# Research Papers — 2026-03 · bundle page 135 of 243 > Full-text markdown of papers #6701–6750 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/135 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/134.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/136.md) ### Demand-Driven Context: A Methodology for Building Enterprise Knowledge Bases Through Agent Failure Authors: Raj Navakoti, Saideep Navakoti Published: 2026-03-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.14057v1 Large language model agents demonstrate expert-level reasoning, yet consistently fail on enterprise-specific tasks due to missing domain knowledge -- terminology, operational procedures, system interdependencies, and institutional decisions that exist largely as tribal knowledge. Current approaches fall into two categories: top-down knowledge engineering, which documents domain knowledge before agents use it, and bottom-up automation, where agents learn from task experience. Both have fundamental limitations: top-down efforts produce bloated, untested knowledge bases; bottom-up approaches cannot acquire knowledge that exists only in human heads. We present Demand-Driven Context (DDC), a problem-first methodology that uses agent failure as the primary signal for what domain knowledge to curate. Inspired by Test-Driven Development, DDC inverts knowledge engineering: instead of curating knowledge and hoping it is useful, DDC gives agents real problems, lets them demand the context they need, and curates only the minimum knowledge required to succeed. We describe the methodology, its entity meta-model, and a convergence hypothesis suggesting that 20-30 problem cycles produce a knowledge base sufficient for a given domain role. We demonstrate DDC through a worked example in retail order fulfillment, where nine cycles targeting an SRE incident management agent produce a reusable knowledge base of 46 entities. Finally, we propose a scaling architecture for enterprise adoption with semi-automated curation and human governance. --- ### NepTam: A Nepali-Tamang Parallel Corpus and Baseline Machine Translation Experiments Authors: Rupak Raj Ghimire, Bipesh Subedi, Balaram Prasain, Prakash Poudyal, Praveen Acharya, Nischal Karki, Rupak Tiwari, Rishikesh Kumar Sharma, Jenny Poudel, Bal Krishna Bal Published: 2026-03-14 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.14053v1 Modern Translation Systems heavily rely on high-quality, large parallel datasets for state-of-the-art performance. However, such resources are largely unavailable for most of the South Asian languages. Among them, Nepali and Tamang fall into such category, with Tamang being among the least digitally resourced languages in the region. This work addresses the gap by developing NepTam20K, a 20K gold standard parallel corpus, and NepTam80K, an 80K synthetic Nepali-Tamang parallel corpus, both sentence-aligned and designed to support machine translation. The datasets were created through a pipeline involving data scraping from Nepali news and online sources, pre-processing, semantic filtering, balancing for tense and polarity (in NepTam20K dataset), expert translation into Tamang by native speakers of the language, and verification by an expert Tamang linguist. The dataset covers five domains: Agriculture, Health, Education and Technology, Culture, and General Communication. To evaluate the dataset, baseline machine translation experiments were carried out using various multilingual pre-trained models: mBART, M2M-100, NLLB-200, and a vanilla Transformer model. The fine-tuning on the NLLB-200 achieved the highest sacreBLEU scores of 40.92 (Nepali-Tamang) and 45.26 (Tamang-Nepali). --- ### A Multi-Agent Perception-Action Alliance for Efficient Long Video Reasoning Authors: Yichang Xu, Gaowen Liu, Ramana Rao Kompella, Tiansheng Huang, Sihao Hu, Fatih Ilhan, Selim Furkan Tekin, Zachary Yahn, Ling Liu Published: 2026-03-14 Categories: cs.CV, cs.MA arXiv: https://arxiv.org/abs/2603.14052v3 This paper presents a multi-agent perception-action exploration alliance, dubbed A4VL, for efficient long-video reasoning. A4VL operates in a multi-round perception-action exploration loop with a selection of VLM agents. In each round, the team of agents performs video question-answer (VideoQA) via perception exploration followed by action exploration. During perception exploration, each agent learns to extract query-specific perception clue(s) from a few sampled frames and performs clue-based alignment to find the video block(s) that are most relevant to the query-specific event. During action exploration, A4VL performs video reasoning in three steps: (1) each agent produces its initial answer with rational, (2) all agents collaboratively scores one another through cross-reviews and relevance ranking, and (3) based on whether a satisfactory consensus is reached, the decision is made either to start a new round of perception-action deliberation by pruning (e.g., filtering out the lowest performing agent) and re-staging (e.g., new-clue and matching block based perception-action exploration), or to conclude by producing its final answer. The integration of the multi-agent alliance through multi-round perception-action exploration, coupled with event-driven partitioning and cue-guided block alignment, enables A4VL to effectively scale to real world long videos while preserving high quality video reasoning. Evaluation Results on five popular VideoQA benchmarks show that A4VL outperforms 18 existing representative VLMs and 11 recent methods optimized for long-video reasoning, while achieving significantly lower inference latency. Our code is released at https://github.com/git-disl/A4VL. --- ### A Theory of Appropriateness That Accounts for Norms of Rationality Authors: Joel Z. Leibo, Alexander Sasha Vezhnevets, Manfred Diaz, John P. Agapiou, William A. Cunningham, Peter Sunehag, Logan Cross, Raphael Koster, Stanley M. Bileschi, Minsuk Chang, Iyad Rahwan, Simon Osindero et al. Published: 2026-03-14 Categories: cs.NE arXiv: https://arxiv.org/abs/2603.14050v1 We propose a society-first theory of normative appropriateness where individuals, modeled as pre-trained actors with cognitive architectures analogous to Large Language Models (LLMs), generate behavior via predictive pattern completion. Our theory posits that individuals act by completing distributed symbolic patterns based on context, answering questions such as "What does a person such as I do in a situation such as this?". This sense-making mechanism provides a parsimonious account of the key features of human norms: their context-dependence, arbitrariness, automaticity, dynamism, and their support from social sanctioning. It challenges rational-choice theories of social norms by accounting for their key features without needing to exogenously posit scalar rewards or preference relations. By distinguishing between explicit norms, which we associate with in-context adaptation, and implicit norms, which we associate with long-term memory, the theory reconceptualizes several foundational ideas in cognitive science. In particular, it gives an alternative account to the data traditionally seen as supporting dual-process models, and it flips the role of rationality, allowing us to construe it as adherence to culturally-contingent justification standards. --- ### Schrödinger Bridge Over A Compact Connected Lie Group Authors: Hamza Mahmood, Abhishek Halder, Adeel Akhtar Published: 2026-03-14 Categories: math.OC, cs.LG, eess.SY, math.PR arXiv: https://arxiv.org/abs/2603.14049v2 This work studies the Schrödinger bridge problem for the kinematic equation on a compact connected Lie group. The objective is to steer a controlled diffusion between given initial and terminal densities supported over the Lie group while minimizing the control effort. We develop a coordinate-free formulation of this stochastic optimal control problem that respects the underlying geometric structure of the Lie group, thereby avoiding limitations associated with local parameterizations or embeddings in Euclidean spaces. We establish the existence and uniqueness of solution to the corresponding Schrödinger system. Our results are constructive in that they derive a geometric controller that optimally interpolates probability densities supported over the Lie group. To illustrate the results, we provide numerical examples on $\mathsf{SO}(2)$ and $\mathsf{SO}(3)$. The codes and animations are publicly available at https://github.com/gradslab/SbpLieGroups.git . --- ### The Reasoning Bottleneck in Graph-RAG: Structured Prompting and Context Compression for Multi-Hop QA Authors: Yasaman Zarrinkia, Venkatesh Srinivasan, Alex Thomo Published: 2026-03-14 Categories: cs.IR, cs.CL arXiv: https://arxiv.org/abs/2603.14045v2 Graph-RAG systems achieve strong multi-hop question answering by indexing documents into knowledge graphs, but strong retrieval does not guarantee strong answers. Evaluating KET-RAG, a leading Graph-RAG system, on three multi-hop QA benchmarks (HotpotQA, MuSiQue, 2WikiMultiHopQA), we find that 77% to 91% of questions have the gold answer in the retrieved context, yet accuracy is only 35% to 78%, and 73% to 84% of errors are reasoning failures. We propose two augmentations: (i) SPARQL chain-of-thought prompting, which decomposes questions into triple-pattern queries aligned with the entity-relationship context, and (ii) graph-walk compression, which compresses the context by ~60% via knowledge-graph traversal with no LLM calls. SPARQL CoT improves accuracy by +2 to +14 pp; graph-walk compression adds +6 pp on average when paired with structured prompting on smaller models. Surprisingly, we show that, with question-type routing, a fully augmented budget open-weight Llama-8B model matches or exceeds the unaugmented Llama-70B baseline on all three benchmarks at ~12x lower cost. A replication on LightRAG confirms that our augmentations transfer across Graph-RAG systems. --- ### GRPO and Reflection Reward for Mathematical Reasoning in Large Language Models Authors: Zhijie Wang Published: 2026-03-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.14041v1 