-Local Adaptive Generative Diffusion Framework for Improving Gene Expression Prediction in Data-Limited Spatial Transcriptomics Authors: Yaoyu Fang, Jiahe Qian, Xinkun Wang, Lee A. Cooper, Bo Zhou Published: 2026-03-27 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2603.26827v1 Spatial Transcriptomics (ST) provides spatially resolved gene expression profiles within intact tissue architecture, enabling molecular analysis in histological context. However, the high cost, limited throughput, and restricted data sharing of ST experiments result in severe data scarcity, constraining the development of robust computational models. To address this limitation, we present a Central-to-Local adaptive generative diffusion framework for ST (C2L-ST) that integrates large-scale morphological priors with limited molecular guidance. A global central model is first pretrained on extensive histopathology datasets to learn transferable morphological representations, and institution-specific local models are then adapted through lightweight gene-conditioned modulation using a small number of paired image-gene spots. This strategy enables the synthesis of realistic and molecularly consistent histology patches under data-limited conditions. The generated images exhibit high visual and structural fidelity, reproduce cellular composition, and show strong embedding overlap with real data across multiple organs, reflecting both realism and diversity. When incorporated into downstream training, synthetic image-gene pairs improve gene expression prediction accuracy and spatial coherence, achieving performance comparable to real data while requiring only a fraction of sampled spots. C2L-ST provides a scalable and data-efficient framework for molecular-level data augmentation, offering a domain-adaptive and generalizable approach for integrating histology and transcriptomics in spatial biology and related fields. --- ### Throughput Optimization as a Strategic Lever in Large-Scale AI Systems: Evidence from Dataloader and Memory Profiling Innovations Authors: Mayank Jha Published: 2026-03-27 Categories: cs.LG, cs.AI, cs.PF arXiv: https://arxiv.org/abs/2603.26823v1 The development of large-scale foundation models, particularly Large Language Models (LLMs), is constrained by significant computational and memory bottlenecks. These challenges elevate throughput optimization from a mere engineering task to a critical strategic lever, directly influencing training time, operational cost, and the feasible scale of next-generation models. This paper synthesizes evidence from recent academic and industry innovations to analyze key advancements in training efficiency. We examine architectural solutions to dataloader bottlenecks, such as the OVERLORD framework, which has demonstrated a 4.5% improvement in end-to-end training throughput. We investigate memory optimization techniques designed to overcome the GPU memory wall, including CPU offloading strategies like DeepSpeed's ZeRO-Offload, which enable the training of models far exceeding single-accelerator capacity. Furthermore, we explore the growing importance of compiler-centric optimizations, exemplified by Triton-distributed, which enables the joint optimization of computation, memory, and communication for substantial performance gains. The analysis is contextualized by advanced profiling tools and hardware characterization studies that identify and mitigate previously overlooked overheads like Dynamic Voltage and Frequency Scaling (DVFS). Findings indicate that a holistic, system-level approach, integrating innovations across data pipelines, memory management, network fabrics, and compiler technologies, is essential for accelerating AI development, managing costs, and pushing the boundaries of model scale. --- ### Detailed Geometry and Appearance from Opportunistic Motion Authors: Ryosuke Hirai, Kohei Yamashita, Antoine Guédon, Ryo Kawahara, Vincent Lepetit, Ko Nishino Published: 2026-03-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.26665v1 Reconstructing 3D geometry and appearance from a sparse set of fixed cameras is a foundational task with broad applications, yet it remains fundamentally constrained by the limited viewpoints. We show that this bound can be broken by exploiting opportunistic object motion: as a person manipulates an object~(e.g., moving a chair or lifting a mug), the static cameras effectively ``orbit'' the object in its local coordinate frame, providing additional virtual viewpoints. Harnessing this object motion, however, poses two challenges: the tight coupling of object pose and geometry estimation and the complex appearance variations of a moving object under static illumination. We address these by formulating a joint pose and shape optimization using 2D Gaussian splatting with alternating minimization of 6DoF trajectories and primitive parameters, and by introducing a novel appearance model that factorizes diffuse and specular components with reflected directional probing within the spherical harmonics space. Extensive experiments on synthetic and