# Research Papers — 2026-03 · bundle page 187 of 243 > Full-text markdown of papers #9301–9350 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/187 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/186.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/188.md) ### Exoskeleton Control through Learning to Reduce Biological Joint Moments in Simulations Authors: Zihang You, Xianlian Zhou Published: 2026-03-08 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2603.07629v1 Data-driven joint-moment predictors offer a scalable alternative to laboratory-based inverse-dynamics pipelines for biomechanics estimation and exoskeleton control. Meanwhile, physics-based reinforcement learning (RL) enables simulation-trained controllers to learn dynamics-aware assistance strategies without extensive human experimentation. However, quantitative verification of simulation-trained exoskeleton torque predictors, and their impact on human joint power injection, remains limited. This paper presents (1) an RL framework to learn exoskeleton assistance policies that reduce biological joint moments, and (2) a validation pipeline that verifies the trained control networks using an open-source gait dataset through inference and comparison with biological joint moments. Simulation-trained multilayer perceptron (MLP) controllers are developed for level-ground and ramp walking, mapping short-horizon histories of bilateral hip and knee kinematics to normalized assistance torques. Results show that predicted assistance preserves task-intensity trends across speeds and inclines. Agreement is particularly strong at the hip, with cross-correlation coefficients reaching 0.94 at 1.8 m/s and 0.98 during 5° decline walking, demonstrating near-matched temporal structure. Discrepancies increase at higher speeds and steeper inclines, especially at the knee, and are more pronounced in joint power comparisons. Delay tuning biases assistance toward greater positive power injection; modest timing shifts increase positive power and improve agreement in specific gait intervals. Together, these results establish a quantitative validation framework for simulation-trained exoskeleton controllers, demonstrate strong sim-to-data consistency at the torque level, and highlight both the promise and the remaining challenges for sim-to-real transfer. --- ### Accelerating Diffusion Models for Generative AI Applications with Silicon Photonics Authors: Tharini Suresh, Salma Afifi, Sudeep Pasricha Published: 2026-03-08 Categories: cs.AR, cs.LG arXiv: https://arxiv.org/abs/2603.07626v1 Diffusion models have revolutionized generative AI, with their inherent capacity to generate highly realistic state-of-the-art synthetic data. However, these models employ an iterative denoising process over computationally intensive layers such as UNets and attention mechanisms. This results in high inference energy on conventional electronic platforms, and thus, there is an emerging need to accelerate these models in a sustainable manner. To address this challenge, we present a novel silicon photonics-based accelerator for diffusion models. Experimental evaluations demonstrate that our photonic accelerator achieves at least 3x better energy efficiency and 5.5x throughput improvement compared to state-of-the-art diffusion model accelerators. --- ### Duala: Dual-Level Alignment of Subjects and Stimuli for Cross-Subject fMRI Decoding Authors: Shumeng Li, Jintao Guo, Jian Zhang, Yulin Zhou, Luyang Cao, Yinghuan Shi Published: 2026-03-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07625v1 Cross-subject visual decoding aims to reconstruct visual experiences from brain activity across individuals, enabling more scalable and practical brain-computer interfaces. However, existing methods often suffer from degraded performance when adapting to new subjects with limited data, as they struggle to preserve both the semantic consistency of stimuli and the alignment of brain responses. To address these challenges, we propose Duala, a dual-level alignment framework designed to achieve stimulus-level consistency and subject-level alignment in fMRI-based cross-subject visual decoding. (1) At the stimulus level, Duala introduces a semantic alignment and relational consistency strategy that preserves intra-class similarity and inter-class separability, maintaining clear semantic boundaries during adaptation. (2) At the subject level, a distribution-based feature perturbation mechanism is developed to capture both global and subject-specific variations, enabling adaptation to individual neural representations without overfitting. Experiments on the Natural Scenes Dataset (NSD) demonstrate that Duala effectively improves alignment across subjects. Remarkably, even when fine-tuned with only about one hour of fMRI data, Duala achieves over 81.1% image-to-brain retrieval accuracy and consistently outperforms existing fine-tuning strategies in both retrieval and reconstruction. Our code is available at https://github.com/ShumengLI/Duala. --- ### Overthinking Causes Hallucination: Tracing Confounder Propagation in Vision Language Models Authors: Abin Shoby, Ta Duc Huy, Tuan Dung Nguyen, Minh Khoi Ho, Qi Chen, Anton van den Hengel, Phi Le Nguyen, Johan W. Verjans, Vu Minh Hieu Phan Published: 2026-03-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07619v2 Vision Language models (VLMs) often hallucinate non-existent objects. Detecting hallucination is analogous to detecting deception: a single final statement is insufficient, one must examine the underlying reasoning process. Yet existing detectors rely mostly on final-layer signals. Attention-based methods assume hallucinated tokens exhibit low attention, while entropy-based ones use final-step uncertainty. Our analysis reveals the opposite: hallucinated objects can exhibit peaked attention due to contextual priors; and models often express high confidence because intermediate layers have already converged to an incorrect hypothesis. We show that the key to hallucination detection lies within the model's thought process, not its final output. By probing decoder layers, we uncover a previously overlooked behavior, overthinking: models repeatedly revise object hypotheses across layers before committing to an incorrect answer. Once the model latches onto a confounded hypothesis, it can propagate through subsequent layers, ultimately causing hallucination. To capture this behavior, we introduce the Overthinking Score, a metric to measure how many competing hypotheses the model entertains and how unstable these hypotheses are across layers. This score significantly improves hallucination detection: 78.9% F1 on MSCOCO and 71.58% on AMBER. --- ### SMAT: Staged Multi-Agent Training for Co-Adaptive Exoskeleton Control Authors: Yifei Yuan, Ghaith Androwis, Xianlian Zhou Published: 2026-03-08 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.07618v1 Effective exoskeleton assistance requires co-adaptation: as the device alters joint dynamics, the user reorganizes neuromuscular coordination, creating a non-stationary learning problem. Most learning-based approaches do not explicitly account for the sequential nature of human motor adaptation, leading to training instability and poorly timed assistance. We propose Staged Multi-Agent Training (SMAT), a four-stage curriculum designed to mirror how users naturally acclimate to a wearable device. In SMAT, a musculoskeletal human actor and a bilateral hip exoskeleton actor are trained progressively: the human first learns unassisted gait, then adapts to the added device mass; the exoskeleton subsequently learns a positive assistance pattern against a stabilized human policy, and finally both agents co-adapt with full torque capacity and bidirectional feedback. We implement SMAT in the MyoAssist simulation environment using a 26-muscle lower-limb model and an attached hip exoskeleton. Our musculoskeletal simulations demonstrate that the learned exoskeleton control policy produces an average 10.1% reduction in hip muscle activation relative to the no-assist condition. We validated the learned controller in an offline setting using open-source gait data, then deployed it to a physical hip exoskeleton for treadmill experiments with five subjects. The resulting policy delivers consistent assistance and predominantly positive mechanical power without the need for any explicitly imposed timing shift (mean positive power: 13.6 W at 6 Nm RMS torque to 23.8 W at 9.3 Nm RMS torque, with minimal negative power) consistently across all subjects without subject-specific retraining. --- ### Compression as Adaptation: Implicit Visual Representation with Diffusion Foundation Models Authors: Zongyu Guo, Jiajun He, Zhaoyang Jia, Xiaoyi Zhang, Jiahao Li, Xiao Li, Bin Li, José Miguel Hernández-Lobato, Yan Lu Published: 2026-03-08 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2603.07615v3 Modern visual generative models acquire rich visual knowledge through large-scale training, yet existing visual representations (such as pixels, latents, or tokens) remain external to the model and cannot directly exploit this knowledge for compact storage or reuse. In this work, we introduce a new visual representation framework that encodes a signal as a function, which is parametrized by low-rank adaptations attached to a frozen visual generative model. Such implicit representations of visual signals, \textit{e.g.