The enhancement of reasoning capabilities in large language models (LLMs) has garnered significant attention, with supervised fine-tuning (SFT) and reinforcement learning emerging as dominant paradigms. While recent studies recognize the importance of reflection in reasoning processes, existing methodologies seldom address proactive reflection encouragement during training. This study focuses on mathematical reasoning by proposing a four-stage framework integrating Group Relative Policy Optimization (GRPO) with reflection reward mechanisms to strengthen LLMs' self-reflective capabilities. Besides, this approach incorporates established accuracy and format reward. Experimental results demonstrate GRPO's state-of-the-art performance through reflection-encouraged training, with ablation studies confirming the reflection reward's pivotal role. Comparative evaluations demonstrate full-parameter SFT's superiority over low-rank adaptation (LoRA) despite heightened computational demands. Building on these cumulative findings, this research substantiates GRPO's methodological significance in post-training optimization and envisions its potential to serve as a pivotal enabler for future LLM-based intelligent agents through the synergistic integration of cognitive rewards with dynamic environmental interactions. --- ### EyeWorld: A Generative World Model of Ocular State and Dynamics Authors: Ziyu Gao, Xinyuan Wu, Xiaolan Chen, Zhuoran Liu, Ruoyu Chen, Bowen Liu, Bingjie Yan, Zhenhan Wang, Kai Jin, Jiancheng Yang, Yih Chung Tham, Mingguang He et al. Published: 2026-03-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14039v1 Ophthalmic decision-making depends on subtle lesion-scale cues interpreted across multimodal imaging and over time, yet most medical foundation models remain static and degrade under modality and acquisition shifts. Here we introduce EyeWorld, a generative world model that conceptualizes the eye as a partially observed dynamical system grounded in clinical imaging. EyeWorld learns an observation-stable latent ocular state shared across modalities, unifying fine-grained parsing, structure-preserving cross-modality translation and quality-robust enhancement within a single framework. Longitudinal supervision further enables time-conditioned state transitions, supporting forecasting of clinically meaningful progression while preserving stable anatomy. By moving from static representation learning to explicit dynamical modeling, EyeWorld provides a unified approach to robust multimodal interpretation and prognosis-oriented simulation in medicine. --- ### Probing neural audio codecs for distinctions among English nuclear tunes Authors: Juan Pablo Vigneaux, Jennifer Cole Published: 2026-03-14 Categories: cs.SD, cs.CL arXiv: https://arxiv.org/abs/2603.14035v1 State-of-the-art spoken dialogue models (Défossez et al. 2024; Schalkwyk et al. 2025) use neural audio codecs to "tokenize" audio signals into a lower-frequency stream of vectorial latent representations, each quantized using a hierarchy of vector codebooks. A transformer layer allows these representations to reflect some time- and context-dependent patterns. We train probes on labeled audio data from Cole et al. (2023) to test whether the pitch trajectories that characterize English phrase-final (nuclear) intonational tunes are among these patterns. Results: Linear probes trained on the unquantized latents or some of the associated codewords yield above-chance accuracy in distinguishing eight phonologically specified nuclear tunes with monotonal pitch accents (top average test accuracy (TATA): 0.31) and the five clusters of these tunes that are robust in human speech production and perception (TATA: 0.45). Greater accuracy (TATAs: 0.74-0.89) is attained for binary distinctions between classes of rising vs. falling tunes, respectively used for questions and assertions. Information about tunes is spread among all codebooks, which calls into question a distinction between 'semantic' and 'acoustic' codebooks found in the literature. Accuracies improve with nonlinear probes, but discrimination among the five clusters remains far from human performance, suggesting a fundamental limitation of current codecs. --- ### What Counts as Real? Speech Restoration and Voice Quality Conversion Pose New Challenges to Deepfake Detection Authors: Shree Harsha Bokkahalli Satish, Harm Lameris, Joakim Gustafson, Éva Székely Published: 2026-03-14 Categories: cs.SD, cs.AI, cs.LG, eess.AS arXiv: https://arxiv.org/abs/2603.14033v2 Audio anti-spoofing systems are typically trained to assign one authenticity label to an entire speech utterance. This formulation becomes under-specified for transformations where the underlying speaker identity and linguistic content remain unchanged. We study this problem using benign, authenticity-preserving speech transformations, including voice quality conversion and speech restoration, applied to both bona fide and spoofed speech. Instead of treating all processed audio as spoofed, we factorise labels into source authenticity and processed status. Across SSL representations and DF-Arena fine-tuning experiments, we find that utterance processing status can transfer more reliably than source attribution: detectors can often identify that speech has been processed, while still confusing processed bona fide and processed spoofed speech. These results suggest that audio deepfake defences must move beyond the binary spoofed/authentic paradigm. Robust detection requires granular reporting on source authenticity, processing status, and precise processing localisation. --- ### Intrinsic Tolerance in C-Arm Imaging: How Extrinsic Re-optimization Preserves 3D Reconstruction Accuracy Authors: Lin Li, Benjamin Aubert, Paul Kemper, Aric Plumley Published: 2026-03-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14031v1 \textbf{Purpose:} C-arm fluoroscopy's 3D reconstruction relies on accurate intrinsic calibration, which is often challenging in clinical practice. This study ensures high-precision reconstruction accuracy by re-optimizing the extrinsic parameters to compensate for intrinsic calibration errors. \noindent\textbf{Methods:} We conducted both simulation and real-world experiments using five commercial C-arm systems. Intrinsic parameters were perturbed in controlled increments. Focal length was increased by 100 to 700 pixels ($\approx$20 mm to 140 mm) and principal point by 20 to 200 pixels. For each perturbation, we (1) reconstructed 3D points from known phantom geometries, (2) re-estimated extrinsic poses using standard optimization, and (3) measured reconstruction and reprojection errors relative to ground truth. \noindent\textbf{Results:} Even with focal length errors up to 500 pixels ($\approx$100 mm, assuming a nominal focal length of $\sim$1000 mm), mean 3D reconstruction error remained under 0.2 mm. Larger focal length deviations (700 pixels) elevated error to only $\approx$0.3 mm. Principal point shifts up to 200 pixels introduced negligible reconstruction error once extrinsic parameters were re-optimized, with reprojection error increases below 0.5 pixels. \noindent\textbf{Conclusion:} Moderate errors in intrinsic calibration can be effectively mitigated by extrinsic re-optimization, preserving submillimeter 3D reconstruction accuracy. This intrinsic tolerance suggests a practical pathway to relax calibration precision requirements, thereby simplifying C-arm system setup and reducing clinical workflow burden without compromising performance. --- ### Benchmarking Open-Source PPG Foundation Models for Biological Age Prediction Authors: N. Brag Published: 2026-03-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.14030v1 A task-specific model trained on 212,231 UK Biobank subjects to predict vascular age from PPG (AI-PPG Age) fails on a different clinical population: predictions collapse to a narrow 38-67 year range regardless of true age. Meanwhile, a general-purpose foundation model with no age-related training objective achieves lower error on the same data. We investigate why this happens and what it means for PPG-based biological age prediction. We evaluate three open-source PPG models (Pulse-PPG, PaPaGei-S, AI-PPG Age) on 906 surgical patients from PulseDB, using frozen embeddings with Ridge regression and 5-fold cross-validation. Pulse-PPG reaches MAE = 9.28 years, beating both AI-PPG Age in linear probe mode (9.72) and HR/HRV combined with demographics (9.59). Adding demographic features brings the best result down to MAE = 8.22 years (R2 = 0.517, r = 0.725). The predicted age gap correlates with diastolic blood pressure after adjusting for chronological age (r = -0.188, p = 1.2e-8), consistent with what Apple reported for their proprietary PpgAge model. The remaining gap with Apple (MAE 2.43) appears driven by dataset size (906 vs 213,593 subjects) and population differences rather than model architecture, as our learning curve shows no plateau. Code is publicly available. --- ### Traffic and weather driven hybrid digital twin for bridge monitoring Authors: Phani Raja Bharath Balijepalli, Bulent Soykan, Veeraraghava Raju Hasti Published: 2026-03-14 Categories: cs.AI, cs.ET arXiv: https://arxiv.org/abs/2603.14028v1 A hybrid digital twin framework is presented for bridge condition monitoring using existing traffic cameras and weather APIs, reducing reliance on dedicated sensor installations. The approach is demonstrated on the Peace Bridge (99 years in service) under high traffic demand and harsh winter exposure. The framework fuses three near-real-time streams: YOLOv8 computer vision from a bridge-deck camera estimates vehicle counts, traffic density, and load proxies; a Lighthill--Whitham--Richards (LWR) model propagates density $ρ(x,t)$ and detects deceleration-driven shockwaves linked to repetitive loading and fatigue accumulation; and weather APIs provide deterioration drivers including temperature cycling, freeze-thaw activity, precipitation-related corrosion potential, and wind effects. Monte Carlo simulation quantifies uncertainty across