# Research Papers — 2026-03 · bundle page 17 of 243 > Full-text markdown of papers #801–850 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/17 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/16.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/18.md) ### $AutoDrive\text{-}P^3$: Unified Chain of Perception-Prediction-Planning Thought via Reinforcement Fine-Tuning Authors: Yuqi Ye, Zijian Zhang, Junhong Lin, Shangkun Sun, Changhao Peng, Wei Gao Published: 2026-03-30 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2603.28116v1 Vision-language models (VLMs) are increasingly being adopted for end-to-end autonomous driving systems due to their exceptional performance in handling long-tail scenarios. However, current VLM-based approaches suffer from two major limitations: 1) Some VLMs directly output planning results without chain-of-thought (CoT) reasoning, bypassing crucial perception and prediction stages which creates a significant domain gap and compromises decision-making capability; 2) Other VLMs can generate outputs for perception, prediction, and planning tasks but employ a fragmented decision-making approach where these modules operate separately, leading to a significant lack of synergy that undermines true planning performance. To address these limitations, we propose ${AutoDrive\text{-}P^3}$, a novel framework that seamlessly integrates $\textbf{P}$erception, $\textbf{P}$rediction, and $\textbf{P}$lanning through structured reasoning. We introduce the ${P^3\text{-}CoT}$ dataset to facilitate coherent reasoning and propose ${P^3\text{-}GRPO}$, a hierarchical reinforcement learning algorithm that provides progressive supervision across all three tasks. Specifically, ${AutoDrive\text{-}P^3}$ progressively generates CoT reasoning and answers for perception, prediction, and planning, where perception provides essential information for subsequent prediction and planning, while both perception and prediction collectively contribute to the final planning decisions, enabling safer and more interpretable autonomous driving. Additionally, to balance inference efficiency with performance, we introduce dual thinking modes: detailed thinking and fast thinking. Extensive experiments on both open-loop (nuScenes) and closed-loop (NAVSIMv1/v2) benchmarks demonstrate that our approach achieves state-of-the-art performance in planning tasks. Code is available at https://github.com/haha-yuki-haha/AutoDrive-P3. --- ### Graph Vector Field: A Unified Framework for Multimodal Health Risk Assessment from Heterogeneous Wearable and Environmental Data Streams Authors: Silvano Coletti, Francesca Fallucchi Published: 2026-03-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.28115v1 Digital health research has advanced dynamic graph-based disease models, topological learning on simplicial complexes, and multimodal mixture-of-experts architectures, but these strands remain largely disconnected. We propose Graph Vector Field (GVF), a framework that models health risk as a vector-valued field on time-varying simplicial complexes, coupling discrete differential-geometric operators with modality-structured mixture-of-experts. Risk is represented as a vector-valued cochain whose evolution is parameterised with Hodge Laplacians and discrete exterior calculus operators, yielding a Helmholtz-Hodge decomposition into potential-driven (exact), circulation-like (coexact), and topologically constrained (harmonic) components linked to interpretable propagation, cyclic, and persistent risk mechanisms. Multimodal inputs from wearable sensors, behavioural/environmental context, and clinical/genomic data are incorporated through a bundle-structured mixture-of-experts in which modality-specific latent spaces are attached as fibres to the base complex. This separates modality-specific from shared contributions and offers a principled route toward modality-level identifiability. GVF integrates geometric dynamical systems, higher-order topology (enforced indirectly via geometric regularisation and Hodge decomposition), and structured multimodal fusion into a single framework for interpretable, modality-resolved risk modelling. This paper develops the mathematical foundations, architectural design, and formal guarantees; empirical validation is the subject of ongoing work. --- ### Attention Frequency Modulation: Training-Free Spectral Modulation of Diffusion Cross-Attention Authors: Seunghun Oh, Unsang Park Published: 2026-03-30 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.28114v1 Cross-attention is the primary interface through which text conditions latent diffusion models, yet its step-wise multi-resolution dynamics remain under-characterized, limiting principled training-free control. We cast diffusion cross-attention as a spatiotemporal signal on the latent grid by summarizing token-softmax weights into token-agnostic concentration maps and tracking their radially binned Fourier power over denoising. Across prompts and seeds, encoder cross-attention exhibits a consistent coarse-to-fine spectral progression, yielding a stable time-frequency fingerprint of token competition. Building on this structure, we introduce Attention Frequency Modulation (AFM), a plug-and-play inference-time intervention that edits token-wise pre-softmax cross-attention logits in the Fourier domain: low- and high-frequency bands are reweighted with a progress-aligned schedule and can be adaptively gated by token-allocation entropy, before the token softmax. AFM provides a continuous handle to bias the spatial scale of token-competition patterns without retraining, prompt editing, or parameter updates. Experiments on Stable Diffusion show that AFM reliably redistributes attention spectra and produces substantial visual edits while largely preserving semantic alignment. Finally, we find that entropy mainly acts as an adaptive gain on the same frequency-based edit rather than an independent control axis. --- ### Demystifying Lipschitz verification: positive matrices, negative results Authors: Simon Kuang, Yuezhu Xu, S. Sivaranjani, Xinfan Lin Published: 2026-03-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.28113v2 The global Lipschitz constant of a neural network is related to robustness and generalization, yet unlike in many classical models, it is not plainly legible from the parameters. This has motivated sophisticated verification algorithms, especially semidefinite programming (SDP) based on incremental quadratic constraints on the activation functions, to improve on the fast but often loose product of layerwise Lipschitz constants (the trivial bound). We ask why Lipschitz verification is a problem in the first place. Our answer is that the difficulty is structural: estimating a network's Lipschitz constant requires knowing which hidden states are reachable, and reachability is NP-hard. If P!