}, an 81-frame video, can further be hashed into a single compact vector, achieving strong perceptual video compression at extremely low bitrates. Beyond basic compression, the functional nature of this representation enables inference-time scaling and control, allowing additional refinement on the compression performance. More broadly, as the implicit representations directly act as a function of the generation process, this suggests a unified framework bridging visual compression and generation. --- ### Looking Into the Water by Unsupervised Learning of the Surface Shape Authors: Ori Lifschitz, Tali Treibitz, Dan Rosenbaum Published: 2026-03-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07614v1 We address the problem of looking into the water from the air, where we seek to remove image distortions caused by refractions at the water surface. Our approach is based on modeling the different water surface structures at various points in time, assuming the underlying image is constant. To this end, we propose a model that consists of two neural-field networks. The first network predicts the height of the water surface at each spatial position and time, and the second network predicts the image color at each position. Using both networks, we reconstruct the observed sequence of images and can therefore use unsupervised training. We show that using implicit neural representations with periodic activation functions (SIREN) leads to effective modeling of the surface height spatio-temporal signal and its derivative, as required for image reconstruction. Using both simulated and real data we show that our method outperforms the latest unsupervised image restoration approach. In addition, it provides an estimate of the water surface. --- ### KohakuRAG: A simple RAG framework with hierarchical document indexing Authors: Shih-Ying Yeh, Yueh-Feng Ku, Ko-Wei Huang, Buu-Khang Tu Published: 2026-03-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.07612v1 Retrieval-augmented generation (RAG) systems that answer questions from document collections face compounding difficulties when high-precision citations are required: flat chunking strategies sacrifice document structure, single-query formulations miss relevant passages through vocabulary mismatch, and single-pass inference produces stochastic answers that vary in both content and citation selection. We present KohakuRAG, a hierarchical RAG framework that preserves document structure through a four-level tree representation (document $\rightarrow$ section $\rightarrow$ paragraph $\rightarrow$ sentence) with bottom-up embedding aggregation, improves retrieval coverage through an LLM-powered query planner with cross-query reranking, and stabilizes answers through ensemble inference with abstention-aware voting. We evaluate on the WattBot 2025 Challenge, a benchmark requiring systems to answer technical questions from 32 documents with $\pm$0.1% numeric tolerance and exact source attribution. KohakuRAG achieves first place on both public and private leaderboards (final score 0.861), as the only team to maintain the top position across both evaluation partitions. Ablation studies reveal that prompt ordering (+80% relative), retry mechanisms (+69%), and ensemble voting with blank filtering (+1.2pp) each contribute substantially, while hierarchical dense retrieval alone matches hybrid sparse-dense approaches (BM25 adds only +3.1pp). We release KohakuRAG as open-source software at https://github.com/KohakuBlueleaf/KohakuRAG. --- ### MAS-H2: A Hierarchical Multi-Agent System for Holistic Cloud-Native Autoscaling Authors: Hamed Hamzeh, Parisa Vahdatian Published: 2026-03-08 Categories: cs.DC, cs.LG arXiv: https://arxiv.org/abs/2603.07607v1 Autoscaling in cloud-native platforms like Kubernetes is reactive and metric-driven, leading to a strategic void problem. This comes from the decoupling of higher-level business policies from lower-level resource provisioning. The strategic void, coupled with a fragmented coordination of pod and node scaling, can lead to significant resource waste and performance degradation under dynamic workloads. In this paper, we present MAS-H2, a new hierarchical multi-agent system that addresses the challenges of autonomic cloud resource management with a complete end-to-end solution. MAS-H2 systematically decomposes the control problem into three layers: a Strategic Agent that formalises business policies (e.g., cost vs. performance) into a global utility function; Planning Agents that produce a joint, proactive scaling plan for pods and nodes with time-series forecasting; and Execution Agents that execute the scaling plan. We built and tested a MAS-H2 prototype as a Kubernetes Operator on Google Kubernetes Engine (GKE) to benchmark it against the native Horizontal Pod Autoscaler (HPA) and Cluster Autoscaler (CA) baselines under two realistic, spiky, and stress-inducing workload scenarios. The results show that the MAS-H2 system maintained application CPU usage under 40% for predictable Heartbeat workloads. This resulted in over 50% less sustained CPU stress than the native HPA baseline, which typically operated above 80%. The MAS-H2 system demonstrated proactive planning in a volatile Chaotic Flash Sale scenario by filtering transient noise and deploying more replicas compared to HPA. It reduced peak CPU load by 55% without under-provisioning. Beyond performance, MAS-H2 seamlessly performed a zero-downtime strategic migration between two cost- and performance-optimised infrastructures. --- ### TT-Sparse: Learning Sparse Rule Models with Differentiable Truth Tables Authors: Hans Farrell Soegeng, Sarthak Ketanbhai Modi, Thomas Peyrin Published: 2026-03-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.07606v2 Interpretable machine learning is essential in high-stakes domains where decision-making requires accountability, transparency, and trust. While rule-based models offer global and exact interpretability, learning rule sets that simultaneously achieve high predictive performance and low, human-understandable complexity remains challenging. To address this, we introduce TT-Sparse, a flexible neural building block that leverages differentiable truth tables as nodes to learn sparse, effective connections. A key contribution of our approach is a new soft TopK operator with straight-through estimation for learning discrete, cardinality-constrained feature selection in an end-to-end differentiable manner. Crucially, the forward pass remains sparse, enabling efficient computation and exact symbolic rule extraction. As a result, each node (and the entire model) can be transformed exactly into compact, globally interpretable DNF/CNF Boolean formulas via Quine-McCluskey minimization. Extensive empirical results across 28 datasets spanning binary, multiclass, and regression tasks show that the learned sparse rules exhibit superior predictive performance with lower complexity compared to existing state-of-the-art methods. --- ### EmbedTalk: Talking Head Synthesis using Gaussian Embeddings Authors: Arpita Saggar, Jonathan C. Darling, Duygu Sarikaya, David C. Hogg Published: 2026-03-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07604v2 Deformable 3D Gaussian Splatting (3DGS) has emerged as a popular method for real-time talking head synthesis, offering high-quality renderings at low latency. Tri-planes are a common choice for encoding Gaussians prior to deformation since they provide a compact and continuous representation. However, tri-plane encodings are limited by grid resolution and approximation errors introduced by projecting 3D volumetric fields onto 2D subspaces. Recent work has demonstrated the effectiveness of per-Gaussian embeddings for driving temporal deformations in 4D scene reconstruction. We introduce EmbedTalk, which leverages these embeddings to model speech-driven facial deformations for talking head synthesis. Comprehensive experiments show that EmbedTalk improves rendering quality, lip synchronisation, and motion consistency over previous 3DGS-based methods, while remaining competitive with state-of-the-art generative models. Replacing tri-plane features with embeddings also yields significantly more compact models that achieve 60+ FPS on a laptop GPU (RTX 2060 6 GB). Our code will be placed in the public domain on acceptance. --- ### EmbedTalk: Triplane-Free Talking Head Synthesis using Embedding-Driven Gaussian Deformation Authors: Arpita Saggar, Jonathan C. Darling, Duygu Sarikaya, David C. Hogg Published: 2026-03-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07604v1 Real-time talking head synthesis increasingly relies on deformable 3D Gaussian Splatting (3DGS) due to its low latency. Tri-planes are the standard choice for encoding Gaussians prior to deformation, since they provide a continuous domain with explicit spatial relationships. However, tri-plane representations are limited by grid resolution and approximation errors introduced by projecting 3D volumetric fields onto 2D subspaces. Recent work has shown the superiority of learnt embeddings for driving temporal deformations in 4D scene reconstruction. We introduce $\textbf{EmbedTalk}$, which shows how such embeddings can be leveraged for modelling speech deformations in talking head synthesis. Through comprehensive experiments, we show that EmbedTalk outperforms existing 3DGS-based methods in rendering quality, lip synchronisation, and motion consistency, while remaining competitive with state-of-the-art generative models. Moreover, replacing the tri-plane encoding with learnt embeddings enables significantly more compact models that achieve over 60 FPS on a mobile GPU (RTX 2060 6 GB). Our code will be placed in the public domain on acceptance. --- ### MetaSort: An Accelerated Approach for Non-uniform Compression and Few-shot Classification of Neural Spike Waveforms Authors: Luca M. Meyer, Majid Zamani Published: 2026-03-08 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2603.07602v1 Many previous works in spike sorting study spike classification and compression independently. In this paper, a novel algorithm is proposed called MetaSort to address these two problems. To deal with compression, a novel adaptive level crossing algorithm is proposed to approximate spike shapes with high fidelity. Meanwhile, the latent feature representation is used to handle the classification problem. Besides, to guarantee MetaSort is robust and discriminative, the geometric information of data is exploited simultaneously in the proposed framework by