traffic-environment scenarios, while Random Forest models map fused features to fatigue indicators and maintenance classification. The framework demonstrates utilizing existing infrastructure for cost-effective predictive maintenance of aging, high-traffic bridges in harsh climates. --- ### SemEval-2026 Task 6: CLARITY -- Unmasking Political Question Evasions Authors: Konstantinos Thomas, Giorgos Filandrianos, Maria Lymperaiou, Chrysoula Zerva, Giorgos Stamou Published: 2026-03-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.14027v2 Political speakers often avoid answering questions directly while maintaining the appearance of responsiveness. Despite its importance for public discourse, such strategic evasion remains underexplored in Natural Language Processing. We introduce SemEval-2026 Task 6, CLARITY, a shared task on political question evasion consisting of two subtasks: (i) clarity-level classification into Clear Reply, Ambivalent, and Clear Non-Reply, and (ii) evasion-level classification into nine fine-grained evasion strategies. The benchmark is constructed from U.S. presidential interviews and follows an expert-grounded taxonomy of response clarity and evasion. The task attracted 124 registered teams, who submitted 946 valid runs for clarity-level classification and 539 for evasion-level classification. Results show a substantial gap in difficulty between the two subtasks: the best system achieved 0.89 macro-F1 on clarity classification, surpassing the strongest baseline by a large margin, while the top evasion-level system reached 0.68 macro-F1, matching the best baseline. Overall, large language model prompting and hierarchical exploitation of the taxonomy emerged as the most effective strategies, with top systems consistently outperforming those that treated the two subtasks independently. CLARITY establishes political response evasion as a challenging benchmark for computational discourse analysis and highlights the difficulty of modeling strategic ambiguity in political language. --- ### High-speed Imaging through Turbulence with Event-based Light Fields Authors: Yu-Hsiang Huang, Levi Burner, Sachin Shah, Ziyuan Qu, Adithya Pediredla, Christopher A. Metzler Published: 2026-03-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14023v3 This work introduces and demonstrates the first system capable of imaging fast-moving extended non-rigid objects through strong atmospheric turbulence at high frame rate. Event cameras are a novel sensing architecture capable of estimating high-speed imagery at thousands of frames per second. However, on their own event cameras are unable to disambiguate scene motion from turbulence. In this work, we overcome this limitation using event-based light field cameras: By simultaneously capturing multiple views of a scene, event-based light field cameras and machine learning-based reconstruction algorithms are able to disambiguate motion-induced dynamics, which produce events that are strongly correlated across views, from turbulence-induced dynamics, which produce events that are weakly correlated across view. Tabletop experiments demonstrate event-based light field can overcome strong turbulence while imaging high-speed objects traveling at up to 16,000 pixels per second. --- ### High-speed Imaging through Turbulence with Event-based Light Fields Authors: Yu-Hsiang Huang, Levi Burner, Sachin Shah, Ziyuan Qu, Adithya Pediredla, Christopher A. Metzler Published: 2026-03-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14023v2 This work introduces and demonstrates the first system capable of imaging fast-moving extended non-rigid objects through strong atmospheric turbulence at high frame rate. Event cameras are a novel sensing architecture capable of estimating high-speed imagery at thousands of frames per second. However, on their own event cameras are unable to disambiguate scene motion from turbulence. In this work, we overcome this limitation using event-based light field cameras: By simultaneously capturing multiple views of a scene, event-based light field cameras and machine learning-based reconstruction algorithms are able to disambiguate motion-induced dynamics, which produce events that are strongly correlated across views, from turbulence-induced dynamics, which produce events that are weakly correlated across view. Tabletop experiments demonstrate event-based light field can overcome strong turbulence while imaging high-speed objects traveling at up to 16,000 pixels per second. --- ### A Hyperbolic Perspective on Hierarchical Structure in Object-Centric Scene Representations Authors: Neelu Madan, Àlex Pujol, Andreas Møgelmose, Sergio Escalera, Kamal Nasrollahi, Graham W. Taylor, Thomas B. Moeslund Published: 2026-03-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14022v2 Slot attention has emerged as a powerful framework for unsupervised object-centric learning, decomposing visual scenes into a small set of compact vector representations called \emph{slots}, each capturing a distinct region or object. However, these slots are learned in Euclidean space, which provides no geometric inductive bias for the hierarchical relationships that naturally structure visual scenes. In this work, we propose a simple post-hoc pipeline to project Euclidean slot embeddings onto the Lorentz hyperboloid of hyperbolic space, without modifying the underlying training pipeline. We construct five-level visual hierarchies directly from slot attention masks and analyse whether hyperbolic geometry reveals latent hierarchical structure that remains invisible in Euclidean space. Integrating our pipeline with SPOT (images), VideoSAUR (video), and SlotContrast (video), We find that hyperbolic projection exposes a consistent scene-level to object-level organisation, where coarse slots occupy greater manifold depth than fine slots, which is absent in Euclidean space. We further identify a "curvature--task tradeoff": low curvature ($c{=}0.2$) matches or outperforms Euclidean on parent slot retrieval, while moderate curvature ($c{=}0.5$) achieves better inter-level separation. Together, these findings suggest that slot representations already encode latent hierarchy that hyperbolic geometry reveals, motivating end-to-end hyperbolic training as a natural next step. Code and models are available at \href{https://github.com/NeeluMadan/HHS}{github.com/NeeluMadan/HHS}. --- ### EI-Part: Explode for Completion and Implode for Refinement Authors: Wanhu Sun, Zhongjin Luo, Heliang Zheng, Jiahao Chang, Chongjie Ye, Huiang He, Shengchu Zhao, Rongfei Jia, Xiaoguang Han Published: 2026-03-14 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.14021v1 Part-level 3D generation is crucial for various downstream applications, including gaming, film production, and industrial design. However, decomposing a 3D shape into geometrically plausible and meaningful components remains a significant challenge. Previous part-based generation methods often struggle to produce well-constructed parts, exhibiting poor structural coherence, geometric implausibility, inaccuracy, or inefficiency. To address these challenges, we introduce EI-Part, a novel framework specifically designed to generate high-quality 3D shapes with components, characterized by strong structural coherence, geometric plausibility, geometric fidelity, and generation efficiency. We propose utilizing distinct representations at different stages: an Explode state for part completion and an Implode state for geometry refinement. This strategy fully leverages spatial resolution, enabling flexible part completion and fine geometric detail generation. To maintain structural coherence between parts, a self-attention mechanism is incorporated in both exploded and imploded states, facilitating effective information perception and feature fusion among components during generation. Extensive experiments on multiple benchmarks demonstrate that EI-Part efficiently produces semantically meaningful and structurally coherent parts with fine-grained geometric details, achieving state-of-the-art performance in part-level 3D generation. Project page: https://cvhadessun.github.io/EI-Part/ --- ### Aumann-SHAP: The Geometry of Counterfactual Interaction Explanations in Machine Learning Authors: Adam Belahcen, Stéphane Mussard Published: 2026-03-14 Categories: cs.LG, cs.GT arXiv: https://arxiv.org/abs/2603.14014v2 We introduce Aumann-SHAP, an interaction-aware framework that decomposes counterfactual transitions by restricting the model to a local hypercube connecting baseline and counterfactual features. Each hypercube is discretized into a grid to construct an induced micro-player cooperative game in which elementary grid-step moves become players. Shapley and LES values on this TU-micro-game yield geometry-aware within-pot attributions that converge to the diagonal Aumann--Shapley / Integrated Gradients limit under grid refinement, and recover equal-split Shapley as the degenerate $m=1$ special case. An exact grid-state closed form gives polynomial-time computation for fixed interaction order. On a synthetic benchmark with known ground truth, equal-split Shapley carries an irreducible bias while Aumann-SHAP converges to the correct decomposition. On German Credit, interaction geometry changes feature priority rankings in $12.3\%$ of instances. On UCI Heart Disease, equal-split misattributes a cholesterol suppressor as a positive contributor, which is a sign error Aumann-SHAP corrects. On MNIST, game-theoretic attribution reaches target confidence with $3.5\times$ fewer edits than magnitude-based ordering, with micro-game Shapley achieving the best efficiency across all budgets. --- ### Multi-Grained Vision-Language Alignment for Domain Generalized Person Re-Identification Authors: Jiachen Li, Xiaojin Gong, Dongping Zhang Published: 2026-03-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14012v1 Domain Generalized person Re-identification (DG Re-ID) is a challenging task, where models are trained on source domains but tested on unseen target domains. Although previous pure vision-based models have achieved significant