=NP, then reachability is a barrier to any polynomial-time algorithm. Through explicit constructions, we show that this blindness can force SDP-based bounds to inherit the same qualitative failures as the trivial bound, including but not limited to polynomial per-layer conservatism. We show that the difficulties of NP-hard questions are not isolated to worst-case computational reductions, but actually afflict every instance of the verification problem. Thus SDP is not sufficient for Lipschitz verification. We also argue that it is not necessary: several apparent failures of the trivial bound arise from removable parameterization pathologies, and can be mitigated by optimizing or regularizing the trivial bound itself. We demonstrate this claim via a "spherical cow" linear model and numerical proofs of concept. While the main contribution is theoretical and negative, we finally motivate a novel form of trigonometric layers that do not need biases for universal approximation. Combined with trivial bound regularization, they make the trivial bound provably and practically tight. --- ### Contour-Guided Query-Based Feature Fusion for Boundary-Aware and Generalizable Cardiac Ultrasound Segmentation Authors: Zahid Ullah, Sieun Choi, Jihie Kim Published: 2026-03-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.28110v1 Accurate cardiac ultrasound segmentation is essential for reliable assessment of ventricular function in intelligent healthcare systems. However, echocardiographic images are challenging due to low contrast, speckle noise, irregular boundaries, and domain shifts across devices and patient populations. Existing methods, largely based on appearance-driven learning, often fail to preserve boundary precision and structural consistency under these conditions. To address these issues, we propose a Contour-Guided Query Refinement Network (CGQR-Net) for boundary-aware cardiac ultrasound segmentation. The framework integrates multi-resolution feature representations with contour-derived structural priors. An HRNet backbone preserves high-resolution spatial details while capturing multi-scale context. A coarse segmentation is first generated, from which anatomical contours are extracted and encoded into learnable query embeddings. These contour-guided queries interact with fused feature maps via cross-attention, enabling structure-aware refinement that improves boundary delineation and reduces noise artifacts. A dual-head supervision strategy jointly optimizes segmentation and boundary prediction to enforce structural consistency. The proposed method is evaluated on the CAMUS dataset and further validated on the CardiacNet dataset to assess cross-dataset generalization. Experimental results demonstrate improved segmentation accuracy, enhanced boundary precision, and robust performance across varying imaging conditions. These results highlight the effectiveness of integrating contour-level structural information with feature-level representations for reliable cardiac ultrasound segmentation. --- ### Quid est VERITAS? A Modular Framework for Archival Document Analysis Authors: Leonardo Bassanini, Ludovico Biancardi, Alfio Ferrara, Andrea Gamberini, Sergio Picascia, Folco Vaglienti Published: 2026-03-30 Categories: cs.DL, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2603.28108v1 The digitisation of historical documents has traditionally been conceived as a process limited to character-level transcription, producing flat text that lacks the structural and semantic information necessary for substantive computational analysis. We present VERITAS (Vision-Enhanced Reading, Interpretation, and Transcription of Archival Sources), a modular, model-agnostic framework that reconceptualises digitisation as an integrated workflow encompassing transcription, layout analysis, and semantic enrichment. The pipeline is organised into four stages - Preprocessing, Extraction, Refinement, and Enrichment - and employs a schema-driven architecture that allows researchers to declaratively specify their extraction objectives. We evaluate VERITAS on the critical edition of Bernardino Corio's Storia di Milano, a Renaissance chronicle of over 1,600 pages. Results demonstrate that the pipeline achieves a 67.6% relative reduction in word error rate compared to a commercial OCR baseline, with a threefold reduction in end-to-end processing time when accounting for manual correction. We further illustrate the downstream utility of the pipeline's output by querying the transcribed corpus through a retrieval-augmented generation system, demonstrating its capacity to support historical inquiry. --- ### RAWIC: Bit-Depth Adaptive Lossless Raw Image Compression Authors: Chunhang Zheng, Tongda Xu, Mingli Xie, Yan Wang, Dou Li Published: 2026-03-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.28105v1 Raw images preserve linear sensor measurements and high bit-depth information crucial for advanced vision tasks and photography applications, yet their storage remains challenging due to large file sizes, varying bit depths, and sensor-dependent characteristics. Existing learned lossless compression methods mainly target 8-bit sRGB images, while raw reconstruction approaches are inherently lossy and rely on camera-specific assumptions. To address these challenges, we introduce RAWIC, a bit-depth-adaptive learned lossless compression framework for Bayer-pattern raw images. We first convert single-channel Bayer data into a four-channel RGGB format and partition it into patches. For each patch, we compute its bit depth and use it as auxiliary input to guide compression. A bit-depth-adaptive entropy model is then designed to estimate patch distributions conditioned on their bit depths. This architecture enables a single model to handle raw images from diverse cameras and bit depths. Experiments show that RAWIC consistently surpasses traditional lossless codecs, achieving an average 7.7% bitrate reduction over JPEG-XL. Our code is available at https://github.com/chunbaobao/RAWIC. --- ### Transcription and Recognition of Italian Parliamentary Speeches Using Vision-Language Models Authors: Luigi Curini, Alfio Ferrara, Giovanni Pagano, Sergio Picascia Published: 2026-03-30 Categories: cs.DL, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2603.28103v2 Parliamentary proceedings represent a rich yet challenging resource for computational analysis, particularly when preserved only as scanned historical documents. Existing efforts to transcribe Italian parliamentary speeches have relied on traditional Optical Character Recognition pipelines, resulting in transcription errors and limited semantic annotation. In this paper, we propose a pipeline based on Vision-Language Models for the automatic transcription, semantic segmentation, and entity linking of Italian parliamentary speeches. The pipeline employs a specialised OCR model to extract text while preserving reading order, followed by a large-scale Vision-Language Model that performs transcription refinement, element classification, and speaker identification by jointly reasoning over visual layout and textual content. Extracted speakers are then linked to the Chamber of Deputies knowledge base through SPARQL queries and a multi-strategy fuzzy matching procedure. Evaluation against an established benchmark demonstrates substantial improvements both in transcription quality and speaker tagging. --- ### Heddle: A Distributed Orchestration System for Agentic RL Rollout Authors: Zili Zhang, Yinmin Zhong, Chengxu Yang, Chao Jin, Bingyang Wu, Xinming Wei, Yuliang Liu, Xin Jin Published: 2026-03-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.28101v1 Agentic Reinforcement Learning (RL) enables LLMs to solve complex tasks by alternating between a data-collection rollout phase and a policy training phase. During rollout, the agent generates trajectories, i.e., multi-step interactions between LLMs and external tools. Yet, frequent tool calls induce