meta-transfer learning. Empirical experiments with in-vivo spike data demonstrate that MetaSort delivers promising performance, highlighting its potential and motivating continued development toward an ultra-low-power, on-chip implementation. --- ### StyleBench: Evaluating Speech Language Models on Conversational Speaking Style Control Authors: Haishu Zhao, Aokai Hao, Yuan Ge, Zhenqiang Hong, Tong Xiao, Jingbo Zhu Published: 2026-03-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.07599v1 Speech language models (SLMs) have significantly extended the interactive capability of text-based Large Language Models (LLMs) by incorporating paralinguistic information. For more realistic interactive experience with customized styles, current SLMs have managed to interpret and control speaking style intensity from user prompts during the dialogue process. However, there remains a lack of systematic benchmarks that quantifies and evaluates the style intensity control ability in conversations. In this paper, we propose StyleBench, a multi-turn dialogue benchmark for comprehensively evaluating the style intensity control ability across four dimensions: emotion, speed, volume, and pitch. Our results reveal the performance gaps between leading SLMs and omni language models (OLMs), suggesting the underlying reasons and promising approaches for future exploration. --- ### SCA: Segment-Wise CoT Compression with Answer Alignment Authors: Ye Tian, Hongyu Lin Published: 2026-03-08 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.07598v2 Chain-of-thought (CoT) reasoning improves problem solving, but long think traces increase inference cost. Existing CoT compression methods usually optimize completion-level length. For structured thinking models, however, a completion contains both a think segment and an answer segment, so completion-level compression can save tokens by compressing not only the CoT but also the answer. We call this failure mode answer drift. We propose Segment-wise CoT Compression with Answer Alignment (SCA), an answer-preserving think-compression method. SCA parses completions into functional segments, routes compression rewards only to successful think tokens, and protects answer tokens through length and distribution alignment to a frozen base model. Experiments show that, across datasets from multiple domains, SCA achieves state-of-the-art-level chain-of-thought compression while preserving the base model's performance and answer alignment. Training data and code are included in the supplementary code and data package. --- ### Fast Attention-Based Simplification of LiDAR Point Clouds for Object Detection and Classification Authors: Z. Rozsa, Á. Madaras, Q. Wei, X. Lu, M. Golarits, H. Yuan, T. Sziranyi, R. Hamzaoui Published: 2026-03-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07593v1 LiDAR point clouds are widely used in autonomous driving and consist of large numbers of 3D points captured at high frequency to represent surrounding objects such as vehicles, pedestrians, and traffic signs. While this dense data enables accurate perception, it also increases computational cost and power consumption, which can limit real-time deployment. Existing point cloud sampling methods typically face a trade-off: very fast approaches tend to reduce accuracy, while more accurate methods are computationally expensive. To address this limitation, we propose an efficient learned point cloud simplification method for LiDAR data. The method combines a feature embedding module with an attention-based sampling module to prioritize task-relevant regions and is trained end-to-end. We evaluate the method against farthest point sampling (FPS) and random sampling (RS) on 3D object detection on the KITTI dataset and on object classification across four datasets. The method was consistently faster than FPS and achieved similar, and in some settings better, accuracy, with the largest gains under aggressive downsampling. It was slower than RS, but it typically preserved accuracy more reliably at high sampling ratios. --- ### Models as Lego Builders: Assembling Malice from Benign Blocks via Semantic Blueprints Authors: Chenxi Li, Xianggan Liu, Dake Shen, Yaosong Du, Zhibo Yao, Hao Jiang, Linyi Jiang, Chengwei Cao, Jingzhe Zhang, RanYi Peng, Peiling Bai, Xiande Huang Published: 2026-03-08 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.07590v1 Despite the rapid progress of Large Vision-Language Models (LVLMs), the integration of visual modalities introduces new safety vulnerabilities that adversaries can exploit to elicit biased or malicious outputs. In this paper, we demonstrate an underexplored vulnerability via semantic slot filling, where LVLMs complete missing slot values with unsafe content even when the slot types are deliberately crafted to appear benign. Building on this finding, we propose StructAttack, a simple yet effective single-query jailbreak framework under black-box settings. StructAttack decomposes a harmful query into a central topic and a set of benign-looking slot types, then embeds them as structured visual prompts (e.g., mind maps, tables, or sunburst diagrams) with small random perturbations. Paired with a completion-guided instruction, LVLMs automatically recompose the concealed semantics and generate unsafe outputs without triggering safety mechanisms. Although each slot appears benign in isolation (local benignness), StructAttack exploits LVLMs' reasoning to assemble these slots into coherent harmful semantics. Extensive experiments on multiple models and benchmarks show the efficacy of our proposed StructAttack. --- ### 3DGS-HPC: Distractor-free 3D Gaussian Splatting with Hybrid Patch-wise Classification Authors: Jiahao Chen, Yipeng Qin, Ganlong Zhao, Xin Li, Wenping Wang, Guanbin Li Published: 2026-03-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07587v2 3D Gaussian Splatting (3DGS) has demonstrated remarkable performance in novel view synthesis and 3D scene reconstruction, but its quality often degrades in real-world environments due to transient distractors, such as moving objects and varying shadows. Existing methods commonly introduce semantic priors from pre-trained vision models either to group pixels into coherent regions or to define perceptual error metrics. However, semantic grouping is often misaligned with the binary static/transient distinction, while perceptual features can be fragile under appearance perturbations introduced during 3DGS optimization. We propose 3DGS-HPC, a framework that addresses these issues by combining two complementary principles: a patch-wise classification strategy that leverages local spatial consistency for robust region-level decisions, and a hybrid classification metric that adaptively integrates photometric and perceptual cues for more reliable separation. Extensive experiments demonstrate the superiority and robustness of our method in mitigating distractors to improve 3DGS-based novel view synthesis. Our project page is https://cnhaox.github.io/3DGS-HPC/ . --- ### 3DGS-HPC: Distractor-free 3D Gaussian Splatting with Hybrid Patch-wise Classification Authors: Jiahao Chen, Yipeng Qin, Ganlong Zhao, Xin Li, Wenping Wang, Guanbin Li Published: 2026-03-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07587v1 3D Gaussian Splatting (3DGS) has demonstrated remarkable performance in novel view synthesis and 3D scene reconstruction, yet its quality often degrades in real-world environments due to transient distractors, such as moving objects and varying shadows. Existing methods commonly rely on semantic cues extracted from pre-trained vision models to identify and suppress these distractors, but such semantics are misaligned with the binary distinction between static and transient regions and remain fragile under the appearance perturbations introduced during 3DGS optimization. We propose 3DGS-HPC, a framework that circumvents these limitations by combining two complementary principles: a patch-wise classification strategy that leverages local spatial consistency for robust region-level decisions, and a hybrid classification metric that adaptively integrates photometric and perceptual cues for more reliable separation. Extensive experiments demonstrate the superiority and robustness of our method in mitigating distractors to improve 3DGS-based novel view synthesis. --- ### Analysis-Driven Procedural Generation of an Engine Sound Dataset with Embedded Control Annotations Authors: Robin Doerfler, Lonce Wyse Published: 2026-03-08 Categories: cs.SD, cs.LG, eess.AS arXiv: https://arxiv.org/abs/2603.07584v2 Computational engine sound modeling is central to the automotive audio industry, particularly for active sound design applications and virtual prototyping. Emerging data-driven engine sound synthesis methods require large volumes of standardized, clean audio recordings with precisely time-aligned operating-state annotations: data that is difficult to obtain due to high costs, specialized measurement equipment requirements, and inevitable noise contamination. We present an analysis-driven framework for generating engine audio with sample-accurate control annotations. The method extracts harmonic structures from real recordings through pitch-adaptive spectral analysis, which then drive an extended parametric harmonic-plus-noise synthesizer. With this framework, we augment 5-10 min of source audio per engine 15-30x via diverse control trajectories and parametric variation, producing the Procedural Engine Sounds Dataset (19.0 h, 5,935 files): a set of engine audio signals with sample-accurate RPM and torque annotations spanning a wide range of operating conditions, signal complexities, and harmonic profiles. Comparison against real recordings validates that the synthesized data preserves characteristic harmonic structures, and a baseline differentiable synthesis network trained on the dataset confirms its suitability for data-driven engine sound modeling. The dataset is released publicly