progress, the performance remains further improved. Recently, Vision-Language Models (VLMs) present outstanding generalization capabilities in various visual applications. However, directly adapting a VLM to Re-ID shows limited generalization improvement. This is because the VLM only produces with global features that are insensitive to ID nuances. To tacle this problem, we propose a CLIP-based multi-grained vision-language alignment framework in this work. Specifically, several multi-grained prompts are introduced in language modality to describe different body parts and align with their counterparts in vision modality. To obtain fine-grained visual information, an adaptively masked multi-head self-attention module is employed to precisely extract specific part features. To train the proposed module, an MLLM-based visual grounding expert is employed to automatically generate pseudo labels of body parts for supervision. Extensive experiments conducted on both single- and multi-source generalization protocols demonstrate the superior performance of our approach. The implementation code will be released at https://github.com/RikoLi/MUVA. --- ### Formal Abductive Explanations for Navigating Mental Health Help-Seeking and Diversity in Tech Workplaces Authors: Belona Sonna, Alain Momo, Alban Grastien Published: 2026-03-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.14007v1 This work proposes a formal abductive explanation framework designed to systematically uncover rationales underlying AI predictions of mental health help-seeking within tech workplace settings. By computing rigorous justifications for model outputs, this approach enables principled selection of models tailored to distinct psychiatric profiles and underpins ethically robust recourse planning. Beyond moving past ad-hoc interpretability, we explicitly examine the influence of sensitive attributes such as gender on model decisions, a critical component for fairness assessments. In doing so, it aligns explanatory insights with the complex landscape of workplace mental health, ultimately supporting trustworthy deployment and targeted interventions. --- ### Beyond Explicit Edges: Robust Reasoning over Noisy and Sparse Knowledge Graphs Authors: Hang Gao, Dimitris N. Metaxas Published: 2026-03-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.14006v1 GraphRAG is increasingly adopted for converting unstructured corpora into graph structures to enable multi-hop reasoning. However, standard graph algorithms rely heavily on static connectivity and explicit edges, often failing in real-world scenarios where knowledge graphs (KGs) are noisy, sparse, or incomplete. To address this limitation, we introduce INSES (Intelligent Navigation and Similarity Enhanced Search), a dynamic framework designed to reason beyond explicit edges. INSES couples LLM-guided navigation, which prunes noise and steers exploration, with embedding-based similarity expansion to recover hidden links and bridge semantic gaps. Recognizing the computational cost of graph reasoning, we complement INSES with a lightweight router that delegates simple queries to Naïve RAG and escalates complex cases to INSES, balancing efficiency with reasoning depth. INSES consistently outperforms SOTA RAG and GraphRAG baselines across multiple benchmarks. Notably, on the MINE benchmark, it demonstrates superior robustness across KGs constructed by varying methods (KGGEN, GraphRAG, OpenIE), improving accuracy by 5%, 10%, and 27%, respectively. --- ### Towards Generalizable Deepfake Detection via Real Distribution Bias Correction Authors: Ming-Hui Liu, Harry Cheng, Xin Luo, Xin-Shun Xu, Mohan S. Kankanhalli Published: 2026-03-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14005v2 To generalize deepfake detectors to future unseen forgeries, most existing methods attempt to simulate the dynamically evolving forgery types using available source domain data. However, predicting an unbounded set of future manipulations from limited prior examples is infeasible. To overcome this limitation, we propose to exploit the invariance of \textbf{real data} from two complementary perspectives: the fixed population distribution of the entire real class and the inherent Gaussianity of individual real images. Building on these properties, we introduce the Real Distribution Bias Correction (RDBC) framework, which consists of two key components: the Real Population Distribution Estimation module and the Distribution-Sampled Feature Whitening module. The former utilizes the independent and identically distributed (\iid) property of real samples to derive the normal distribution form of their statistics, from which the distribution parameters can be estimated using limited source domain data. Based on the learned population distribution, the latter utilizes the inherent Gaussianity of real data as a discriminative prior and performs a sampling-based whitening operation to amplify the Gaussianity gap between real and fake samples. Through synergistic coupling of the two modules, our model captures the real-world properties of real samples, thereby enhancing its generalizability to unseen target domains. Extensive experiments demonstrate that RDBC achieves state-of-the-art performance in both in-domain and cross-domain deepfake detection. --- ### Towards Generalizable Deepfake Detection via Real Distribution Bias Correction Authors: Ming-Hui Liu, Harry Cheng, Xin Luo, Xin-Shun Xu, Mohan S. Kankanhalli Published: 2026-03-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14005v1 To generalize deepfake detectors to future unseen forgeries, most existing methods attempt to simulate the dynamically evolving forgery types using available source domain data. However, predicting an unbounded set of future manipulations from limited prior examples is infeasible. To overcome this limitation, we propose to exploit the invariance of \textbf{real data} from two complementary perspectives: the fixed population distribution of the entire real class and the inherent Gaussianity of individual real images. Building on these properties, we introduce the Real Distribution Bias Correction (RDBC) framework, which consists of two key components: the Real Population Distribution Estimation module and the Distribution-Sampled Feature Whitening module. The former utilizes the independent and identically distributed (\iid) property of real samples to derive the normal distribution form of their statistics, from which the distribution parameters can be estimated using limited source domain data. Based on the learned population distribution, the latter utilizes the inherent Gaussianity of real data as a discriminative prior and performs a sampling-based whitening operation to amplify the Gaussianity gap between real and fake samples. Through synergistic coupling of the two modules, our model captures the real-world properties of real samples, thereby enhancing its generalizability to unseen target domains. Extensive experiments demonstrate that RDBC achieves state-of-the-art performance in both in-domain and cross-domain deepfake detection. --- ### U-Face: An Efficient and Generalizable Framework for Unsupervised Facial Attribute Editing via Subspace Learning Authors: Bo Liu, Xuan Cui, Run Zeng, Wei Duan, Chongwen Liu, Jinrui Qian, Lianggui Tang, Hongping Gan Published: 2026-03-14 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.14004v1 Latent space-based facial attribute editing methods have gained popularity in applications such as digital entertainment, virtual avatar creation, and human-computer interaction systems due to their potential for efficient and flexible attribute manipulation, particularly for continuous edits. Among these, unsupervised latent space-based methods, which discover effective semantic vectors without relying on labeled data, have attracted considerable attention in the research community. However, existing methods still encounter difficulties in disentanglement, as manipulating a specific facial attribute may unintentionally affect other attributes, complicating fine-grained controllability. To address these challenges, we propose a novel framework designed to offer an effective and adaptable solution for unsupervised facial attribute editing, called Unsupervised Facial Attribute Controllable Editing (U-Face). The proposed method frames semantic vector learning as a subspace learning problem, where latent vectors are approximated within a lower-dimensional semantic subspace spanned by a semantic vector matrix. This formulation can also be equivalently interpreted from a projection-reconstruction perspective and further generalized into an autoencoder framework, providing a foundation that can support disentangled representation learning in a flexible manner. To improve disentanglement and controllability, we impose orthogonal non-negative constraints on the semantic vectors and incorporate attribute boundary vectors to reduce entanglement in the learned directions. Although these constraints make the optimization problem challenging, we design an alternating iterative algorithm, called Alternating Iterative Disentanglement and Controllability (AIDC), with closed-form updates and provable convergence under specific conditions. --- ### The Taxonomies, Training, and Applications of Event Stream Modelling for Electronic Health Records Authors: Mingcheng Zhu, Yu Liu, Zhiyao Luo, Tingting Zhu Published: 2026-03-14 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2603.14003v1 The widespread adoption of electronic health records (EHRs) enables the acquisition of heterogeneous clinical data, spanning lab tests, vital signs, medications, and procedures, which offer transformative potential for artificial intelligence in healthcare. Although traditional modelling approaches have typically relied on multivariate time series, they often struggle to accommodate the inherent sparsity and irregularity of real-world clinical workflows. Consequently, research has shifted toward event stream representation, which treats patient records as continuous sequences, thereby preserving the