real-world datasets with extremely sparse viewpoints demonstrate that our method recovers significantly more accurate geometry and appearance than state-of-the-art baselines. --- ### Learning to Commit: Generating Organic Pull Requests via Online Repository Memory Authors: Mo Li, L. H. Xu, Qitai Tan, Ting Cao, Yunxin Liu Published: 2026-03-27 Categories: cs.SE, cs.CL arXiv: https://arxiv.org/abs/2603.26664v1 Large language model (LLM)-based coding agents achieve impressive results on controlled benchmarks yet routinely produce pull requests that real maintainers reject. The root cause is not functional incorrectness but a lack of organicity: generated code ignores project-specific conventions, duplicates functionality already provided by internal APIs, and violates implicit architectural constraints accumulated over years of development. Simply exposing an agent to the latest repository snapshot is not enough: the snapshot reveals the final state of the codebase, but not the repository-specific change patterns by which that state was reached. We introduce Learning to Commit, a framework that closes this gap through Online Repository Memory. Given a repository with a strict chronological split, the agent performs supervised contrastive reflection on earlier commits: it blindly attempts to resolve each historical issue, compares its prediction against the oracle diff, and distils the gap into a continuously growing set of skills-reusable patterns capturing coding style, internal API usage, and architectural invariants. When a new PR description arrives, the agent conditions its generation on these accumulated skills, producing changes grounded in the project's own evolution rather than generic pretraining priors. Evaluation is conducted on genuinely future, merged pull requests that could not have been seen during the skill-building phase, and spans multiple dimensions including functional correctness, code-style consistency, internal API reuse rate, and modified-region plausibility. Experiments on an expert-maintained repository with rich commit history show that Online Repository Memory effectively improves organicity scores on held-out future tasks. --- ### Weight Tying Biases Token Embeddings Towards the Output Space Authors: Antonio Lopardo, Avyukth Harish, Catherine Arnett, Akshat Gupta Published: 2026-03-27 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.26663v1 Weight tying, i.e. sharing parameters between input and output embedding matrices, is common practice in language model design, yet its impact on the learned embedding space remains poorly understood. In this paper, we show that tied embedding matrices align more closely with output (unembedding) matrices than with input embeddings of comparable untied models, indicating that the shared matrix is shaped primarily for output prediction rather than input representation. This unembedding bias arises because output gradients dominate early in training. Using tuned lens analysis, we show this negatively affects early-layer computations, which contribute less effectively to the residual stream. Scaling input gradients during training reduces this bias, providing causal evidence for the role of gradient imbalance. This is mechanistic evidence that weight tying optimizes the embedding matrix for output prediction, compromising its role in input representation. These results help explain why weight tying can harm performance at scale and have implications for training smaller LLMs, where the embedding matrix contributes substantially to total parameter count. --- ### GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation Authors: Nicolas von Lützow, Barbara Rössle, Katharina Schmid, Matthias Nießner Published: 2026-03-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.26661v2 Most recent advances in 3D generative modeling rely on diffusion or flow-matching formulations. We instead explore a fully autoregressive alternative and introduce GaussianGPT, a transformer-based model that directly generates 3D Gaussians via next-token prediction, thus facilitating full 3D scene generation. We first compress Gaussian primitives into a discrete latent grid using a sparse 3D convolutional autoencoder with vector quantization. The resulting tokens are serialized and modeled using a causal transformer with 3D rotary positional embedding, enabling sequential generation of spatial structure and appearance. Unlike diffusion-based methods that refine scenes holistically, our formulation constructs scenes step-by-step, naturally supporting completion, outpainting, controllable sampling via temperature, and flexible generation horizons. This formulation leverages the compositional inductive biases and scalability of autoregressive modeling while operating on explicit representations compatible with modern neural rendering pipelines, positioning autoregressive transformers as a complementary paradigm for controllable and context-aware 3D generation. --- ### Ruka-v2: Tendon Driven Open-Source Dexterous Hand with Wrist and Abduction for Robot Learning Authors: Xinqi Lucas Liu, Ruoxi Hu, Alejandro Ojeda Olarte, Zhuoran Chen, Kenny Ma, Charles Cheng Ji, Lerrel Pinto, Raunaq Bhirangi, Irmak Guzey Published: 2026-03-27 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2603.26660v2 Lack of accessible and dexterous robot hardware has been a significant bottleneck to achieving human-level dexterity in robots. Last year, we released Ruka, a fully open-sourced, tendon-driven humanoid hand with 11 degrees of freedom - 2 per finger and 3 at the thumb - buildable for under $1,300. It was one of the first fully open-sourced humanoid hands, and introduced a novel data-driven approach to finger control that captures tendon dynamics within the control system. Despite these contributions, Ruka lacked two degrees of freedom essential for closely imitating human behavior: wrist mobility and finger adduction/abduction. In this paper, we introduce Ruka-v2: a fully open-sourced, tendon-driven humanoid hand featuring a decoupled 2-DOF parallel wrist and abduction/adduction at the fingers. The parallel wrist adds smooth, independent flexion/extension and radial/ulnar deviation, enabling manipulation in confined environments such as cabinets. Abduction enables motions such as grasping thin objects, in-hand rotation, and calligraphy. We present the design of Ruka-v2 and evaluate it against Ruka through user studies on teleoperated tasks, finding a 51.3% reduction in completion time and a 21.2% increase in success rate. We further demonstrate its full range of applications for robot learning: bimanual and single-arm teleoperation across 13 dexterous tasks, and autonomous policy learning on 3 tasks. All 3D print files, assembly instructions, controller software, and videos are available at https://ruka-hand-v2.github.io/ . --- ### Zero-Shot Depth from Defocus Authors: Yiming Zuo, Hongyu Wen, Venkat Subramanian, Patrick Chen, Karhan Kayan, Mario Bijelic, Felix Heide, Jia Deng Published: 2026-03-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.26658v2 Depth from Defocus (DfD) is the task of estimating a dense metric depth map from a focus stack. Unlike previous works overfitting to a certain dataset, this paper focuses on the challenging and practical setting of zero-shot generalization. We first propose a new real-world DfD benchmark ZEDD, which contains 8.3x more scenes and significantly higher quality images and ground-truth depth maps compared to previous benchmarks. We also design a novel network architecture named FOSSA. FOSSA is a Transformer-based architecture with novel designs tailored to the DfD task. The key contribution is a stack attention layer with a focus distance embedding, allowing efficient information exchange across the focus stack. Finally, we develop a new training data pipeline allowing us to utilize existing large-scale RGBD datasets to generate synthetic focus stacks. Experiment results on ZEDD and other benchmarks show a significant improvement over the baselines, reducing errors by up to 55.7%. The ZEDD benchmark is released at https://zedd.cs.princeton.edu. The code and checkpoints are released at https://github.com/princeton-vl/FOSSA. --- ### Tunable Soft Equivariance with Guarantees Authors: Md Ashiqur Rahman, Lim Jun Hao, Jeremiah Jiang, Teck-Yian Lim, Raymond A. Yeh Published: 2026-03-27 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.26657v1 Equivariance is a fundamental property in computer vision models, yet strict equivariance is rarely satisfied in real-world data, which can limit a model's performance. Controlling the degree of equivariance is therefore desirable. We propose a general framework for constructing soft equivariant models by projecting the model weights into a designed subspace. The method applies to any pre-trained architecture and provides theoretical bounds on the induced equivariance error. Empirically, we demonstrate the effectiveness of our method on multiple pre-trained backbones, including ViT and ResNet, across image classification, semantic segmentation, and human-trajectory prediction tasks. Notably, our approach improves the performance while simultaneously reducing equivariance error on the competitive ImageNet benchmark. --- ### PerceptionComp: A Video Benchmark for Complex Perception-Centric Reasoning Authors: Shaoxuan Li, Zhixuan Zhao, Hanze Deng, Zirun Ma, Shulin Tian, Zuyan Liu, Yushi Hu, Haoning Wu, Yuhao Dong, Benlin Liu, Ziwei Liu, Ranjay Krishna Published: 2026-03-27 Categories: cs.CV, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.26653v1 We introduce PerceptionComp, a manually annotated benchmark for complex, long-horizon, perception-centric video reasoning. PerceptionComp is designed so that no single moment is sufficient: answering each question requires multiple temporally separated pieces of visual evidence and compositional constraints under conjunctive and sequential logic, spanning perceptual subtasks such as objects, attributes, relations, locations, actions, and events, and requiring skills including semantic recognition, visual correspondence, temporal reasoning, and spatial