to support research on engine timbre analysis, control parameter estimation, and neural generative synthesis. --- ### KCoEvo: A Knowledge Graph Augmented Framework for Evolutionary Code Generation Authors: Jiazhen Kang, Yuchen Lu, Chen Jiang, Jinrui Liu, Tianhao Zhang, Bo Jiang, Ningyuan Sun, Tongtong Wu, Guilin Qi Published: 2026-03-08 Categories: cs.SE, cs.CL arXiv: https://arxiv.org/abs/2603.07581v1 Code evolution is inevitable in modern software development. Changes to third-party APIs frequently break existing code and complicate maintenance, posing practical challenges for developers. While large language models (LLMs) have shown promise in code generation, they struggle to reason without a structured representation of these evolving relationships, often leading them to produce outdated APIs or invalid outputs. In this work, we propose a knowledge graph-augmented framework that decomposes the migration task into two synergistic stages: evolution path retrieval and path-informed code generation. Our approach constructs static and dynamic API graphs to model intra-version structures and cross-version transitions, enabling structured reasoning over API evolution. Both modules are trained with synthetic supervision automatically derived from real-world API diffs, ensuring scalability and minimal human effort. Extensive experiments across single-package and multi-package benchmarks demonstrate that our framework significantly improves migration accuracy, controllability, and execution success over standard LLM baselines. The source code and datasets are available at: https://github.com/kangjz1203/KCoEvo. --- ### Integration of deep generative Anomaly Detection algorithm in high-speed industrial line Authors: Niccolò Ferrari, Nicola Zanarini, Michele Fraccaroli, Alice Bizzarri, Evelina Lamma Published: 2026-03-08 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.07577v1 Industrial visual inspection in pharmaceutical production requires high accuracy under strict constraints on cycle time, hardware footprint, and operational cost. Manual inline inspection is still common, but it is affected by operator variability and limited throughput. Classical rule-based computer vision pipelines are often rigid and difficult to scale to highly variable production scenarios. To address these limitations, we present a semi-supervised anomaly detection framework based on a generative adversarial architecture with a residual autoencoder and a dense bottleneck, specifically designed for online deployment on a high-speed Blow-Fill-Seal (BFS) line. The model is trained only on nominal samples and detects anomalies through reconstruction residuals, providing both classification and spatial localization via heatmaps. The training set contains 2,815,200 grayscale patches. Experiments on a real industrial test kit show high detection performance while satisfying timing constraints compatible with a 500 ms acquisition slot. --- ### TS-MLLM: A Multi-Modal Large Language Model-based Framework for Industrial Time-Series Big Data Analysis Authors: Haiteng Wang, Yikang Li, Yunfei Zhu, Jingheng Yan, Lei Ren, Laurence T. Yang Published: 2026-03-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.07572v1 Accurate analysis of industrial time-series big data is critical for the Prognostics and Health Management (PHM) of industrial equipment. While recent advancements in Large Language Models (LLMs) have shown promise in time-series analysis, existing methods typically focus on single-modality adaptations, failing to exploit the complementary nature of temporal signals, frequency-domain visual representations, and textual knowledge information. In this paper, we propose TS-MLLM, a unified multi-modal large language model framework designed to jointly model temporal signals, frequency-domain images, and textual domain knowledge. Specifically, we first develop an Industrial time-series Patch Modeling branch to capture long-range temporal dynamics. To integrate cross-modal priors, we introduce a Spectrum-aware Vision-Language Model Adaptation (SVLMA) mechanism that enables the model to internalize frequency-domain patterns and semantic context. Furthermore, a Temporal-centric Multi-modal Attention Fusion (TMAF) mechanism is designed to actively retrieve relevant visual and textual cues using temporal features as queries, ensuring deep cross-modal alignment. Extensive experiments on multiple industrial benchmarks demonstrate that TS-MLLM significantly outperforms state-of-the-art methods, particularly in few-shot and complex scenarios. The results validate our framework's superior robustness, efficiency, and generalization capabilities for industrial time-series prediction. --- ### A Systematic Comparison of Training Objectives for Out-of-Distribution Detection in Image Classification Authors: Furkan Genç, Onat Özdemir, Emre Akbaş Published: 2026-03-08 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.07571v3 Out-of-distribution (OOD) detection is critical in safety-sensitive applications. While this challenge has been addressed from various perspectives, the influence of training objectives on OOD behavior remains comparatively underexplored. In this paper, we present a systematic comparison of four widely used training objectives: Cross-Entropy Loss, Prototype Loss, Triplet Loss, and Average Precision (AP) Loss, spanning probabilistic, prototype-based, metric-learning, and ranking-based supervision, for OOD detection in image classification under standardized OpenOOD protocols. Within the evaluated ResNet-18/OpenOOD setting and objective-specific OOD scoring rules, Cross-Entropy Loss, Prototype Loss, and AP Loss achieve comparable in-distribution accuracy, while Cross-Entropy Loss provides the most consistent near- and far-OOD AUROC overall; the other objectives can be competitive in specific settings. --- ### A Systematic Comparison of Training Objectives for Out-of-Distribution Detection in Image Classification Authors: Furkan Genç, Onat Özdemir, Emre Akbaş Published: 2026-03-08 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.07571v2 Out-of-distribution (OOD) detection is critical in safety-sensitive applications. While this challenge has been addressed from various perspectives, the influence of training objectives on OOD behavior remains comparatively underexplored. In this paper, we present a systematic comparison of four widely used training objectives: Cross-Entropy Loss, Prototype Loss, Triplet Loss, and Average Precision (AP) Loss, spanning probabilistic, prototype-based, metric-learning, and ranking-based supervision, for OOD detection in image classification under standardized OpenOOD protocols. Across CIFAR-10/100 and ImageNet-200, we find that Cross-Entropy Loss, Prototype Loss, and AP Loss achieve comparable in-distribution accuracy, while Cross-Entropy Loss provides the most consistent near- and far-OOD performance overall; the other objectives can be competitive in specific settings. --- ### Efficient RGB-D Scene Understanding via Multi-task Adaptive Learning and Cross-dimensional Feature Guidance Authors: Guodong Sun, Junjie Liu, Gaoyang Zhang, Bo Wu, Yang Zhang Published: 2026-03-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07570v1 Scene understanding plays a critical role in enabling intelligence and autonomy in robotic systems. Traditional approaches often face challenges, including occlusions, ambiguous boundaries, and the inability to adapt attention based on task-specific requirements and sample variations. To address these limitations, this paper presents an efficient RGB-D scene understanding model that performs a range of tasks, including semantic segmentation, instance segmentation, orientation estimation, panoptic segmentation, and scene classification. The proposed model incorporates an enhanced fusion encoder, which effectively leverages redundant information from both RGB and depth inputs. For semantic segmentation, we introduce normalized focus channel layers and a context feature interaction layer, designed to mitigate issues such as shallow feature misguidance and insufficient local-global feature representation. The instance segmentation task benefits from a non-bottleneck 1D structure, which achieves superior contour representation with fewer parameters. Additionally, we propose a multi-task adaptive loss function that dynamically adjusts the learning strategy for different tasks based on scene variations. Extensive experiments on the NYUv2, SUN RGB-D, and Cityscapes datasets demonstrate that our approach outperforms existing methods in both segmentation accuracy and processing speed. --- ### Constraints Matrix Diffusion based Generative Neural Solver for Vehicle Routing Problems Authors: Zhenwei Wang, Tiehua Zhang, Ning Xue, Ender Ozcan, Ling Wang, Ruibin Bai Published: 2026-03-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.07568v1 Over the past decade, neural network solvers powered by generative artificial intelligence have garnered significant attention in the domain of vehicle routing problems (VRPs), owing to their exceptional computational efficiency and superior reasoning capabilities. In particular, autoregressive solvers integrated with reinforcement learning have emerged as a prominent trend. However, much of the existing work emphasizes large-scale generalization of neural approaches while neglecting the limited robustness of attention-based methods across heterogeneous distributions of problem parameters. Their improvements over heuristic search remain largely restricted to hand-curated, fixed-distribution benchmarks. Furthermore, these architectures tend to degrade significantly when node representations are highly similar or when tasks involve long decision horizons. To address the aforementioned limitations, we propose a novel fusion neural network framework that employs a discrete noise graph diffusion model to learn the underlying constraints of vehicle routing problems and generate a constraint