long-tailed trajectory generation that bottlenecks rollouts. This stems from step-centric designs that ignore trajectory context, triggering three system problems for long-tail trajectory generation: queueing delays, interference overhead, and inflated per-token time. We propose Heddle, a trajectory-centric system to optimize the when, where, and how of agentic rollout execution. Heddle integrates three core mechanisms: trajectory-level scheduling using runtime prediction and progressive priority to minimize cumulative queueing; trajectory-aware placement via presorted dynamic programming and opportunistic migration during idle tool call intervals to minimize interference; and trajectory-adaptive resource manager that dynamically tunes model parallelism to accelerate the per-token time of long-tail trajectories while maintaining high throughput for short trajectories. Evaluations across diverse agentic RL workloads demonstrate that Heddle effectively neutralizes the long-tail bottleneck, achieving up to 2.5$\times$ higher end-to-end rollout throughput compared to state-of-the-art baselines. --- ### Octree-based Learned Point Cloud Geometry Compression: A Lossy Perspective Authors: Kaiyu Zheng, Wei Gao, Huiming Zheng Published: 2026-03-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.28095v1 Octree-based context learning has recently become a leading method in point cloud compression. However, its potential on lossy compression remains undiscovered. The traditional lossy compression paradigm using lossless octree representation with quantization step adjustment may result in severe distortions due to massive missing points in quantization. Therefore, we analyze data characteristics of different point clouds and propose lossy approaches specifically. For object point clouds that suffer from quantization step adjustment, we propose a new leaf nodes lossy compression method, which achieves lossy compression by performing bit-wise coding and binary prediction on leaf nodes. For LiDAR point clouds, we explore variable rate approaches and propose a simple but effective rate control method. Experimental results demonstrate that the proposed leaf nodes lossy compression method significantly outperforms the previous octree-based method on object point clouds, and the proposed rate control method achieves about 1% bit error without finetuning on LiDAR point clouds. --- ### InkDrop: Invisible Backdoor Attacks Against Dataset Condensation Authors: He Yang, Dongyi Lv, Song Ma, Wei Xi, Zhi Wang, Hanlin Gu, Yajie Wang Published: 2026-03-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.28092v1 Dataset Condensation (DC) is a data-efficient learning paradigm that synthesizes small yet informative datasets, enabling models to match the performance of full-data training. However, recent work exposes a critical vulnerability of DC to backdoor attacks, where malicious patterns (\textit{e.g.}, triggers) are implanted into the condensation dataset, inducing targeted misclassification on specific inputs. Existing attacks always prioritize attack effectiveness and model utility, overlooking the crucial dimension of stealthiness. To bridge this gap, we propose InkDrop, which enhances the imperceptibility of malicious manipulation without degrading attack effectiveness and model utility. InkDrop leverages the inherent uncertainty near model decision boundaries, where minor input perturbations can induce semantic shifts, to construct a stealthy and effective backdoor attack. Specifically, InkDrop first selects candidate samples near the target decision boundary that exhibit latent semantic affinity to the target class. It then learns instance-dependent perturbations constrained by perceptual and spatial consistency, embedding targeted malicious behavior into the condensed dataset. Extensive experiments across diverse datasets validate the overall effectiveness of InkDrop, demonstrating its ability to integrate adversarial intent into condensed datasets while preserving model utility and minimizing detectability. Our code is available at https://github.com/lvdongyi/InkDrop. --- ### SHARP: Short-Window Streaming for Accurate and Robust Prediction in Motion Forecasting Authors: Alexander Prutsch, Christian Fruhwirth-Reisinger, David Schinagl, Horst Possegger Published: 2026-03-30 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2603.28091v1 In dynamic traffic environments, motion forecasting models must be able to accurately estimate future trajectories continuously. Streaming-based methods are a promising solution, but despite recent advances, their performance often degrades when exposed to heterogeneous observation lengths. To address this, we propose a novel streaming-based motion forecasting framework that explicitly focuses on evolving scenes. Our method incrementally processes incoming observation windows and leverages an instance-aware context streaming to maintain and update latent agent representations across inference steps. A dual training objective further enables consistent forecasting accuracy across diverse observation horizons. Extensive experiments on Argoverse 2, nuScenes, and Argoverse 1 demonstrate the robustness of our approach under evolving scene conditions and also on the single-agent benchmarks. Our model achieves state-of-the-art performance in streaming inference on the Argoverse 2 multi-agent benchmark, while maintaining minimal latency, highlighting its suitability for real-world deployment. --- ### To View Transform or Not to View Transform: NeRF-based Pre-training Perspective Authors: Hyeonjun Jeong, Juyeb Shin, Dongsuk Kum Published: 2026-03-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.28090v2 Neural radiance fields (NeRFs) have emerged as a prominent pre-training paradigm for vision-centric autonomous driving, which enhances 3D geometry and appearance understanding in a fully self-supervised manner. To apply NeRF-based pretraining to 3D perception models, recent approaches have simply applied NeRFs to volumetric features obtained from view transformation. However, coupling NeRFs with view transformation inherits conflicting priors; view transformation imposes discrete and rigid representations, whereas radiance fields assume continuous and adaptive functions. When these opposing assumptions are forced into a single pipeline, the misalignment surfaces as blurry and ambiguous 3D representations that ultimately limit 3D scene understanding. Moreover, the NeRF network for pre-training is discarded during downstream tasks, resulting in inefficient utilization of enhanced 3D representations through NeRF. In this paper, we propose a novel NeRF-Resembled Point-based 3D detector that can learn continuous 3D representation and thus avoid the misaligned priors from view transformation. NeRP3D preserves the pre-trained NeRF network regardless of the tasks, inheriting the principle of continuous 3D representation learning and leading to greater potentials for both scene reconstruction and detection tasks. Experiments on nuScenes dataset demonstrate that our proposed approach significantly improves previous state-of-the-art methods, outperforming not only pretext scene reconstruction tasks but also downstream detection tasks. --- ### GEMS: Agent-Native Multimodal Generation with Memory and Skills Authors: Zefeng He, Siyuan Huang, Xiaoye Qu, Yafu Li, Tong Zhu, Yu Cheng, Yang Yang Published: 