reasoning. The benchmark contains 1,114 highly complex questions on 279 videos from diverse domains including city walk tours, indoor villa tours, video games, and extreme outdoor sports, with 100% manual annotation. Human studies show that PerceptionComp requires substantial test-time thinking and repeated perception steps: participants take much longer than on prior benchmarks, and accuracy drops to near chance (18.97%) when rewatching is disallowed. State-of-the-art MLLMs also perform substantially worse on PerceptionComp than on existing benchmarks: the best model in our evaluation, Gemini-3-Flash, reaches only 45.96% accuracy in the five-choice setting, while open-source models remain below 40%. These results suggest that perception-centric long-horizon video reasoning remains a major bottleneck, and we hope PerceptionComp will help drive progress in perceptual reasoning. --- ### Vision2Web: A Hierarchical Benchmark for Visual Website Development with Agent Verification Authors: Zehai He, Wenyi Hong, Zhen Yang, Ziyang Pan, Mingdao Liu, Xiaotao Gu, Jie Tang Published: 2026-03-27 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2603.26648v3 Recent advances in large language models have improved the capabilities of coding agents, yet systematic evaluation of complex, end-to-end website development remains limited. To address this gap, we introduce Vision2Web, a hierarchical benchmark for visual website development, spanning from static UI-to-code generation, interactive multi-page frontend reproduction, to long-horizon full-stack website development. The benchmark is constructed from real-world websites and comprises a total of 193 tasks across 16 categories, with 918 prototype images and 1,255 test cases. To support flexible, thorough and reliable evaluation, we propose workflow-based agent verification paradigm based on two complementary components: a GUI agent verifier and a VLM-based judge. We evaluate multiple visual language models instantiated under different coding-agent frameworks, revealing substantial performance gaps at all task levels, with state-of-the-art models still struggling on full-stack development. --- ### An LP-based Sampling Policy for Multi-Armed Bandits with Side-Observations and Stochastic Availability Authors: Ashutosh Soni, Peizhong Ju, Atilla Eryilmaz, Ness B. Shroff Published: 2026-03-27 Categories: cs.LG, eess.SY arXiv: https://arxiv.org/abs/2603.26647v1 We study the stochastic multi-armed bandit (MAB) problem where an underlying network structure enables side-observations across related actions. We use a bipartite graph to link actions to a set of unknowns, such that selecting an action reveals observations for all the unknowns it is connected to. While previous works rely on the assumption that all actions are permanently accessible, we investigate the more practical setting of stochastic availability, where the set of feasible actions (the "activation set") varies dynamically in each round. This framework models real-world systems with both structural dependencies and volatility, such as social networks where users provide side-information about their peers' preferences, yet are not always online to be queried. To address this challenge, we propose UCB-LP-A, a novel policy that leverages a Linear Programming (LP) approach to optimize exploration-exploitation trade-offs under stochastic availability. Unlike standard network bandit algorithms that assume constant access, UCB-LP-A computes an optimal sampling distribution over the realizable activation sets, ensuring that the necessary observations are gathered using only the currently active arms. We derive a theoretical upper bound on the regret of our policy, characterizing the impact of both the network structure and the activation probabilities. Finally, we demonstrate through numerical simulations that UCB-LP-A significantly outperforms existing heuristics that ignore either the side-information or the availability constraints. --- ### Beyond Language: Grounding Referring Expressions with Hand Pointing in Egocentric Vision Authors: Ling Li, Bowen Liu, Zinuo Zhan, Peng Jie, Jianhui Zhong, Kenglun Chang, Zhidong Deng Published: 2026-03-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.26646v1 Traditional Visual Grounding (VG) predominantly relies on textual descriptions to localize objects, a paradigm that inherently struggles with linguistic ambiguity and often ignores non-verbal deictic cues prevalent in real-world interactions. In natural egocentric engagements, hand-pointing combined with speech forms the most intuitive referring mechanism. To bridge this gap, we introduce EgoPoint-Ground, the first large-scale multimodal dataset dedicated to egocentric deictic visual grounding. Comprising over \textbf{15k} interactive samples in complex scenes, the dataset provides rich, multi-grained annotations including hand-target bounding box pairs and dense semantic captions. We establish a comprehensive benchmark for hand-pointing referring expression resolution, evaluating a wide spectrum of mainstream Multimodal Large