assignment matrix. This matrix is subsequently integrated adaptively into the feature representation learning and decision process of the autoregressive solver, serving as a graph structure mask that facilitates the formation of solutions characterized by both global vision and local feature integration. To the best of our knowledge, this work represents the first comprehensive experimental investigation of neural network model solvers across a 378-combinatorial space spanning four distinct dimensions within the CVRPlib public dataset. Extensive experimental evaluations demonstrate that our proposed fusion model effectively captures and leverages problem constraints, achieving state-of-the-art performance across multiple benchmark datasets. --- ### Revisiting the LiRA Membership Inference Attack Under Realistic Assumptions Authors: Najeeb Jebreel, Mona Khalil, David Sánchez, Josep Domingo-Ferrer Published: 2026-03-08 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2603.07567v1 Membership inference attacks (MIAs) have become the standard tool for evaluating privacy leakage in machine learning (ML). Among them, the Likelihood-Ratio Attack (LiRA) is widely regarded as the state of the art when sufficient shadow models are available. However, prior evaluations have often overstated the effectiveness of LiRA by attacking models overconfident on their training samples, calibrating thresholds on target data, assuming balanced membership priors, and/or overlooking attack reproducibility. We re-evaluate LiRA under a realistic protocol that (i) trains models using anti-overfitting (AOF) and transfer learning (TL), when applicable, to reduce overconfidence as in production models; (ii) calibrates decision thresholds using shadow models and data rather than target data; (iii) measures positive predictive value (PPV, or precision) under shadow-based thresholds and skewed membership priors (pi <= 10%); and (iv) quantifies per-sample membership reproducibility across different seeds and training variations. We find that AOF significantly weakens LiRA, while TL further reduces attack effectiveness while improving model accuracy. Under shadow-based thresholds and skewed priors, LiRA's PPV often drops substantially, especially under AOF or AOF+TL. We also find that thresholded vulnerable sets at extremely low FPR show poor reproducibility across runs, while likelihood-ratio rankings are more stable. These results suggest that LiRA, and likely weaker MIAs, are less effective than previously suggested under realistic conditions, and that reliable privacy auditing requires evaluation protocols that reflect practical training practices, feasible attacker assumptions, and reproducibility considerations. Code is available at https://github.com/najeebjebreel/lira_analysis. --- ### GRD-Net: Generative-Reconstructive-Discriminative Anomaly Detection with Region of Interest Attention Module Authors: Niccolò Ferrari, Michele Fraccaroli, Evelina Lamma Published: 2026-03-08 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.07566v1 Anomaly detection is nowadays increasingly used in industrial applications and processes. One of the main fields of the appliance is the visual inspection for surface anomaly detection, which aims to spot regions that deviate from regularity and consequently identify abnormal products. Defect localization is a key task, that usually is achieved using a basic comparison between generated image and the original one, implementing some blob-analysis or image-editing algorithms, in the post-processing step, which is very biased towards the source dataset, and they are unable to generalize. Furthermore, in industrial applications, the totality of the image is not always interesting but could be one or some regions of interest (ROIs), where only in those areas there are relevant anomalies to be spotted. For these reasons, we propose a new architecture composed by two blocks. The first block is a Generative Adversarial Network (GAN), based on a residual autoencoder (ResAE), to perform reconstruction and denoising processes, while the second block produces image segmentation, spotting defects. This method learns from a dataset composed of good products and generated synthetic defects. The discriminative network is trained using a ROI for each image contained in the training dataset. The network will learn in which area anomalies are relevant. This approach guarantees the reduction of using pre-processing algorithms, formerly developed with blob-analysis and image-editing procedures. To test our model we used challenging MVTec anomaly detection datasets and an industrial large dataset of pharmaceutical BFS strips of vials. This set constitutes a more realistic use case of the aforementioned network. --- ### Geometric-Topological Perception and Motion Prior for Real-Time Satellite Video Object Tracking Authors: Zixiao Wen, Guangyao Zhou, Jiawei Li, Xiantai Xiang, Zhen Yang, Yuxin Hu, Yuhan Liu Published: 2026-03-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07564v2 Satellite video object tracking (SVOT) remains fundamentally challenging due to texture scarcity, arbitrary rotation, aspect ratio changes, and severe occlusions. While recent state-of-the-art trackers excel in general scenarios, their reliance on rich appearance details or rigid spatial matching mechanisms leads to significant performance degradation in the satellite domain. To bridge this gap, we propose SiamGM, a real-time spatial-temporal unified tracking framework tailored for satellite videos. Instead of conventionally stacking modules, we synergize geometric-topological perception with temporal-kinematic prior, addressing the core limitations of SVOT. Spatially, we closely couple a Topological Attention Module (TAM) with a Geometry-Constrained Label Assignment (GCLA) method during the training phase, where a Local Graph Propagation (LGP) mechanism enforces neighborhood-consistent template-search correspondences. This joint paradigm establishes fine-grained structural correspondences and explicitly suppresses surrounding background noise. Temporally, rather than passively relying on visual cues, we propose an Online Motion Model Refinement (OMMR) strategy during the tracking phase. Gated by an online self-calibrated confidence indicator, OMMR adaptively fuse long-term stable and short-term instantaneous motion estimation for robust tracking. Evaluations on two challenging SatSOT and SV248S benchmarks confirm that SiamGM outperforms not only recent Siamese-based satellite trackers but also state-of-the-art Transformer trackers in both precision and success metrics. Notably, this highly unified architecture introduces only minor computational overhead, enabling real-time tracking at 130 frames per second (FPS). --- ### Brain-WM: Brain Glioblastoma World Model Authors: Chenhui Wang, Boyun Zheng, Liuxin Bao, Zhihao Peng, Peter Y. M. Woo, Hongming Shan, Yixuan Yuan Published: 2026-03-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07562v1 Precise prognostic modeling of glioblastoma (GBM) under varying treatment interventions is essential for optimizing clinical outcomes. While generative AI has shown promise in simulating GBM evolution, existing methods typically treat interventions as static conditional inputs rather than dynamic decision variables. Consequently, they fail to capture the complex, reciprocal interplay between tumor evolution and treatment response. To bridge this gap, we present Brain-WM, a pioneering brain GBM world model that unifies next-step treatment prediction and future MRI generation, thereby capturing the co-evolutionary dynamics between tumor and treatment. Specifically, Brain-WM encodes spatiotemporal dynamics into a shared latent space for joint autoregressive treatment prediction and flow-based future MRI generation. Then, instead of a conventional monolithic framework, Brain-WM adopts a novel Y-shaped Mixture-of-Transformers (MoT) architecture. This design structurally disentangles heterogeneous objectives, successfully leveraging cross-task synergies while preventing feature collapse. Finally, a synergistic multi-timepoint mask alignment objective explicitly anchors latent representations to anatomically grounded tumor structures and progression-aware semantics. Extensive validation on internal and external multi-institutional cohorts demonstrates the superiority of Brain-WM, achieving 91.5% accuracy in treatment planning and SSIMs of 0.8524, 0.8581, and 0.8404 for FLAIR, T1CE, and T2W sequences, respectively. Ultimately, Brain-WM offers a robust clinical sandbox for optimizing patient healthcare. The source code is made available at https://github.com/thibault-wch/Brain-GBM-world-model. --- ### PureCC: Pure Learning for Text-to-Image Concept Customization Authors: Zhichao Liao, Xiaole Xian, Qingyu Li, Wenyu Qin, Meng Wang, Weicheng Xie, Siyang Song, Pingfa Feng, Long Zeng, Liang Pan Published: 2026-03-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07561v2 Existing concept customization methods have achieved remarkable outcomes in high-fidelity and multi-concept customization. However, they often neglect the influence on the original model's behavior and capabilities when learning new personalized concepts. To address this issue, we propose PureCC. PureCC introduces a novel decoupled learning objective for concept customization, which combines the implicit guidance of the target concept with the original conditional prediction. This separated form enables PureCC to substantially focus on the original model during training. Moreover, based on this objective, PureCC designs a dual-branch training pipeline that includes a frozen extractor providing purified target concept representations as implicit guidance and a trainable flow model producing the original conditional prediction, jointly achieving pure learning for personalized concepts. Furthermore, PureCC introduces a novel adaptive guidance scale $λ^\star$ to dynamically adjust