2026-03-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.28088v1 Recent multimodal generation models have achieved remarkable progress on general-purpose generation tasks, yet continue to struggle with complex instructions and specialized downstream tasks. Inspired by the success of advanced agent frameworks such as Claude Code, we propose \textbf{GEMS} (Agent-Native Multimodal \textbf{GE}neration with \textbf{M}emory and \textbf{S}kills), a framework that pushes beyond the inherent limitations of foundational models on both general and downstream tasks. GEMS is built upon three core components. Agent Loop introduces a structured multi-agent framework that iteratively improves generation quality through closed-loop optimization. Agent Memory provides a persistent, trajectory-level memory that hierarchically stores both factual states and compressed experiential summaries, enabling a global view of the optimization process while reducing redundancy. Agent Skill offers an extensible collection of domain-specific expertise with on-demand loading, allowing the system to effectively handle diverse downstream applications. Across five mainstream tasks and four downstream tasks, evaluated on multiple generative backends, GEMS consistently achieves significant performance gains. Most notably, it enables the lightweight 6B model Z-Image-Turbo to surpass the state-of-the-art Nano Banana 2 on GenEval2, demonstrating the effectiveness of agent harness in extending model capabilities beyond their original limits. --- ### MOSS-VoiceGenerator: Create Realistic Voices with Natural Language Descriptions Authors: Kexin Huang, Liwei Fan, Botian Jiang, Yaozhou Jiang, Qian Tu, Jie Zhu, Yuqian Zhang, Yiwei Zhao, Chenchen Yang, Zhaoye Fei, Shimin Li, Xiaogui Yang et al. Published: 2026-03-30 Categories: cs.SD, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.28086v1 Voice design from natural language aims to generate speaker timbres directly from free-form textual descriptions, allowing users to create voices tailored to specific roles, personalities, and emotions. Such controllable voice creation benefits a wide range of downstream applications-including storytelling, game dubbing, role-play agents, and conversational assistants, making it a significant task for modern Text-to-Speech models. However, existing models are largely trained on carefully recorded studio data, which produces speech that is clean and well-articulated, yet lacks the lived-in qualities of real human voices. To address these limitations, we present MOSS-VoiceGenerator, an open-source instruction-driven voice generation model that creates new timbres directly from natural language prompts. Motivated by the hypothesis that exposure to real-world acoustic variation produces more perceptually natural voices, we train on large-scale expressive speech data sourced from cinematic content. Subjective preference studies demonstrate its superiority in overall performance, instruction-following, and naturalness compared to other voice design models. --- ### LogiStory: A Logic-Aware Framework for Multi-Image Story Visualization Authors: Chutian Meng, Fan Ma, Chi Zhang, Jiaxu Miao, Yi Yang, Yueting Zhuang Published: 2026-03-30 Categories: cs.CV, cs.MA arXiv: https://arxiv.org/abs/2603.28082v1 Generating coherent and communicative visual sequences, such as image sequences and videos, remains a significant challenge for current multimodal systems. Despite advances in visual quality and the integration of world knowledge, existing models still struggle to maintain logical flow, often resulting in disjointed actions, fragmented narratives, and unclear storylines. We attribute these issues to the lack of attention to visual logic, a critical yet underexplored dimension of visual sequence generation that we define as the perceptual and causal coherence among characters, actions, and scenes over time. To bridge this gap, we propose a logic-aware multi-image story visualization framework, LogiStory. The framework is built around the central innovation of explicitly modeling visual logic in story visualization. To realize this idea, we design a multi-agent system that grounds roles, extracts causal chains, and verifies story-level consistency, transforming narrative coherence from an implicit byproduct of image generation into an explicit modeling objective. This design effectively bridges structured story planning with visual generation, enhancing both narrative clarity and visual quality in story visualization. Furthermore, to evaluate the generation capacity, we construct LogicTale, a benchmark comprising richly annotated stories, emphasizing causal reasoning, and visual logic interpretability. We establish comprehensive automatic and human evaluation protocols designed to measure both visual logic and perceptual quality. Experiments demonstrate that our approach significantly improves the narrative logic of generated visual stories. This work provides a foundational step towards modeling and enforcing visual logic in general image sequence and video generation tasks. --- ### Transformer-Based Prognostics: Enhancing Network Availability by Improved Monitoring of Optical Fiber Amplifiers Authors: Dominic Schneider, Lutz Rapp, Christoph Ament Published: 2026-03-30 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2603.28081v1 We enhance optical network availability and reliability through a lightweight transformer model that predicts optical fiber amplifier lifetime from condition-based monitoring data, enabling real-time, edge-level predictive maintenance and advancing deployable AI for autonomous network operation. --- ### Koopman-based surrogate modeling for reinforcement-learning-control of Rayleigh-Benard convection Authors: Tim Plotzki, Sebastian Peitz Published: 2026-03-30 Categories: cs.LG, math.DS arXiv: https://arxiv.org/abs/2603.28074v1 Training reinforcement learning (RL) agents to control fluid dynamics systems is computationally expensive due to the high cost of direct numerical simulations (DNS) of the governing equations. Surrogate models offer a promising alternative by approximating the dynamics at a fraction of the computational cost, but their feasibility as training environments for RL is limited by distribution shifts, as policies induce state distributions not covered by the surrogate training data. In this work, we investigate the use of Linear Recurrent Autoencoder Networks (LRANs) for accelerating RL-based control of 2D Rayleigh-Bénard convection. We evaluate two training strategies: a surrogate trained on precomputed data generated with random actions, and a policy-aware surrogate trained iteratively using data collected from an evolving policy. Our results show that while surrogate-only training leads to reduced control performance, combining surrogates with DNS in a pretraining scheme recovers state-of-the-art performance while reducing training time by more than 40%. We demonstrate that policy-aware training mitigates the effects of distribution shift, enabling more accurate predictions in policy-relevant regions of the state space. --- ### SIMR-NO: A Spectrally-Informed Multi-Resolution Neural Operator for Turbulent Flow Super-Resolution Authors: Muhammad Abid, Omer San Published: 2026-03-30 Categories: cs.LG, physics.flu-dyn arXiv: https://arxiv.org/abs/2603.28073v1 Reconstructing high-resolution turbulent flow fields from severely under-resolved