Language Models (MLLMs) and state-of-the-art VG architectures. Furthermore, we propose SV-CoT, a novel baseline framework that reformulates grounding as a structured inference process, synergizing gestural and linguistic cues through a Visual Chain-of-Thought paradigm. Extensive experiments demonstrate that SV-CoT achieves an $\textbf{11.7\%}$ absolute improvement over existing methods, effectively mitigating semantic ambiguity and advancing the capability of agents to comprehend multimodal physical intents. The dataset and code will be made publicly available. --- ### Automatic Laplace Collapsed Sampling: Scalable Marginalisation of Latent Parameters via Automatic Differentiation Authors: Toby Lovick, David Yallup, Will Handley Published: 2026-03-27 Categories: cs.LG, astro-ph.IM, stat.ME arXiv: https://arxiv.org/abs/2603.26644v1 We present Automatic Laplace Collapsed Sampling (ALCS), a general framework for marginalising latent parameters in Bayesian models using automatic differentiation, which we combine with nested sampling to explore the hyperparameter space in a robust and efficient manner. At each nested sampling likelihood evaluation, ALCS collapses the high-dimensional latent variables $z$ to a scalar contribution via maximum a posteriori (MAP) optimisation and a Laplace approximation, both computed using autodiff. This reduces the effective dimension from $d_θ+ d_z$ to just $d_θ$, making Bayesian evidence computation tractable for high-dimensional settings without hand-derived gradients or Hessians, and with minimal model-specific engineering. The MAP optimisation and Hessian evaluation are parallelised across live points on GPU-hardware, making the method practical at scale. We also show that automatic differentiation enables local approximations beyond Laplace to parametric families such as the Student-$t$, which improves evidence estimates for heavy-tailed latents. We validate ALCS on a suite of benchmarks spanning hierarchical, time-series, and discrete-likelihood models and establish where the Gaussian approximation holds. This enables a post-hoc ESS diagnostic that localises failures across hyperparameter space without expensive joint sampling. --- ### Make Geometry Matter for Spatial Reasoning Authors: Shihua Zhang, Qiuhong Shen, Shizun Wang, Tianbo Pan, Xinchao Wang Published: 2026-03-27 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.26639v1 Empowered by large-scale training, vision-language models (VLMs) achieve strong image and video understanding, yet their ability to perform spatial reasoning in both static scenes and dynamic videos remains limited. Recent advances try to handle this limitation by injecting geometry tokens from pretrained 3D foundation models into VLMs. Nevertheless, we observe that naive token fusion followed by standard fine-tuning in this line of work often leaves such geometric cues underutilized for spatial reasoning, as VLMs tend to rely heavily on 2D visual cues. In this paper, we propose GeoSR, a framework designed to make geometry matter by encouraging VLMs to actively reason with geometry tokens. GeoSR introduces two key components: (1) Geometry-Unleashing Masking, which strategically masks portions of 2D vision tokens during training to weaken non-geometric shortcuts and force the model to consult geometry tokens for spatial reasoning; and (2) Geometry-Guided Fusion, a gated routing mechanism that adaptively amplifies geometry token contributions in regions where geometric evidence is critical. Together, these designs unleash the potential of geometry tokens for spatial reasoning tasks. Extensive experiments on both static and dynamic spatial reasoning benchmarks demonstrate that GeoSR consistently outperforms prior methods and establishes new state-of-the-art performance by effectively leveraging geometric information. The project page is available at https://suhzhang.github.io/GeoSR/. --- ### Drive-Through 3D Vehicle Exterior Reconstruction via Dynamic-Scene SfM and Distortion-Aware Gaussian Splatting Authors: Nitin Kulkarni, Akhil Devarashetti, Charlie Cluss, Livio Forte, Philip Schneider, Chunming Qiao, Alina Vereshchaka Published: 2026-03-27 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2603.26638v1 High-fidelity 3D reconstruction of vehicle exteriors improves buyer confidence in online automotive marketplaces, but generating these models in cluttered dealership drive-throughs presents severe technical challenges. Unlike static-scene photogrammetry, this setting features a dynamic vehicle moving against heavily cluttered, static backgrounds. This problem is further compounded by wide-angle lens distortion, specular automotive paint, and non-rigid wheel rotations that violate classical epipolar constraints. We propose an end-to-end pipeline utilizing a two-pillar camera rig. First, we resolve dynamic-scene ambiguities by coupling SAM 3 for instance segmentation with motion-gating to cleanly isolate the moving vehicle, explicitly masking out non-rigid wheels to enforce strict epipolar geometry. Second, we extract robust correspondences