the guidance strength of the target concept, balancing customization fidelity and model preservation. Extensive experiments show that PureCC achieves state-of-the-art performance in preserving the original behavior and capabilities while enabling high-fidelity concept customization. The code is available at https://github.com/lzc-sg/PureCC. --- ### Active Inference for Micro-Gesture Recognition: EFE-Guided Temporal Sampling and Adaptive Learning Authors: Weijia Feng, Jingyu Yang, Ruojia Zhang, Fengtao Sun, Qian Gao, Chenyang Wang, Tongtong Su, Jia Guo, Xiaobai Li, Minglai Shao Published: 2026-03-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07559v1 Micro-gestures are subtle and transient movements triggered by unconscious neural and emotional activities, holding great potential for human-computer interaction and clinical monitoring. However, their low amplitude, short duration, and strong inter-subject variability make existing deep models prone to degradation under low-sample, noisy, and cross-subject conditions. This paper presents an active inference-based framework for micro-gesture recognition, featuring Expected Free Energy (EFE)-guided temporal sampling and uncertainty-aware adaptive learning. The model actively selects the most discriminative temporal segments under EFE guidance, enabling dynamic observation and information gain maximization. Meanwhile, sample weighting driven by predictive uncertainty mitigates the effects of label noise and distribution shift. Experiments on the SMG dataset demonstrate the effectiveness of the proposed method, achieving consistent improvements across multiple mainstream backbones. Ablation studies confirm that both the EFE-guided observation and the adaptive learning mechanism are crucial to the performance gains. This work offers an interpretable and scalable paradigm for temporal behavior modeling under low-resource and noisy conditions, with broad applicability to wearable sensing, HCI, and clinical emotion monitoring. --- ### ECG Classification on PTB-XL: A Data-Centric Approach with Simplified CNN-VAE Authors: Naqcho Ali Mehdi, Amir Ali Published: 2026-03-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.07558v1 Automated electrocardiogram (ECG) classification is essential for early detection of cardiovascular diseases. While recent approaches have increasingly relied on deep neural networks with complex architectures, we demonstrate that careful data preprocessing, class balancing, and a simplified convolutional neural network combined with a variational autoencoder (CNN-VAE) architecture can achieve competitive performance with significantly reduced model complexity. Using the publicly available PTB XL dataset, we achieve 87.01% binary accuracy and 0.7454 weighted F1-score across five diagnostic classes (CD, HYP, MI, NORM, STTC) with only 197,093 trainable parameters. Our work emphasises the importance of data-centric machine learning practices over architectural complexity, demonstrating that systematic preprocessing and balanced training strategies are critical for medical signal classification. We identify challenges in minority class detection (particularly hypertrophy) and provide insights for future improvements in handling imbalanced ECG datasets. Index Terms: ECG classification, convolutional neural networks, class balancing, data preprocessing, variational autoencoders, PTB-XL dataset --- ### Nwāchā Munā: A Devanagari Speech Corpus and Proximal Transfer Benchmark for Nepal Bhasha ASR Authors: Rishikesh Kumar Sharma, Safal Narshing Shrestha, Jenny Poudel, Rupak Tiwari, Arju Shrestha, Rupak Raj Ghimire, Bal Krishna Bal Published: 2026-03-08 Categories: cs.CL, cs.AI, cs.SD arXiv: https://arxiv.org/abs/2603.07554v2 Nepal Bhasha (Newari), an endangered language of the Kathmandu Valley, remains digitally marginalized due to the severe scarcity of annotated speech resources. In this work, we introduce Nwāchā Munā, a newly curated 5.39-hour manually transcribed Devanagari speech corpus for Nepal Bhasha, and establish the first benchmark using script-preserving acoustic modeling. We investigate whether proximal cross-lingual transfer from a geographically and linguistically adjacent language (Nepali) can rival large-scale multilingual pretraining in an ultra-low-resource Automatic Speech Recognition (ASR) setting. Fine-tuning a Nepali Conformer model reduces the Character Error Rate (CER) from a 52.54% zero-shot baseline to 17.59% with data augmentation, effectively matching the performance of the multilingual Whisper-Small model despite utilizing significantly fewer parameters. Our findings demonstrate that proximal transfer from Nepali language serves as a computationally efficient alternative to massive multilingual models. We openly release the dataset and benchmarks to digitally enable the Newari community and foster further research in Nepal Bhasha. --- ### ReconDrive: Fast Feed-Forward 4D Gaussian Splatting for Autonomous Driving Scene Reconstruction Authors: Haibao Yu, Kuntao Xiao, Jiahang Wang, Ruiyang Hao, Yuxin Huang, Guoran Hu, Haifang Qin, Bowen Jing, Yuntian Bo, Ping Luo Published: 2026-03-08 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2603.07552v1 High-fidelity visual reconstruction and novel-view synthesis are essential for realistic closed-loop evaluation in autonomous driving. While 4D Gaussian Splatting (4DGS) offers a promising balance of accuracy and efficiency, existing per-scene optimization methods require costly iterative refinement, rendering them unscalable for extensive urban environments. Conversely, current feed-forward approaches often suffer from degraded photometric quality. To address these limitations, we propose ReconDrive, a feed-forward framework that leverages and extends the 3D foundation model VGGT for rapid, high-fidelity 4DGS generation. Our architecture introduces two core adaptations to tailor the foundation model to dynamic driving scenes: (1) Hybrid Gaussian Prediction Heads, which decouple the regression of spatial coordinates and appearance attributes to overcome the photometric deficiencies inherent in generalized foundation features; and (2) a Static-Dynamic 4D Composition strategy that explicitly captures temporal motion via velocity modeling to represent complex dynamic environments. Benchmarked on nuScenes, ReconDrive significantly outperforms existing feed-forward baselines in reconstruction, novel-view synthesis, and 3D perception. It achieves performance competitive with per-scene optimization while being orders of magnitude faster, providing a scalable and practical solution for realistic driving simulation. --- ### Speech Generation Speaker Poisoning: Capability Erasure in Zero-Shot Text-to-Speech Authors: Thanathai Lertpetchpun, Thanapat Trachu, Sai Praneeth Karimireddy, Shrikanth Narayanan Published: 2026-03-08 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2603.07551v3 Recent zero-shot Text-to-Speech (TTS) systems can clone previously unseen voices from only a few seconds of audio. We formulate Speech Generation Speaker Poisoning (SGSP), a task that seeks to prevent a model from synthesizing targeted speaker identities while maintaining performance on all other speakers. Unlike conventional machine unlearning, removing training examples is insufficient because modern zero-shot TTS systems can reconstruct identities through learned speaker representations and strong generalization capabilities. We evaluate both inference-time filtering and parameter-modification approaches across settings involving 1, 15, and 100 forget speakers, focusing primarily on speakers seen during training, which we show are harder to suppress than unseen speakers. To characterize the trade-off between utility and privacy, we introduce an evaluation framework based on AUC analysis and a proposed metric, Forget Set Similarity (FSSIM). Our results demonstrate effective speaker suppression for up to 15 forget speakers while revealing that worst-case identity leakage (Max-FSSIM) remains unresolved at multi-speaker scale - establishing this as an open challenge for future work. Together, our work establishes targeted speaker poisoning as a task for zero-shot TTS and, using StyleTTS2 as an initial testbed, provides methods and evaluation protocols for future research, with code and model weights. --- ### Targeted Speaker Poisoning Framework in Zero-Shot Text-to-Speech Authors: Thanapat Trachu, Thanathai Lertpetchpun, Sai Praneeth Karimireddy, Shrikanth Narayanan Published: 2026-03-08 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2603.07551v2 Zero-shot Text-to-Speech (TTS) voice cloning poses severe privacy risks, demanding the removal of specific speaker identities from trained TTS models. Conventional machine unlearning is insufficient in this context, as zero-shot TTS can dynamically reconstruct voices from just reference prompts. We formalize this task as Speech Generation Speaker Poisoning (SGSP), in which we modify trained models to prevent the generation of specific identities while preserving utility for other speakers. We evaluate inference-time filtering and parameter-modification baselines across 1, 15, and 100 forgotten speakers. Performance is assessed through the trade-off between utility (WER) and privacy, quantified using AUC and Forget Speaker Similarity (FSSIM). We achieve strong privacy for up to 15 speakers but reveal scalability limits at 100 speakers due to increased identity overlap. Our study thus introduces a novel problem and evaluation framework toward further advances in generative voice privacy. --- ### Learning-free L2-Accented Speech Generation using Phonological Rules Authors: Thanathai Lertpetchpun, Yoonjeong Lee, Jihwan Lee, Tiantian Feng, Dani Byrd, Shrikanth Narayanan Published: 2026-03-08 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.07550v1 Accent plays a crucial role in speaker identity and inclusivity in speech technologies. Existing accented text-to-speech (TTS) systems either require