precise temporal structure of the patient journey. However, the existing literature remains fragmented, characterised by inconsistent definitions, disparate modelling architectures, and varying training protocols. To address these gaps, this review establishes a unified definition of EHR event streams and introduces a novel taxonomy that categorises models based on their handling of event time, type, and value. We systematically review training strategies, ranging from supervised learning to self-supervised methods, and provide a comprehensive discussion of applications across clinical scenarios. Finally, we identify open critical challenges and future directions, with the aim of clarifying the current landscape and guiding the development of next-generation healthcare models. --- ### PhyGaP: Physically-Grounded Gaussians with Polarization Cues Authors: Jiale Wu, Xiaoyang Bai, Zongqi He, Weiwei Xu, Yifan Peng Published: 2026-03-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14001v1 Recent advances in 3D Gaussian Splatting (3DGS) have demonstrated great success in modeling reflective 3D objects and their interaction with the environment via deferred rendering (DR). However, existing methods often struggle with correctly reconstructing physical attributes such as albedo and reflectance, and therefore they do not support high-fidelity relighting. Observing that this limitation stems from the lack of shape and material information in RGB images, we present PhyGaP, a physically-grounded 3DGS method that leverages polarization cues to facilitate precise reflection decomposition and visually consistent relighting of reconstructed objects. Specifically, we design a polarimetric deferred rendering (PolarDR) process to model polarization by reflection, and a self-occlusion-aware environment map building technique (GridMap) to resolve indirect lighting of non-convex objects. We validate on multiple synthetic and real-world scenes, including those featuring only partial polarization cues, that PhyGaP not only excels in reconstructing the appearance and surface normal of reflective 3D objects (~2 dB in PSNR and 45.7% in Cosine Distance better than existing RGB-based methods on average), but also achieves state-of-the-art inverse rendering and relighting capability. Our code will be released soon. --- ### A Systematic Evaluation Protocol of Graph-Derived Signals for Tabular Machine Learning Authors: Mario Heidrich, Jeffrey Heidemann, Rüdiger Buchkremer, Gonzalo Wandosell Fernández de Bobadilla Published: 2026-03-14 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.13998v1 While graph-derived signals are widely used in tabular learning, existing studies typically rely on limited experimental setups and average performance comparisons, leaving the statistical reliability and robustness of observed gains largely unexplored. Consequently, it remains unclear which signals provide consistent and robust improvements. This paper presents a taxonomy-driven empirical analysis of graph-derived signals for tabular machine learning. We propose a unified and reproducible evaluation protocol to systematically assess which categories of graph-derived signals yield statistically significant and robust performance improvements. The protocol provides an extensible setup for the controlled integration of diverse graph-derived signals into tabular learning pipelines. To ensure a fair and rigorous comparison, it incorporates automated hyperparameter optimization, multi-seed statistical evaluation, formal significance testing, and robustness analysis under graph perturbations. We demonstrate the protocol through an extensive case study on a large-scale, imbalanced cryptocurrency fraud detection dataset. The analysis identifies signal categories providing consistently reliable performance gains and offers interpretable insights into which graph-derived signals indicate fraud-discriminative structural patterns. Furthermore, robustness analyses reveal pronounced differences in how various signals handle missing or corrupted relational data. These findings demonstrate practical utility for fraud detection and illustrate how the proposed taxonomy-driven evaluation protocol can be applied in other application domains. --- ### Location Aware Embedding for Geotargeting in Sponsored Search Advertising Authors: Jelena Gligorijevic, Djordje Gligorijevic, Aravindan Raghuveer, Mihajlo Grbovic, Zoran Obradovic Published: 2026-03-14 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2603.13997v1 Web search has become an inevitable part of everyday life. Improving and monetizing web search has been a focus of major Internet players. Understanding the context of web search query is an important aspect of this task as it represents unobserved facts that add meaning to an otherwise incomplete query.The context of a query consists of user's location, local time, search history, behavioral segments, installed apps on their phone and so on. Queries that either explicitly use location context (eg: "best hotels in New York City") or implicitly refer to the user's physical location (e.g. "coffee shops near me") are becoming increasingly common on mobile devices. Understanding and representing the user's interest location and/or physical location is essential for providing a relevant user experience. In this study, we developed a simple and powerful neural embedding based framework to represent a user's query and their location in a single low-dimensional space. We show that this representation is able to capture the subtle interactions between the user's query intent and query/physical location, while improving the ad ranking and query-ad relevance scores over other location-unaware approaches and location-aware approaches. --- ### Human-like Object Grouping in Self-supervised Vision Transformers Authors: Hossein Adeli, Seoyoung Ahn, Andrew Luo, Mengmi Zhang, Nikolaus Kriegeskorte, Gregory Zelinsky Published: 2026-03-14 Categories: cs.CV, cs.AI, q-bio.NC arXiv: https://arxiv.org/abs/2603.13994v3 Vision foundation models trained with self-supervised objectives achieve strong performance across diverse tasks and exhibit emergent object segmentation properties. However, their alignment with human object perception remains poorly understood. Here, we introduce a behavioral benchmark in which participants make same/different object judgments for dot pairs on naturalistic scenes, scaling up a classical psychophysics paradigm to over 1000 trials. We test a diverse set of vision models using a simple readout from their representations to predict subjects' reaction times. We observe a steady improvement across model generations, with both architecture and training objective contributing to alignment, and transformer-based models trained with the DINO self-supervised objective showing the strongest performance. To investigate the source of this improvement, we propose a novel metric to quantify the object-centric component of representations by measuring patch similarity within and between objects. Across models, stronger object-centric structure predicts human segmentation behavior more accurately. We further show that matching the Gram matrix of supervised transformer models, capturing similarity structure across image patches, with that of a self-supervised model through distillation improves their alignment with human behavior, converging with the prior finding that Gram anchoring improves DINOv3's feature quality. Together, these results demonstrate that self-supervised vision models capture object structure in a behaviorally human-like manner, and that Gram matrix structure plays a role in driving perceptual alignment. --- ### VAD4Space: Visual Anomaly Detection for Planetary Surface Imagery Authors: Fabrizio Genilotti, Arianna Stropeni, Francesco Borsatti, Manuel Barusco, Davide Dalle Pezze, Gian Antonio Susto Published: 2026-03-14 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.13993v1 Space missions generate massive volumes of high-resolution orbital and surface imagery that far exceed the capacity for manual inspection. Detecting rare phenomena is scientifically critical, yet traditional supervised learning struggles due to scarce labeled examples and closed-world assumptions that prevent discovery of genuinely novel observations. In this work, we investigate Visual Anomaly Detection (VAD) as a framework for automated discovery in planetary exploration. We present the first empirical evaluation of state-of-the-art feature-based VAD methods on real planetary imagery, encompassing both orbital lunar data and Mars rover surface imagery. To support this evaluation, we introduce two benchmarks: (i) a lunar dataset derived from Lunar Reconnaissance Orbiter Camera Narrow Angle imagery, comprising of fresh and degraded craters as anomalies alongside normal terrain; and (ii) a Mars surface dataset designed to reflect the characteristics of rover-acquired imagery. We evaluate multiple VAD approaches with a focus on computationally efficient, edge-oriented solutions suitable for onboard deployment, applicable to both orbital platforms surveying the lunar surface and surface rovers operating on Mars. Our results demonstrate that feature-based VAD methods can effectively identify rare planetary surface phenomena while remaining feasible for resource-constrained environments. By grounding anomaly detection in planetary science, this work establishes practical benchmarks and highlights the potential of open-world perception systems to support a range of mission-critical applications, including tactical planning, landing site selection, hazard detection, bandwidth-aware data prioritization, and the discovery of unanticipated geological processes. --- ### Faithful or Just Plausible? Evaluating the Faithfulness of Closed-Source LLMs in Medical Reasoning Authors: Halimat Afolabi, Zainab Afolabi, Elizabeth Friel, Jude Roberts, Antonio Ji-Xu, Lloyd Chen, Egheosa Ogbomo, Emiliomo Imevbore, Phil Eneje, Wissal El Ouahidi, Aaron Sohal, Alisa Kennan et al. Published: 2026-03-14 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.13988v1 