observations is a fundamental inverse problem in computational fluid dynamics and scientific machine learning. Classical interpolation methods fail to recover missing fine-scale structures, while existing deep learning approaches rely on convolutional architectures that lack the spectral and multiscale inductive biases necessary for physically faithful reconstruction at large upscaling factors. We introduce the Spectrally-Informed Multi-Resolution Neural Operator (SIMR-NO), a hierarchical operator learning framework that factorizes the ill-posed inverse mapping across intermediate spatial resolutions, combines deterministic interpolation priors with spectrally gated Fourier residual corrections at each stage, and incorporates local refinement modules to recover fine-scale spatial features beyond the truncated Fourier basis. The proposed method is evaluated on Kolmogorov-forced two-dimensional turbulence, where $128\times128$ vorticity fields are reconstructed from extremely coarse $8\times8$ observations representing a $16\times$ downsampling factor. Across 201 independent test realizations, SIMR-NO achieves a mean relative $\ell_2$ error of $26.04\%$ with the lowest error variance among all methods, reducing reconstruction error by $31.7\%$ over FNO, $26.0\%$ over EDSR, and $9.3\%$ over LapSRN. Beyond pointwise accuracy, SIMR-NO is the only method that faithfully reproduces the ground-truth energy and enstrophy spectra across the full resolved wavenumber range, demonstrating physically consistent super-resolution of turbulent flow fields. --- ### MolmoPoint: Better Pointing for VLMs with Grounding Tokens Authors: Christopher Clark, Yue Yang, Jae Sung Park, Zixian Ma, Jieyu Zhang, Rohun Tripathi, Mohammadreza Salehi, Sangho Lee, Taira Anderson, Winson Han, Ranjay Krishna Published: 2026-03-30 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.28069v1 Grounding has become a fundamental capability of vision-language models (VLMs). Most existing VLMs point by generating coordinates as part of their text output, which requires learning a complicated coordinate system and results in a high token count. Instead, we propose a more intuitive pointing mechanism that directly selects the visual tokens that contain the target concept. Our model generates a special pointing token that cross-attends to the input image or video tokens and selects the appropriate one. To make this model more fine-grained, we follow these pointing tokens with an additional special token that selects a fine-grained subpatch within the initially selected region, and then a third token that specifies a location within that subpatch. We further show that performance improves by generating points sequentially in a consistent order, encoding the relative position of the previously selected point, and including a special no-more-points class when selecting visual tokens. Using this method, we set a new state-of-the-art on image pointing (70.7% on PointBench), set a new state-of-the-art among fully open models on GUI pointing (61.1% on ScreenSpotPro), and improve video pointing (59.1% human preference win rate vs. a text coordinate baseline) and tracking (+6.3% gain on Molmo2Track). We additionally show that our method achieves much higher sample efficiency and discuss the qualitative differences that emerge from this design change. --- ### AIBench: Evaluating Visual-Logical Consistency in Academic Illustration Generation Authors: Zhaohe Liao, Kaixun Jiang, Zhihang Liu, Yujie Wei, Junqiu Yu, Quanhao Li, Hong-Tao Yu, Pandeng Li, Yuzheng Wang, Zhen Xing, Shiwei Zhang, Chen-Wei Xie et al. Published: 2026-03-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.28068v2 Although image generation has boosted various applications via its rapid evolution, whether the state-of-the-art models are able to produce ready-to-use academic illustrations for papers is still largely unexplored. Directly comparing or evaluating the illustration with VLM is native but requires oracle multi-modal understanding ability, which is unreliable for long and complex texts and illustrations. To address this, we propose AIBench, the first benchmark using VQA for evaluating logic correctness of the academic illustrations and VLMs for assessing aesthetics. In detail, we designed four levels of questions proposed from a logic diagram summarized from the method part of the paper, which query whether the generated illustration aligns with the paper on different scales. Our VQA-based approach raises more accurate and detailed evaluations on visual-logical consistency while relying less on the ability of the judger VLM. With our high-quality AIBench, we conduct extensive experiments and conclude that the performance gap between models on this task is significantly larger than general ones, reflecting their various complex reasoning and high-density generation ability. Further, the logic and aesthetics are hard to optimize simultaneously as in handcrafted illustrations. Additional experiments further state that test-time scaling on both abilities significantly boosts the performance on this task. --- ### From Vessel Trajectories to Safety-Critical Encounter Scenarios: A Generative AI Framework for Autonomous Ship Digital Testing Authors: Sijin Sun, Liangbin Zhao, Xiuju Fu Published: 2026-03-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.28067v2 Digital testing has emerged as a key paradigm for the development and verification of autonomous maritime navigation systems, yet the availability of realistic and diverse safety-critical encounter scenarios remains limited. Existing approaches either rely on handcrafted templates, which lack realism, or extract cases directly from historical data, which cannot systematically expand rare high-risk situations. This paper proposes a data-driven framework that converts large-scale Automatic Identification System (AIS) trajectories into structured safety-critical encounter scenarios. The framework combines generative trajectory modeling with automated encounter pairing and temporal parameterization to enable scalable scenario construction while preserving real traffic characteristics. To enhance trajectory realism and robustness under noisy AIS observations, a multi-scale temporal variational autoencoder is introduced to capture vessel motion dynamics across different temporal resolutions. Experiments on real-world maritime traffic flows demonstrate that the proposed method improves trajectory fidelity and smoothness, maintains statistical consistency with observed data, and enables the generation of diverse safety-critical encounter scenarios beyond those directly recorded. The resulting framework provides a practical pathway for building scenario libraries to support digital testing, benchmarking, and safety assessment of autonomous navigation and intelligent maritime traffic management systems. Code is available at https://anonymous.4open.science/r/traj-gen-anonymous-review. --- ### Synonymix: Unified Group Personas for Generative Simulations Authors: Huanxing Chen, Aditesh Kumar Published: 2026-03-30 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2603.28066v1 Generative agent simulations operate at two scales: individual personas for character interaction, and population models for collective behavior analysis and intervention testing. We propose a third scale: meso-level simulation - interaction with group-level representations that