large-scale accented datasets or lack fine-grained phoneme-level controllability. We propose a accented TTS framework that combines phonological rules with a multilingual TTS model. The rules are applied to phoneme sequences to transform accent at the phoneme level while preserving intelligibility. The method requires no accented training data and enables explicit phoneme-level accent manipulation. We design rule sets for Spanish- and Indian-accented English, modeling systematic differences in consonants, vowels, and syllable structure arising from phonotactic constraints. We analyze the trade-off between phoneme-level duration alignment and accent as realized in speech timing. Experimental results demonstrate effective accent shift while maintaining speech quality. --- ### COOL-MC: Verifying and Explaining RL Policies for Multi-bridge Network Maintenance Authors: Dennis Gross Published: 2026-03-08 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.07546v1 Aging bridge networks require proactive, verifiable, and interpretable maintenance strategies, yet reinforcement learning (RL) policies trained solely on reward signals provide no formal safety guarantees and remain opaque to infrastructure managers. We demonstrate COOL-MC as a tool for verifying and explaining RL policies for multi-bridge network maintenance, building on a single-bridge Markov decision process (MDP) from the literature and extending it to a parallel network of three heterogeneous bridges with a shared periodic budget constraint, encoded in the PRISM modeling language. We train an RL agent on this MDP and apply probabilistic model checking and explainability methods to the induced discrete-time Markov chain (DTMC) that arises from the interaction between the learned policy and the underlying MDP. Probabilistic model checking reveals that the trained policy has a safety-violation probability of 3.5\% over the planning horizon, being slightly above the theoretical minimum of 0\% and indicating the suboptimality of the learned policy, noting that these results are based on artificially constructed transition probabilities and deterioration rates rather than real-world data, so absolute performance figures should be interpreted with caution. The explainability analysis further reveals, for instance, a systematic bias in the trained policy toward the state of bridge 1 over the remaining bridges in the network. These results demonstrate COOL-MC's ability to provide formal, interpretable, and practical analysis of RL maintenance policies. --- ### DreamSAC: Learning Hamiltonian World Models via Symmetry Exploration Authors: Jinzhou Tang, Fan Feng, Minghao Fu, Wenjun Lin, Biwei Huang, Keze Wang Published: 2026-03-08 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.07545v1 Learned world models excel at interpolative generalization but fail at extrapolative generalization to novel physical properties. This limitation arises because they learn statistical correlations rather than the environment's underlying generative rules, such as physical invariances and conservation laws. We argue that learning these invariances is key to robust extrapolation. To achieve this, we first introduce \textbf{Symmetry Exploration}, an unsupervised exploration strategy where an agent is intrinsically motivated by a Hamiltonian-based curiosity bonus to actively probe and challenge its understanding of conservation laws, thereby collecting physically informative data. Second, we design a Hamiltonian-based world model that learns from the collected data, using a novel self-supervised contrastive objective to identify the invariant physical state from raw, view-dependent pixel observations. Our framework, \textbf{DreamSAC}, trained on this actively curated data, significantly outperforms state-of-the-art baselines in 3D physics simulations on tasks requiring extrapolation. --- ### CONSTANT: Towards High-Quality One-Shot Handwriting Generation with Patch Contrastive Enhancement and Style-Aware Quantization Authors: Anh-Duy Le, Van-Linh Pham, Thanh-Nam Vo, Xuan Toan Mai, Tuan-Anh Tran Published: 2026-03-08 Categories: cs.CV, cs.MM arXiv: https://arxiv.org/abs/2603.07543v1 One-shot styled handwriting image generation, despite achieving impressive results in recent years, remains challenging due to the difficulty in capturing the intricate and diverse characteristics of human handwriting by using solely a single reference image. Existing methods still struggle to generate visually appealing and realistic handwritten images and adapt to complex, unseen writer styles, struggling to isolate invariant style features (e.g., slant, stroke width, curvature) while ignoring irrelevant noise. To tackle this problem, we introduce Patch Contrastive Enhancement and Style-Aware Quantization via Denoising Diffusion (CONSTANT), a novel one-shot handwriting generation via diffusion model. CONSTANT leverages three key innovations: 1) a Style-Aware Quantization (SAQ) module that models style as discrete visual tokens capturing distinct concepts; 2) a contrastive objective to ensure these tokens are well-separated and meaningful in the embedding style space; 3) a latent patch-based contrastive (LLatentPCE) objective help improving quality and local structures by aligning multiscale spatial patches of generated and real features in latent space. Extensive experiments and analysis on benchmark datasets from multiple languages, including English, Chinese, and our proposed ViHTGen dataset for Vietnamese, demonstrate the superiority of adapting to new reference styles and producing highly detailed images of our method over state-of-the-art approaches. Code is available at GitHub --- ### How Long Can Unified Multimodal Models Generate Images Reliably? Taming Long-Horizon Interleaved Image Generation via Context Curation Authors: Haoyu Chen, Qing Liu, Yuqian Zhou, He Zhang, Zhaowen Wang, Mengwei Ren, Jingjing Ren, Xiang Wang, Zhe Lin, Lei Zhu Published: 2026-03-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.07540v1 Unified multimodal models hold the promise of generating extensive, interleaved narratives, weaving text and imagery into coherent long-form stories. However, current systems suffer from a critical reliability gap: as sequences grow, generation quality rapidly collapses. In this work, we investigate the mechanism behind this failure and argue that it is distinct from standard long-context challenges. We reveal that in generation, accumulated visual history acts as a source of active pollution, a decay governed specifically by the number of image events rather than raw token count. We identify a structural vulnerability where dense visual tokens overwhelm the attention mechanism, creating noise that distorts future synthesis. Guided by these mechanistic insights, we propose UniLongGen, a training-free inference strategy that prioritizes safe conditioning over total recall. Instead of retaining all history, UniLongGen dynamically curates the model's memory, identifying and discarding interfering visual signals based on the model's own internal relevance rankings. Extensive experiments demonstrate that this active forgetting approach is essential for stability: UniLongGen significantly outperforms baselines in long-horizon fidelity and consistency, while simultaneously reducing memory footprint and inference time. --- ### MAWARITH: A Dataset and Benchmark for Legal Inheritance Reasoning with LLMs Authors: Abdessalam Bouchekif, Shahd Gaben, Samer Rashwani, Somaya Eltanbouly, Mutaz Al-Khatib, Heba Sbahi, Mohammed Ghaly, Emad Mohamed Published: 2026-03-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.07539v3 Islamic inheritance law is challenging for large language models because solving inheritance cases requires complex, structured, multi-step reasoning and the correct application of juristic rules to compute heirs' shares. We introduce \textit{MAWARITH}, a large-scale annotated dataset of 12,500 Arabic inheritance cases for training and evaluating models on the full reasoning chain: (i) identifying eligible heirs, (ii) applying blocking (\textit{\d{h}ajb}) and allocation rules, and (iii) computing exact inheritance shares. To the best of our knowledge, \textit{MAWARITH} is the first Arabic corpus and benchmark designed for end-to-end Islamic inheritance reasoning. Unlike prior datasets that restrict inheritance case solving to multiple-choice questions, \textit{MAWARITH} supports the full reasoning chain and provides step-by-step solutions with justifications grounded in classical juristic sources and established inheritance rules, as well as exact share calculations. This enables models to learn how to generate detailed, step-by-step responses to user queries that reflect real-world Islamic inheritance cases. To evaluate models beyond final-answer accuracy, we propose \textit{MIR-E} (Mawarith Inheritance Reasoning Evaluation), a weighted multi-stage metric that scores key reasoning stages and captures error propagation across the pipeline. We evaluate six large language models in a zero-shot setting. A commercial model achieves about 90\%, whereas all evaluated open-source models remain below 50\%. Our error analysis identifies recurring failure patterns, including scenario misinterpretation, errors in heir identification, errors in share allocation, and missing or incorrect application of key inheritance rules such as \textit{\textquotesingle awl} and \textit{radd}. The \textit{MAWARITH} dataset is publicly available at https://gitlab.com/nlpresearcher/mawarith. --- ### Scale-Aware UAV-to-Satellite Cross-View Geo-Localization: A Semantic Geometric Approach Authors: Yibin Ye, Shuo Chen, Kun Wang, Xiaokai Song, Jisheng Dang, Qifeng Yu, Xichao Teng, Zhang Li Published: 2026-03-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07535v1 Cross-View Geo-Localization (CVGL) between UAV imagery and satellite images plays a crucial role in target localization and UAV self-positioning. However, most existing methods