Closed-source large language models (LLMs), such as ChatGPT and Gemini, are increasingly consulted for medical advice, yet their explanations may appear plausible while failing to reflect the model's underlying reasoning process. This gap poses serious risks as patients and clinicians may trust coherent but misleading explanations. We conduct a systematic black-box evaluation of faithfulness in medical reasoning among three widely used closed-source LLMs. Our study consists of three perturbation-based probes: (1) causal ablation, testing whether stated chain-of-thought (CoT) reasoning causally influences predictions; (2) positional bias, examining whether models create post-hoc justifications for answers driven by input positioning; and (3) hint injection, testing susceptibility to external suggestions. We complement these quantitative probes with a small-scale human evaluation of model responses to patient-style medical queries to examine concordance between physician assessments of explanation faithfulness and layperson perceptions of trustworthiness. We find that CoT reasoning steps often do not causally drive predictions, and models readily incorporate external hints without acknowledgment. In contrast, positional biases showed minimal impact in this setting. These results underscore that faithfulness, not just accuracy, must be central in evaluating LLMs for medicine, to ensure both public protection and safe clinical deployment. --- ### Supervised Fine-Tuning versus Reinforcement Learning: A Study of Post-Training Methods for Large Language Models Authors: Haitao Jiang, Wenbo Zhang, Jiarui Yao, Hengrui Cai, Sheng Wang, Rui Song Published: 2026-03-14 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.13985v1 Pre-trained Large Language Model (LLM) exhibits broad capabilities, yet, for specific tasks or domains their attainment of higher accuracy and more reliable reasoning generally depends on post-training through Supervised Fine-Tuning (SFT) or Reinforcement Learning (RL). Although often treated as distinct methodologies, recent theoretical and empirical developments demonstrate that SFT and RL are closely connected. This study presents a comprehensive and unified perspective on LLM post-training with SFT and RL. We first provide an in-depth overview of both techniques, examining their objectives, algorithmic structures, and data requirements. We then systematically analyze their interplay, highlighting frameworks that integrate SFT and RL, hybrid training pipelines, and methods that leverage their complementary strengths. Drawing on a representative set of recent application studies from 2023 to 2025, we identify emerging trends, characterize the rapid shift toward hybrid post-training paradigms, and distill key takeaways that clarify when and why each method is most effective. By synthesizing theoretical insights, practical methodologies, and empirical evidence, this study establishes a coherent understanding of SFT and RL within a unified framework and outlines promising directions for future research in scalable, efficient, and generalizable LLM post-training. --- ### Exploiting temporal parallelism for LSTM Autoencoder acceleration on FPGA Authors: Aimilios Leftheriotis, Dimosthenis Masouros, Dimitrios Soudris, George Theodoridis Published: 2026-03-14 Categories: cs.AR, cs.LG arXiv: https://arxiv.org/abs/2603.13982v1 Recurrent Neural Networks (RNNs) are vital for sequential data processing. Long Short-Term Memory Autoencoders (LSTM-AEs) are particularly effective for unsupervised anomaly detection in time-series data. However, inherent sequential dependencies limit parallel computation. While previous work has explored FPGA-based acceleration for LSTM networks, efforts have typically focused on optimizing a single LSTM layer at a time. We introduce a novel FPGA-based accelerator using a dataflow architecture that exploits temporal parallelism for concurrent multi-layer processing of different timesteps within sequences. Experimental evaluations on four representative LSTM-AE models with varying widths and depths, implemented on a Zynq UltraScale+ MPSoC FPGA, demonstrate significant advantages over CPU (Intel Xeon Gold 5218R) and GPU (NVIDIA V100) implementations. Our accelerator achieves latency speedups up to 79.6x vs. CPU and 18.2x vs. GPU, alongside energy-per-timestep reductions of up to 1722x vs. CPU and 59.3x vs. GPU. These results, including superior network depth scalability, highlight our approach's potential for high-performance, real-time, power-efficient LSTM-AE-based anomaly detection on FPGAs. --- ### When Visual Privacy Protection Meets Multimodal Large Language Models Authors: Xiaofei Hui, Qian Wu, Haoxuan Qu, Majid Mirmehdi, Hossein Rahmani, Jun Liu Published: 2026-03-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.13978v1 The emergence of Multimodal Large Language Models (MLLMs) and the widespread usage of MLLM cloud services such as GPT-4V raised great concerns about privacy leakage in visual data. As these models are typically deployed in cloud services, users are required to submit their images and videos, posing serious privacy risks. However, how to tackle such privacy concerns is an under-explored problem. Thus, in this paper, we aim to conduct a new investigation to protect visual privacy when enjoying the convenience brought by MLLM services. We address the practical case where the MLLM is a "black box", i.e., we only have access to its input and output without knowing its internal model information. To tackle such a challenging yet demanding problem, we propose a novel framework, in which we carefully design the learning objective with Pareto optimality to seek a better trade-off between visual privacy and MLLM's performance, and propose critical-history enhanced optimization to effectively optimize the framework with the black-box MLLM. Our experiments show that our method is effective on different benchmarks. --- ### FLUX: Data Worth Training On Authors: Gowtham, Sai Rupesh, Sanjay Kumar, Saravanan, Venkata Chaithanya Published: 2026-03-14 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.13972v1 Modern large language model training is no longer limited by data availability, but by the inability of existing preprocessing pipelines to simultaneously achieve massive scale and high data quality. Current approaches are forced to sacrifice one for the other: either aggressively filtering to improve quality at the cost of severe token loss, or retaining large volumes of data while introducing substantial noise. In this work, we introduce FLUX, a preprocessing pipeline specifically designed to break this long-standing trade-off by maximizing token retention while enforcing rigorous quality control. Models trained on FLUX-curated data consistently outperform prior methods. A 3B-parameter model trained on 60B tokens with FLUX achieves 32.14% MMLU accuracy, surpassing the previous state-of-the-art pipeline DCLM (31.98%) and significantly outperforming FineWeb (29.88%). FLUX achieves the same aggregate score as a model trained on DCLM data using only 39B tokens, resulting in a 34.4% reduction in training compute. At the data level, FLUX extracts 50B usable tokens from a single dump (CC-MAIN-2025-51), compared to 40B from DCLM (+25% retention). FLUX-Base yields 192B tokens, exceeding FineWeb's 170B while still maintaining superior quality. Overall, FLUX establishes a new state of the art in web-scale data preprocessing by demonstrating that high retention, strong quality control, and computational efficiency can be achieved simultaneously, redefining the limits of scalable dataset construction for modern language models. --- ### Chunk-Guided Q-Learning Authors: Gwanwoo Song, Kwanyoung Park, Youngwoon Lee Published: 2026-03-14 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.13971v1 In offline reinforcement learning (RL), single-step temporal-difference (TD) learning can suffer from bootstrapping error accumulation over long horizons. Action-chunked TD methods mitigate this by backing up over multiple steps, but can introduce suboptimality by restricting the policy class to open-loop action sequences. To resolve this trade-off, we present Chunk-Guided Q-Learning (CGQ), a single-step TD algorithm that guides a fine-grained single-step critic by regularizing it toward a chunk-based critic trained using temporally extended backups. This reduces compounding error while preserving fine-grained value propagation. We theoretically show that CGQ attains tighter critic optimality bounds than either single-step or action-chunked TD learning alone. Empirically, CGQ achieves strong performance on challenging long-horizon OGBench tasks, often outperforming both single-step and action-chunked methods. --- ### Shapes are not enough: CONSERVAttack and its use for finding vulnerabilities and uncertainties in machine learning applications Authors: Philip Bechtle, Lucie Flek, Philipp Alexander Jung, Akbar Karimi, Timo Saala, Alexander Schmidt, Matthias Schott, Philipp Soldin, Christopher Wiebusch, Ulrich Willemsen Published: 2026-03-14 Categories: cs.LG, hep-ex arXiv: https://arxiv.org/abs/2603.13970v2 In High Energy Physics, as in many other fields of science, the application of machine learning techniques has been crucial in advancing our understanding of fundamental phenomena. Increasingly, deep learning models are applied to analyze both simulated and experimental data. In most experiments, a rigorous regime of testing for physically motivated systematic uncertainties is in place. The numerical evaluation of these tests for differences between the data on the one side and simulations on the other side quantifies the effect of potential sources of mismodelling on the machine learning output. In addition, thorough comparisons of marginal distributions and (linear) feature correlations between data and simulation in "control regions" are applied. However, the guidance by physical motivation, and the need to constrain comparisons to specific regions, does not guarantee that all possible sources of deviations have been accounted for. We