retain grounding in rich individual experience. To enable this, we present Synonymix, a pipeline that constructs a "unigraph" from multiple life story personas via graph-based abstraction and merging, producing a queryable collective representation that can be explored for sensemaking or sampled for synthetic persona generation. Evaluating synthetic agents on General Social Survey items, we demonstrate behavioral signal preservation beyond demographic baselines (p<0.001, r=0.59) with demonstrable privacy guarantee (max source contribution <13%). We invite discussion on interaction modalities enabled by meso-level simulations, and whether "high-fidelity" personas can ever capture the texture of lived experience. --- ### \textit{4DSurf}: High-Fidelity Dynamic Scene Surface Reconstruction Authors: Renjie Wu, Hongdong Li, Jose M. Alvarez, Miaomiao Liu Published: 2026-03-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.28064v1 This paper addresses the problem of dynamic scene surface reconstruction using Gaussian Splatting (GS), aiming to recover temporally consistent geometry. While existing GS-based dynamic surface reconstruction methods can yield superior reconstruction, they are typically limited to either a single object or objects with only small deformations, struggling to maintain temporally consistent surface reconstruction of large deformations over time. We propose ``\textit{4DSurf}'', a novel and unified framework for generic dynamic surface reconstruction that does not require specifying the number or types of objects in the scene, can handle large surface deformations and temporal inconsistency in reconstruction. The key innovation of our framework is the introduction of Gaussian deformations induced Signed Distance Function Flow Regularization that constrains the motion of Gaussians to align with the evolving surface. To handle large deformations, we introduce an Overlapping Segment Partitioning strategy that divides the sequence into overlapping segments with small deformations and incrementally passes geometric information across segments through the shared overlapping timestep. Experiments on two challenging dynamic scene datasets, Hi4D and CMU Panoptic, demonstrate that our method outperforms state-of-the-art surface reconstruction methods by 49\% and 19\% in Chamfer distance, respectively, and achieves superior temporal consistency under sparse-view settings. --- ### Reward Hacking as Equilibrium under Finite Evaluation Authors: Jiacheng Wang, Jinbin Huang Published: 2026-03-30 Categories: cs.AI, cs.GT arXiv: https://arxiv.org/abs/2603.28063v1 We prove that under five minimal axioms -- multi-dimensional quality, finite evaluation, effective optimization, resource finiteness, and combinatorial interaction -- any optimized AI agent will systematically under-invest effort in quality dimensions not covered by its evaluation system. This result establishes reward hacking as a structural equilibrium, not a correctable bug, and holds regardless of the specific alignment method (RLHF, DPO, Constitutional AI, or others) or evaluation architecture employed. Our framework instantiates the multi-task principal-agent model of Holmstrom and Milgrom (1991) in the AI alignment setting, but exploits a structural feature unique to AI systems -- the known, differentiable architecture of reward models -- to derive a computable distortion index that predicts both the direction and severity of hacking on each quality dimension prior to deployment. We further prove that the transition from closed reasoning to agentic systems causes evaluation coverage to decline toward zero as tool count grows -- because quality dimensions expand combinatorially while evaluation costs grow at most linearly per tool -- so that hacking severity increases structurally and without bound. Our results unify the explanation of sycophancy, length gaming, and specification gaming under a single theoretical structure and yield an actionable vulnerability assessment procedure. We further conjecture -- with partial formal analysis -- the existence of a capability threshold beyond which agents transition from gaming within the evaluation system (Goodhart regime) to actively degrading the evaluation system itself (Campbell regime), providing the first economic formalization of Bostrom's (2014) "treacherous turn." --- ### SLOW: Strategic Logical-inference Open Workspace for Cognitive Adaptation in AI Tutoring Authors: Yuang Wei, Ruijia Li, Bo Jiang Published: 2026-03-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.28062v1 While Large Language Models (LLMs) have demonstrated remarkable fluency in educational dialogues, most generative tutors primarily operate through intuitive, single-pass generation. This reliance on fast thinking precludes a dedicated reasoning workspace, forcing multiple diagnostic and strategic signals to be processed in a conflated manner. As a result, learner cognitive diagnosis, affective perception, and pedagogical decision-making become tightly entangled, which limits the tutoring system's capacity for deliberate instructional adaptation. We propose SLOW, a theory-informed tutoring framework that supports deliberate learner-state reasoning within a transparent decision workspace. Inspired by dual-process accounts of human tutoring, SLOW explicitly separates learner-state inference from instructional action selection. The framework integrates causal evidence parsing from learner language, fuzzy cognitive diagnosis with counterfactual stability analysis, and prospective affective reasoning to anticipate how instructional choices may influence learners' emotional trajectories. These signals are jointly considered to guide pedagogically and affectively aligned tutoring strategies. Evaluation using hybrid human-AI judgments demonstrates significant improvements in personalization, emotional sensitivity, and clarity. Ablation studies further confirm the necessity of each module, showcasing how SLOW enables interpretable and reliable intelligent tutoring through a visualized decision-making process. This work advances the interpretability and educational validity of LLM-based adaptive instruction. --- ### Physics-Embedded Feature Learning for AI in Medical Imaging Authors: Pulock Das, Al Amin, Kamrul Hasan, Rohan Thompson, Azubike D. Okpalaeze, Liang Hong Published: 2026-03-30 Categories: cs.LG, eess.IV arXiv: https://arxiv.org/abs/2603.28057v1 Deep learning (DL) models have achieved strong performance in an intelligence healthcare setting, yet most existing approaches operate as black boxes and ignore the physical processes that govern tumor growth, limiting interpretability, robustness, and clinical trust. To address this limitation, we propose PhysNet, a physics-embedded DL framework that integrates tumor growth dynamics directly into the feature learning process of a convolutional neural network (CNN). Unlike conventional physics-informed methods that impose physical constraints only at the output level, PhysNet embeds a reaction diffusion model of tumor growth within intermediate feature representations of a ResNet backbone. The architecture jointly performs multi-class tumor classification while learning a latent tumor density field, its temporal evolution, and biologically meaningful physical parameters, including tumor diffusion and growth rates, through end-to-end training. This design is necessary because purely