rely on the idealized assumption of scale consistency between UAV queries and satellite galleries, overlooking the severe scale ambiguity commonly encountered in real-world scenarios. This discrepancy leads to field-of-view misalignment and feature mismatch, significantly degrading CVGL robustness. To address this issue, we propose a geometric framework that recovers the absolute metric scale from monocular UAV images using semantic anchors. Specifically, small vehicles (SVs), characterized by relatively stable prior size distributions and high detectability, are exploited as metric references. A Decoupled Stereoscopic Projection Model is introduced to estimate the absolute image scale from these semantic targets. By decomposing vehicle dimensions into radial and tangential components, the model compensates for perspective distortions in 2D detections of 3D vehicles, enabling more accurate scale estimation. To further reduce intra-class size variation and detection noise, a dual-dimension fusion strategy with Interquartile Range (IQR)-based robust aggregation is employed. The estimated global scale is then used as a physical constraint for scale-adaptive satellite image cropping, improving UAV-to-satellite feature alignment. Experiments on augmented DenseUAV and UAV-VisLoc datasets demonstrate that the proposed method significantly improves CVGL robustness under unknown UAV image scales. Additionally, the framework shows strong potential for downstream applications such as passive UAV altitude estimation and 3D model scale recovery. --- ### Accent Vector: Controllable Accent Manipulation for Multilingual TTS Without Accented Data Authors: Thanathai Lertpetchpun, Thanapat Trachu, Jihwan Lee, Tiantian Feng, Dani Byrd, Shrikanth Narayanan Published: 2026-03-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.07534v1 Accent is an integral part of society, reflecting multiculturalism and shaping how individuals express identity. The majority of English speakers are non-native (L2) speakers, yet current Text-To-Speech (TTS) systems primarily model American-accented English due limited accented data. We propose \textit{Accent Vector}, a controllable representation that enables accent manipulation in multilingual TTS without requiring accented training data. \textit{Accent Vector} is derived by fine-tuning a TTS system on native speech of a different language (i.e. non-English) and computing task vectors capturing accent characteristics (i.e. in English). By scaling and interpolating the vector, we achieve fine-grained control over accent strength and generate mixed-accent speech. In addition, it generalizes beyond English, enabling accent control across multiple languages. Objective and human evaluations confirm the effectiveness of Accent Vector for fine-grained and compositional accent control. --- ### ACCURATE: Arbitrary-shaped Continuum Reconstruction Under Robust Adaptive Two-view Estimation Authors: Yaozhi Zhang, Shun Yu, Yugang Zhang, Yang Liu Published: 2026-03-08 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2603.07533v1 Accurate reconstruction of arbitrary-shaped long slender continuum bodies, such as guidewires, catheters and other soft continuum manipulators, is essential for accurate mechanical simulation. However, existing image-based reconstruction approaches often suffer from limited accuracy because they often underutilize camera geometry, or lack generality as they rely on rigid geometric assumptions that may fail for continuum robots with complex and highly deformable shapes. To address these limitations, we propose ACCURATE, a 3D reconstruction framework integrating an image segmentation neural network with a geometry-constrained topology traversal and dynamic programming algorithm that enforces global biplanar geometric consistency, minimizes the cumulative point-to-epipolar-line distance, and remains robust to occlusions and epipolar ambiguities cases caused by noise and discretization. Our method achieves high reconstruction accuracy on both simulated and real phantom datasets acquired using a clinical X-ray C-arm system, with mean absolute errors below 1.0 mm. --- ### Obliviator Reveals the Cost of Nonlinear Guardedness in Concept Erasure Authors: Ramin Akbari, Milad Afshari, Vishnu Naresh Boddeti Published: 2026-03-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.07529v2 Concept erasure aims to remove unwanted attributes, such as social or demographic factors, from learned representations, while preserving their task-relevant utility. While the goal of concept erasure is protection against all adversaries, existing methods remain vulnerable to nonlinear ones. This vulnerability arises from their failure to fully capture the complex, nonlinear statistical dependencies between learned representations and unwanted attributes. Moreover, although the existence of a trade-off between utility and erasure is expected, its progression during the erasure process, i.e., the cost of erasure, remains unstudied. In this work, we introduce Obliviator, a post-hoc erasure method designed to fully capture nonlinear statistical dependencies. We formulate erasure from a functional perspective, leading to an optimization problem involving a composition of kernels that lacks a closed-form solution. Instead of solving this problem in a single shot, we adopt an iterative approach that gradually morphs the feature space to achieve a more utility-preserving erasure. Unlike prior methods, Obliviator guards unwanted attribute against nonlinear adversaries. Our gradual approach quantifies the cost of nonlinear guardedness and reveals the dynamics between attribute protection and utility-preservation over the course of erasure. The utility-erasure trade-off curves obtained by Obliviator outperform the baselines and demonstrate its strong generalizability: its erasure becomes more utility-preserving when applied to the better-disentangled representations learned by more capable models. --- ### TableMind++: An Uncertainty-Aware Programmatic Agent for Tool-Augmented Table Reasoning Authors: Mingyue Cheng, Shuo Yu, Chuang Jiang, Xiaoyu Tao, Qingyang Mao, Jie Ouyang, Qi Liu, Enhong Chen Published: 2026-03-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.07528v2 Table reasoning requires models to jointly perform semantic understanding and precise numerical operations. Most existing methods rely on a single-turn reasoning paradigm over tables which suffers from context overflow and weak numerical sensitivity. To address these limitations, we previously proposed TableMind as a tuning-based autonomous programmatic agent that simulates human-like interaction within a lightweight large language model (LLM). TableMind internalizes planning, action, and reflection through a two-stage training strategy involving supervised fine-tuning (SFT) on filtered high-quality data and reinforcement learning (RL) via a multi-perspective reward and the Rank-Aware Policy Optimization (RAPO) algorithm. While TableMind establishes a solid foundation for programmatic agents, the inherent stochasticity of LLMs remains a critical challenge that leads to hallucinations. In this paper, we extend this foundation to TableMind++ by introducing a novel uncertainty-aware inference framework to mitigate hallucinations. Specifically, we propose memory-guided plan pruning to retrieve historical trajectories for validating and filtering out logically flawed plans to address epistemic uncertainty. To ensure execution precision, we introduce confidence-based action refinement which monitors token-level probabilities to detect and self-correct syntactic noise for aleatoric uncertainty mitigation. Finally, we employ dual-weighted trajectory aggregation to synthesize a robust consensus from multiple reasoning paths. Extensive experiments on diverse benchmarks demonstrate that TableMind++ consistently outperforms previous baselines and proprietary models to validate the effectiveness of integrating autonomous training with uncertainty quantification. Our code is available. --- ### Generative prediction of laser-induced rocket ignition with dynamic latent space representations Authors: Tony Zahtila, Ettore Saetta, Murray Cutforth, Davy Brouzet, Diego Rossinelli, Gianluca Iaccarino Published: 2026-03-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.07525v1 Accurate and predictive scale-resolving simulations of laser-ignited rocket engines are highly time-consuming because the problem includes turbulent fuel-oxidizer mixing dynamics, laser-induced energy deposition, and high-speed flame growth. This is conflated with the large design space primarily corresponding to the laser operating conditions and target location. To enable rapid exploration and uncertainty quantification, we propose a data-driven surrogate modeling approach that combines convolutional autoencoders (cAEs) with neural ordinary differential equations (neural ODEs). The present target application of an ML-based surrogate model to leading-edge multi-physics turbulence simulation is part of a paradigm shift in the deployment of surrogate models towards increasing real-world complexity. Sequentially, the cAE spatially compresses high-dimensional flow fields into a low-dimensional latent space, wherein the system's temporal dynamics are learned via neural ODEs. Once trained, the model generates fast spatiotemporal predictions from initial conditions and specified operating inputs. By learning a surrogate to replace the entirety of the time-evolving simulation, the cost of predicting an ignition trial is reduced by several orders of magnitude, allowing efficient exploration of the input parameter space. Further, as the current framework yields a spatiotemporal field prediction, appraisal of the model output's physical grounding is more tractable. This approach marks a significant step toward real-time digital twins for laser-ignited rocket combustors and represents surrogate modeling in a complex system context. ---