directly on raw, distorted 4K imagery using the RoMa v2 learned matcher guided by semantic confidence masks. Third, these matches are integrated into a rig-aware SfM optimization that utilizes CAD-derived relative pose priors to eliminate scale drift. Finally, we use a distortion-aware 3D Gaussian Splatting framework (3DGUT) coupled with a stochastic Markov Chain Monte Carlo (MCMC) densification strategy to render reflective surfaces. Evaluations on 25 real-world vehicles across 10 dealerships demonstrate that our full pipeline achieves a PSNR of 28.66 dB, an SSIM of 0.89, and an LPIPS of 0.21 on held-out views, representing a 3.85 dB improvement over standard 3D-GS, delivering inspection-grade interactive 3D models without controlled studio infrastructure. --- ### Machine Learning Transferability for Malware Detection Authors: César Vieira, João Vitorino, Eva Maia, Isabel Praça Published: 2026-03-27 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.26632v1 Malware continues to be a predominant operational risk for organizations, especially when obfuscation techniques are used to evade detection. Despite the ongoing efforts in the development of Machine Learning (ML) detection approaches, there is still a lack of feature compatibility in public datasets. This limits generalization when facing distribution shifts, as well as transferability to different datasets. This study evaluates the suitability of different data preprocessing approaches for the detection of Portable Executable (PE) files with ML models. The preprocessing pipeline unifies EMBERv2 (2,381-dim) features datasets, trains paired models under two training setups: EMBER + BODMAS and EMBER + BODMAS + ERMDS. Regarding model evaluation, both EMBER + BODMAS and EMBER + BODMAS + ERMDS models are tested against TRITIUM, INFERNO and SOREL-20M. ERMDS is also used for testing for the EMBER + BODMAS setup. --- ### Context-specific Credibility-aware Multimodal Fusion with Conditional Probabilistic Circuits Authors: Pranuthi Tenali, Sahil Sidheekh, Saurabh Mathur, Erik Blasch, Kristian Kersting, Sriraam Natarajan Published: 2026-03-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.26629v2 Multimodal fusion requires integrating information from multiple sources that may conflict depending on context. Existing fusion approaches typically rely on static assumptions about source reliability, limiting their ability to resolve conflicts when a modality becomes unreliable due to situational factors such as sensor degradation or class-specific corruption. We introduce C$^2$MF, a context-specfic credibility-aware multimodal fusion framework that models per-instance source reliability using a Conditional Probabilistic Circuit (CPC). We formalize instance-level reliability through Context-Specific Information Credibility (CSIC), a KL-divergence-based measure computed exactly from the CPC. CSIC generalizes conventional static credibility estimates as a special case, enabling principled and adaptive reliability assessment. To evaluate robustness under cross-modal conflicts, we propose the Conflict benchmark, in which class-specific corruptions deliberately induce discrepancies between different modalities. Experimental results show that C$^2$MF improves predictive accuracy by up to 29% over static-reliability baselines in high-noise settings, while preserving the interpretability advantages of probabilistic circuit-based fusion. --- ### Benchmarking Tabular Foundation Models for Conditional Density Estimation in Regression Authors: Rafael Izbicki, Pedro L. C. Rodrigues Published: 2026-03-27 Categories: cs.LG, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2603.26611v1 Conditional density estimation (CDE) - recovering the full conditional distribution of a response given tabular covariates - is essential in settings with heteroscedasticity, multimodality, or asymmetric uncertainty. Recent tabular foundation models, such as TabPFN and TabICL, naturally produce predictive distributions, but their effectiveness as general-purpose CDE methods has not been systematically evaluated, unlike their performance for point prediction, which is well studied. We benchmark three tabular foundation model variants against a diverse set of parametric, tree-based, and neural CDE baselines on 39 real-world datasets, across training sizes from 50 to 20,000, using six metrics covering density accuracy, calibration, and computation time. Across all sample sizes, foundation models achieve the best CDE loss, log-likelihood, and CRPS on the large majority of datasets tested. Calibration is competitive at small sample sizes but, for some metrics and datasets, lags behind task-specific neural baselines at larger sample sizes, suggesting that post-hoc recalibration may be a valuable complement. In a photometric redshift case study using SDSS DR18, TabPFN exposed to 50,000 training galaxies outperforms all baselines trained on the full 500,000-galaxy dataset. Taken together, these results establish tabular foundation models as strong off-the-shelf conditional density estimators. ---