data-driven models, even when highly accurate or ensemble-based, cannot guarantee physically consistent predictions or provide insight into tumor behavior. Experimental results on a large brain MRI dataset demonstrate that PhysNet outperforms multiple state-of-the-art DL baselines, including MobileNetV2, VGG16, VGG19, and ensemble models, achieving superior classification accuracy and F1-score. In addition to improved performance, PhysNet produces interpretable latent representations and learned bio-physical parameters that align with established medical knowledge, highlighting physics-embedded representation learning as a practical pathway toward more trustworthy and clinically meaningful medical AI systems. --- ### Who Wrote the Book? Detecting and Attributing LLM Ghostwriters Authors: Anudeex Shetty, Qiongkai Xu, Olga Ohrimenko, Jey Han Lau Published: 2026-03-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.28054v2 In this paper, we introduce GhostWriteBench, a dataset for LLM authorship attribution. It comprises long-form texts (50K+ words per book) generated by frontier LLMs, and is designed to test generalisation across multiple out-of-distribution (OOD) dimensions, including domain and unseen LLM author. We also propose TRACE -- a novel fingerprinting method that is interpretable and lightweight -- that works for both open- and closed-source models. TRACE creates the fingerprint by capturing token-level transition patterns (e.g., word rank) estimated by another lightweight language model. Experiments on GhostWriteBench demonstrate that TRACE achieves state-of-the-art performance, remains robust in OOD settings, and works well in limited training data scenarios. --- ### Reducing Oracle Feedback with Vision-Language Embeddings for Preference-Based RL Authors: Udita Ghosh, Dripta S. Raychaudhuri, Jiachen Li, Konstantinos Karydis, Amit Roy-Chowdhury Published: 2026-03-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.28053v1 Preference-based reinforcement learning can learn effective reward functions from comparisons, but its scalability is constrained by the high cost of oracle feedback. Lightweight vision-language embedding (VLE) models provide a cheaper alternative, but their noisy outputs limit their effectiveness as standalone reward generators. To address this challenge, we propose ROVED, a hybrid framework that combines VLE-based supervision with targeted oracle feedback. Our method uses the VLE to generate segment-level preferences and defers to an oracle only for samples with high uncertainty, identified through a filtering mechanism. In addition, we introduce a parameter-efficient fine-tuning method that adapts the VLE with the obtained oracle feedback in order to improve the model over time in a synergistic fashion. This ensures the retention of the scalability of embeddings and the accuracy of oracles, while avoiding their inefficiencies. Across multiple robotic manipulation tasks, ROVED matches or surpasses prior preference-based methods while reducing oracle queries by up to 80%. Remarkably, the adapted VLE generalizes across tasks, yielding cumulative annotation savings of up to 90%, highlighting the practicality of combining scalable embeddings with precise oracle supervision for preference-based RL. --- ### Meta-Harness: End-to-End Optimization of Model Harnesses Authors: Yoonho Lee, Roshen Nair, Qizheng Zhang, Kangwook Lee, Omar Khattab, Chelsea Finn Published: 2026-03-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.28052v1 The performance of large language model (LLM) systems depends not only on model weights, but also on their harness: the code that determines what information to store, retrieve, and present to the model. Yet harnesses are still designed largely by hand, and existing text optimizers are poorly matched to this setting because they compress feedback too aggressively. We introduce Meta-Harness, an outer-loop system that searches over harness code for LLM applications. It uses an agentic proposer that accesses the source code, scores, and execution traces of all prior candidates through a filesystem. On online text classification, Meta-Harness improves over a state-of-the-art context management system by 7.7 points while using 4x fewer context tokens. On retrieval-augmented math reasoning, a single discovered harness improves accuracy on 200 IMO-level problems by 4.7 points on average across five held-out models. On agentic coding, discovered harnesses surpass the best hand-engineered baselines on TerminalBench-2. Together, these results show that richer access to prior experience can enable automated harness engineering. --- ### Object Detection Based on Distributed Convolutional Neural Networks Authors: Liang Sun Published: 2026-03-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.28050v1 Based on the Distributed Convolutional Neural Network(DisCNN), a straightforward object detection method is proposed. The modules of the output vector of a DisCNN with respect to a specific positive class are positively monotonic with the presence probabilities of the positive features. So, by identifying all high-scoring patches across all possible scales, the positive object can be detected by overlapping them to form a bounding box. The essential idea is that the object is detected by detecting its features on multiple scales, ranging from specific sub-features to abstract features composed of these sub-features. Training DisCNN requires only object-centered image data with positive and negative class labels. The detection process for multiple positive classes can be conducted in parallel to significantly accelerate it, and also faster for single-object detection because of its lightweight model architecture. --- ### Drift-AR: Single-Step Visual Autoregressive Generation via Anti-Symmetric Drifting Authors: Zhen Zou, Xiaoxiao Ma, Mingde Yao, Jie Huang, LinJiang Huang, Feng Zhao Published: 2026-03-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.28049v3 Autoregressive (AR)-Diffusion hybrid paradigms combine AR's structured semantic modeling with diffusion's high-fidelity synthesis, yet suffer from a dual speed bottleneck: the sequential AR stage and the iterative multi-step denoising of the diffusion vision decode stage. Existing methods address each in isolation without a unified principle design. We observe that the per-position \emph{prediction entropy} of continuous-space AR models naturally encodes spatially varying generation uncertainty, which simultaneously governing draft prediction quality in the AR stage and reflecting the corrective effort required by vision decoding stage, which is not fully explored before. Since entropy is inherently tied to both bottlenecks, it serves as a natural unifying signal for joint acceleration. In this work, we propose \textbf{Drift-AR}, which leverages entropy signal to accelerate both stages: 1) for AR acceleration, we introduce Entropy-Informed Speculative Decoding that align draft-target entropy distributions via a causal-normalized entropy loss, resolving the entropy mismatch that causes excessive draft rejection; 2) for visual decoder acceleration, we reinterpret entropy as the \emph{physical variance} of the initial state for an anti-symmetric drifting field -- high-entropy positions activate stronger drift toward the data manifold while low-entropy positions yield vanishing drift -- enabling single-step (1-NFE) decoding