therefore propose a new adversarial attack - the CONSERVAttack - designed to exploit the remaining space of hypothetical deviations between simulation and data after the above mentioned tests. The resulting adversarial perturbations are consistent within the uncertainty bounds - evading standard validation checks - while successfully fooling the underlying model. We further propose strategies to mitigate such vulnerabilities and argue that robustness to adversarial effects must be considered when interpreting results from deep learning in particle physics. --- ### Leveraging a Statistical Shape Model for Efficient Generation of Annotated Training Data: A Case Study on Liver Landmarks Segmentation Authors: Denis Krnjaca, Lorena Krames, Werner Nahm Published: 2026-03-14 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2603.13969v1 Anatomical landmark segmentation serves as a critical initial step for robust multimodal registration during computer-assisted interventions. Current approaches predominantly rely on deep learning, which often necessitates the extensive manual generation of annotated datasets. In this paper, we present a novel strategy for creating large annotated datasets using a statistical shape model (SSM) based on a mean shape that is manually labeled only once. We demonstrate the method's efficacy through its application to deep-learning-based anatomical landmark segmentation, specifically targeting the detection of the anterior ridge and the falciform ligament in 3D liver shapes. A specialized deep learning network was trained with 8,800 annotated liver shapes generated by the SSM. The network's performance was evaluated on 500 unseen synthetic SSM shapes, yielding a mean Intersection over Union of 91.4% (87.4% for the anterior ridge and 87.6% for the falciform ligament). Subsequently, the network was applied to clinical patient liver shapes, with qualitative evaluation indicating promising results and highlighting the generalizability of the proposed approach. Our findings suggest that the SSM-based data generation approach alleviates the labor-intensive process of manual labeling while enabling the creation of large annotated training datasets for machine learning. Although our study focuses on liver anatomy, the proposed methodology holds potential for a broad range of applications where annotated training datasets play a pivotal role in developing accurate deep-learning models. --- ### EchoLVFM: One-Step Video Generation via Latent Flow Matching for Echocardiogram Synthesis Authors: Emmanuel Oladokun, Sarina Thomas, Jurica Šprem, Vicente Grau Published: 2026-03-14 Categories: eess.IV, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2603.13967v1 Echocardiography is widely used for assessing cardiac function, where clinically meaningful parameters such as left-ventricular ejection fraction (EF) play a central role in diagnosis and management. Generative models capable of synthesising realistic echocardiogram videos with explicit control over such parameters are valuable for data augmentation, counterfactual analysis, and specialist training. However, existing approaches typically rely on computationally expensive multi-step sampling and aggressive temporal normalisation, limiting efficiency and applicability to heterogeneous real-world data. We introduce EchoLVFM, a one-step latent video flow-matching framework for controllable echocardiogram generation. Operating in the latent space, EchoLVFM synthesises temporally coherent videos in a single inference step, achieving a $\mathbf{\sim 50\times}$ improvement in sampling efficiency compared to multi-step flow baselines while maintaining visual fidelity. The model supports global conditioning on clinical variables, demonstrated through precise control of EF, and enables reconstruction and counterfactual generation from partially observed sequences. A masked conditioning strategy further removes fixed-length constraints, allowing shorter sequences to be retained rather than discarded. We evaluate EchoLVFM on the CAMUS dataset under challenging single-frame conditioning. Quantitative and qualitative results demonstrate competitive video quality, strong EF adherence, and 57.9% discrimination accuracy by expert clinicians which is close to chance. These findings indicate that efficient, one-step flow matching can enable practical, controllable echocardiogram video synthesis without sacrificing fidelity. Code available at: https://github.com/EngEmmanuel/EchoLVFM --- ### vla-eval: A Unified Evaluation Harness for Vision-Language-Action Models Authors: Suhwan Choi, Yunsung Lee, Yubeen Park, Chris Dongjoo Kim, Ranjay Krishna, Dieter Fox, Youngjae Yu Published: 2026-03-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.13966v3 Vision-Language-Action (VLA) models are increasingly evaluated across multiple simulation benchmarks, yet adding each benchmark to an evaluation pipeline requires resolving incompatible dependencies, matching underspecified evaluation protocols, and reverse-engineering undocumented preprocessing. This burden scales with the number of models and benchmarks, making comprehensive evaluation impractical for most teams. We present vla-eval, an open-source evaluation harness that eliminates this per-benchmark cost by decoupling model inference from benchmark execution through a WebSocket+msgpack protocol with Docker-based environment isolation. Models integrate once by implementing a single predict() method; benchmarks integrate once via a four-method interface; the full cross-evaluation matrix works automatically. The framework supports 14 simulation benchmarks and six model servers. Parallel evaluation via episode sharding and batch inference achieves up to 47x wall-clock speedup, completing 2,000 LIBERO episodes in ~18 minutes. To validate the framework, we reproduce published scores across six VLA codebases and three benchmarks, documenting previously undocumented pitfalls. We additionally release a VLA leaderboard aggregating 657 published results across 17 benchmarks. Framework, evaluation configs, and all reproduction results are publicly available at https://github.com/allenai/vla-evaluation-harness and https://allenai.github.io/vla-evaluation-harness/leaderboard. --- ### vla-eval: A Unified Evaluation Harness for Vision-Language-Action Models Authors: Suhwan Choi, Yunsung Lee, Yubeen Park, Chris Dongjoo Kim, Ranjay Krishna, Dieter Fox, Youngjae Yu Published: 2026-03-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.13966v2 Vision-Language-Action (VLA) models are increasingly evaluated across multiple simulation benchmarks, yet adding each benchmark to an evaluation pipeline requires resolving incompatible dependencies, matching underspecified evaluation protocols, and reverse-engineering undocumented preprocessing. This burden scales with the number of models and benchmarks, making comprehensive evaluation impractical for most teams. We present vla-eval, an open-source evaluation harness that eliminates this per-benchmark cost by decoupling model inference from benchmark execution through a WebSocket+msgpack protocol with Docker-based environment isolation. Models integrate once by implementing a single predict() method; benchmarks integrate once via a four-method interface; the full cross-evaluation matrix works automatically. The framework supports 14 simulation benchmarks and six model servers. Parallel evaluation via episode sharding and batch inference achieves up to 47x wall-clock speedup, completing 2,000 LIBERO episodes in ~18 minutes. To validate the framework, we reproduce published scores across six VLA codebases and three benchmarks, documenting previously undocumented pitfalls. We additionally release a VLA leaderboard aggregating 657 published results across 17 benchmarks. Framework, evaluation configs, and all reproduction results are publicly available at https://github.com/allenai/vla-evaluation-harness and https://allenai.github.io/vla-evaluation-harness/leaderboard. --- ### VID-AD: A Dataset for Image-Level Logical Anomaly Detection under Vision-Induced Distraction Authors: Hiroto Nakata, Yawen Zou, Shunsuke Sakai, Shun Maeda, Chunzhi Gu, Yijin Wei, Shangce Gao, Chao Zhang Published: 2026-03-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.13964v1 Logical anomaly detection in industrial inspection remains challenging due to variations in visual appearance (e.g., background clutter, illumination shift, and blur), which often distract vision-centric detectors from identifying rule-level violations. However, existing benchmarks rarely provide controlled settings where logical states are fixed while such nuisance factors vary. To address this gap, we introduce VID-AD, a dataset for logical anomaly detection under vision-induced distraction. It comprises 10 manufacturing scenarios and five capture conditions, totaling 50 one-class tasks and 10,395 images. Each scenario is defined by two logical constraints selected from quantity, length, type, placement, and relation, with anomalies including both single-constraint and combined violations. We further propose a language-based anomaly detection framework that relies solely on text descriptions generated from normal images. Using contrastive learning with positive texts and contradiction-based negative texts synthesized from these descriptions, our method learns embeddings that capture logical attributes rather than low-level features. Extensive experiments demonstrate consistent improvements over baselines across the evaluated settings. The dataset is available at: https://github.com/nkthiroto/VID-AD. --- ### sebis at ArchEHR-QA 2026: How Much Can You Do Locally? Evaluating Grounded EHR QA on a Single Notebook Authors: Ibrahim Ebrar Yurt, Fabian Karl, Tejaswi Choppa, Florian Matthes Published: 2026-03-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.13962v2 Clinical question answering over electronic health records (EHRs) can help clinicians and patients access relevant medical information more efficiently. However, many recent approaches rely on large cloud-based models, which are difficult to deploy in clinical environments due to privacy constraints and computational requirements. In this work, we investigate how far grounded EHR question answering can be pushed when restricted to a single notebook. We participate in all four subtasks of the ArchEHR-QA 2026 shared task and evaluate several approaches designed to run on commodity hardware. All experiments are conducted locally without external APIs or cloud infrastructure. Our results show that such systems can achieve competitive performance on the shared task leaderboards. In particular, our submissions perform above average in two subtasks, and we observe that smaller models can approach the performance of much larger systems when properly configured. These findings suggest that privacy-preserving EHR QA systems running fully locally are feasible with current models and commodity hardware. The source code is available at https://github.com/ibrahimey/ArchEHR-QA-2026. --- ### USIS-PGM: Photometric Gaussian Mixtures for Underwater Salient Instance Segmentation Authors: Lin Hong, Xiangtong Yao, Mürüvvet Bozkurt, Xin Wang, Fumin Zhang Published: 2026-03-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.13961v2 Underwater salient instance segmentation (USIS) is crucial for marine robotic systems, as it enables both underwater salient object detection and instance-level mask prediction for visual scene understanding. Compared with its terrestrial counterpart, USIS is more challenging due to the underwater image degradation. To address this issue, this paper proposes USIS-PGM, a single-stage framework for USIS. Specifically, the encoder enhances boundary cues through a frequency-aware module and performs content-adaptive feature reweighting via a dynamic weighting module. The decoder incorporates a Transformer-based instance activation module to better distinguish salient instances. In addition, USIS-PGM employs multi-scale Gaussian heatmaps generated from ground-truth masks through Photometric Gaussian Mixture (PGM) to supervise intermediate decoder features, thereby improving salient instance localization and producing more structurally coherent mask predictions. Experimental results demonstrate the superiority and practical applicability of the proposed USIS-PGM model. --- ### IMS3: Breaking Distributional Aggregation in Diffusion-Based Dataset Distillation Authors: Chenru Wang, Yunyi Chen, Zijun Yang, Joey Tianyi Zhou, Chi Zhang Published: 2026-03-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.13960v1 Dataset Distillation aims to synthesize compact datasets that can approximate the training efficacy of large-scale real datasets, offering an efficient solution to the increasing computational demands of modern deep learning. Recently, diffusion-based dataset distillation methods have shown great promise by leveraging the strong generative capacity of diffusion models to produce diverse and structurally consistent samples. However, a fundamental goal misalignment persists: diffusion models are optimized for generative likelihood rather than discriminative utility, resulting in over-concentration in high-density regions and inadequate coverage of boundary samples crucial for classification. To address this issue, we propose two complementary strategies. Inversion-Matching (IM) introduces an inversion-guided fine-tuning process that aligns denoising trajectories with their inversion counterparts, broadening distributional coverage and enhancing diversity. Selective Subgroup Sampling(S^3) is a training-free sampling mechanism that improves inter-class separability by selecting synthetic subsets that are both representative and distinctive. Extensive experiments demonstrate that our approach significantly enhances the discriminative quality and generalization of distilled datasets, achieving state-of-the-art performance among diffusion-based methods. --- ### EviAgent: Evidence-Driven Agent for Radiology Report Generation Authors: Tuoshi Qi, Shenshen Bu, Yingfei Xiang, Zhiming Dai Published: 2026-03-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.13956v1 Automated radiology report generation holds immense potential to alleviate the heavy workload of radiologists. Despite the formidable vision-language capabilities of recent Multimodal Large Language Models (MLLMs), their clinical deployment is severely constrained by inherent limitations: their "black-box" decision-making renders the generated reports untraceable due to the lack of explicit visual evidence to support the diagnosis, and they struggle to access external domain knowledge. To address these challenges, we propose the Evidence-driven Radiology Report Generation Agent (EviAgent). Unlike opaque end-to-end paradigms, EviAgent coordinates a transparent reasoning trajectory by breaking down the complex generation process into granular operational units. We integrate multi-dimensional visual experts and retrieval mechanisms as external support modules, endowing the system with explicit visual evidence and high-quality clinical priors. Extensive experiments on MIMIC-CXR, CheXpert Plus, and IU-Xray datasets demonstrate that EviAgent outperforms both large-scale generalist models and specialized medical models, providing a robust and trustworthy solution for automated radiology report generation. --- ### LLM-Guided Reinforcement Learning for Audio-Visual Speech Enhancement Authors: Chih-Ning Chen, Jen-Cheng Hou, Hsin-Min Wang, Shao-Yi Chien, Yu Tsao, Fan-Gang Zeng Published: 2026-03-14 Categories: cs.SD, cs.AI, eess.AS arXiv: https://arxiv.org/abs/2603.13952v3 In existing Audio-Visual Speech Enhancement (AVSE) methods, objectives such as Scale-Invariant Signal-to-Noise Ratio (SI-SNR) and Mean Squared Error (MSE) are widely used; however, their correlation with perceived speech quality is often suboptimal and provides limited interpretability for optimization. This work proposes a reinforcement learning-based AVSE framework with a Large Language Model (LLM)-based interpretable reward model. An audio LLM generates natural language descriptions of enhanced speech, which are converted by a sentiment analysis model into a 1-5 rating score serving as the PPO reward for fine-tuning a pretrained AVSE model. Compared with scalar metrics, LLM-generated feedback is semantically rich and explicitly describes speech quality improvements. Experiments on the AVSEC-4 dataset show that the proposed method outperforms a supervised baseline and a DNSMOS-based RL baseline in PESQ, STOI, neural quality metrics, and subjective listening tests. --- ### DCP-CLIP:A Coarse-to-Fine Framework for Open-Vocabulary Semantic Segmentation with Dual Interaction Authors: Jing Wang, Huimin Shi, Quan Zhou, Qibo Liu, Suofei Zhang, Huimin Lu Published: 2026-03-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.13951v1 The recent years have witnessed the remarkable development for open-vocabulary semantic segmentation (OVSS) using visual-language foundation models, yet still suffer from following fundamental challenges: (1) insufficient cross-modal communications between textual and visual spaces, and (2) significant computational costs from the interactions with massive number of categories. To address these issues, this paper describes a novel coarse-to-fine framework, called DCP-CLIP, for OVSS. Unlike prior efforts that mainly relied on pre-established category content and the inherent spatial-class interaction capability of CLIP, we dynamic constructing category-relevant textual features and explicitly models dual interactions between spatial image features and textual class semantics. Specifically, we first leverage CLIP's open-vocabulary recognition capability to identify semantic categories relevant to the image context, upon which we dynamically generate corresponding textual features to serve as initial textual guidance. Subsequently, we conduct a coarse segmentation by cross-modally integrating semantic information from textual guidance into the visual representations and achieve refined segmentation by integrating spatially enriched features from the encoder to recover fine-grained details and enhance spatial resolution. In final, we leverage spatial information from the segmentation side to refine category predictions for each mask, facilitating more precise semantic labeling. Experiments on multiple OVSS benchmarks demonstrate that DCP-CLIP outperforms existing methods by delivering both higher accuracy and greater efficiency. --- ### ToolFlood: Beyond Selection -- Hiding Valid Tools from LLM Agents via Semantic Covering Authors: Hussein Jawad, Nicolas J-B Brunel Published: 2026-03-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.13950v1 Large Language Model (LLM) agents increasingly use external tools for complex tasks and rely on embedding-based retrieval to select a small top-k subset for reasoning. As these systems scale, the robustness of this retrieval stage is underexplored, even though prior work has examined attacks on tool selection. This paper introduces ToolFlood, a retrieval-layer attack on tool-augmented LLM agents. Rather than altering which tool is chosen after retrieval, ToolFlood overwhelms retrieval itself by injecting a few attacker-controlled tools whose metadata is carefully placed by exploiting the geometry of embedding space. These tools semantically span many user queries, dominate the top-k results, and push all benign tools out of the agent's context. ToolFlood uses a two-phase adversarial tool generation strategy. It first samples subsets of target queries and uses an LLM to iteratively generate diverse tool names and descriptions. It then runs an iterative greedy selection that chooses tools maximizing coverage of remaining queries in embedding space under a cosine-distance threshold, stopping when all queries are covered or a budget is reached. We provide theoretical analysis of retrieval saturation and show on standard benchmarks that ToolFlood achieves up to a 95% attack success rate with a low injection rate (1% in ToolBench). The code will be made publicly available at the following link: https://github.com/as1-prog/ToolFlood ---