without iterative denoising or distillation. Moreover, both stages share the same entropy signal, which is computed once with no extra cost. Experiments on MAR, TransDiff, and NextStep-1 demonstrate 3.8-5.5$\times$ speedup with genuine 1-NFE decoding, matching or surpassing original quality. Code will be available at https://github.com/aSleepyTree/Drift-AR. --- ### Dogfight Search: A Swarm-Based Optimization Algorithm for Complex Engineering Optimization and Mountainous Terrain Path Planning Authors: Yujing Sun, Jie Cai, Xingguo Xu, Yuansheng Gao, Lei Zhang, Kaichen Ouyang, Zhanyu Liu Published: 2026-03-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.28046v1 Dogfight is a tactical behavior of cooperation between fighters. Inspired by this, this paper proposes a novel metaphor-free metaheuristic algorithm called Dogfight Search (DoS). Unlike traditional algorithms, DoS draws algorithmic framework from the inspiration, but its search mechanism is constructed based on the displacement integration equations in kinematics. Through experimental validation on CEC2017 and CEC2022 benchmark test functions, 10 real-world constrained optimization problems and mountainous terrain path planning tasks, DoS significantly outperforms 7 advanced competitors in overall performance and ranks first in the Friedman ranking. Furthermore, this paper compares the performance of DoS with 3 SOTA algorithms on the CEC2017 and CEC2022 benchmark test functions. The results show that DoS continues to maintain its lead, demonstrating strong competitiveness. The source code of DoS is available at https://ww2.mathworks.cn/matlabcentral/fileexchange/183519-dogfight-search. --- ### Event6D: Event-based Novel Object 6D Pose Tracking Authors: Jae-Young Kang, Hoonhee Cho, Taeyeop Lee, Minjun Kang, Bowen Wen, Youngho Kim, Kuk-Jin Yoon Published: 2026-03-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.28045v2 Event cameras provide microsecond latency, making them suitable for 6D object pose tracking in fast, dynamic scenes where conventional RGB and depth pipelines suffer from motion blur and large pixel displacements. We introduce EventTrack6D, an event-depth tracking framework that generalizes to novel objects without object-specific training by reconstructing both intensity and depth at arbitrary timestamps between depth frames. Conditioned on the most recent depth measurement, our dual reconstruction recovers dense photometric and geometric cues from sparse event streams. Our EventTrack6D operates at over 120 FPS and maintains temporal consistency under rapid motion. To support training and evaluation, we introduce a comprehensive benchmark suite: a large-scale synthetic dataset for training and two complementary evaluation sets, including real and simulated event datasets. Trained exclusively on synthetic data, EventTrack6D generalizes effectively to real-world scenarios without fine-tuning, maintaining accurate tracking across diverse objects and motion patterns. Our method and datasets validate the effectiveness of event cameras for event-based 6D pose tracking of novel objects. Code and datasets are publicly available at https://chohoonhee.github.io/Event6D. --- ### Bit-Identical Medical Deep Learning via Structured Orthogonal Initialization Authors: Yakov Pyotr Shkolnikov Published: 2026-03-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.28040v1 Deep learning training is non-deterministic: identical code with different random seeds produces models that agree on aggregate metrics but disagree on individual predictions, with per-class AUC swings exceeding 20 percentage points on rare clinical classes. We present a framework for verified bit-identical training that eliminates three sources of randomness: weight initialization (via structured orthogonal basis functions), batch ordering (via golden ratio scheduling), and non-deterministic GPU operations (via architecture selection and custom autograd). The pipeline produces MD5-verified identical trained weights across independent runs. On PTB-XL ECG rhythm classification, structured initialization significantly exceeds Kaiming across two architectures (n=20; Conformer p = 0.016, Baseline p < 0.001), reducing aggregate variance by 2-3x and reducing per-class variability on rare rhythms by up to 7.5x (TRIGU range: 4.1pp vs 30.9pp under Kaiming, independently confirmed by 3-fold CV). A four-basis comparison at n=20 shows all structured orthogonal bases produce equivalent performance (Friedman p=0.48), establishing that the contribution is deterministic structured initialization itself, not any particular basis function. Cross-domain validation on seven MedMNIST benchmarks (n=20, all p > 0.14) confirms no performance penalty on standard tasks; per-class analysis on imbalanced tasks (ChestMNIST, RetinaMNIST) shows the same variance reduction on rare classes observed in ECG. Cross-dataset evaluation on three external ECG databases confirms zero-shot generalization (>0.93 AFIB AUC). --- ### Beyond the Answer: Decoding the Behavior of LLMs as Scientific Reasoners Authors: Rohan Pandey, Eric Ye, Michael Li Published: 2026-03-30 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.28038v1 As Large Language Models (LLMs) achieve increasingly sophisticated performance on complex reasoning tasks, current architectures serve as critical proxies for the internal heuristics of frontier models. Characterizing emergent reasoning is vital for long-term interpretability and safety. Furthermore, understanding how prompting modulates these processes is essential, as natural language will likely be the primary interface for interacting with AGI systems. In this work, we use a custom variant of Genetic Pareto (GEPA) to systematically optimize prompts for scientific reasoning tasks, and analyze how prompting can affect reasoning behavior. We investigate the structural patterns and logical heuristics inherent in GEPA-optimized prompts, and evaluate their transferability and brittleness. Our findings reveal that gains in scientific reasoning often correspond to model-specific heuristics that fail to generalize across systems, which we call "local" logic. By framing prompt optimization as a tool for model interpretability, we argue that mapping these preferred reasoning structures for LLMs is an important prerequisite for effectively collaborating with superhuman intelligence. --- ### Diffusion Maps is not Dimensionality Reduction Authors: Julio Candanedo, Alejandro Patiño Published: 2026-03-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.28037v1 Diffusion maps (DMAP) are often used as a dimensionality-reduction tool, but more precisely they provide a spectral representation of the intrinsic geometry rather than a complete charting method. To illustrate this distinction, we study a Swiss roll with known isometric coordinates and compare DMAP, Isomap, and UMAP across latent dimensions. For each representation, we fit an oracle affine readout to the ground-truth chart and measure reconstruction error. Isomap most efficiently recovers the low-dimensional chart, UMAP provides an intermediate tradeoff, and DMAP becomes accurate only after combining multiple diffusion modes. Thus the correct chart lies in the span of diffusion coordinates, but standard DMAP do not by themselves identify the appropriate combination. --- ### Transfer Learning for an Endangered Slavic Variety: Dependency Parsing in Pomak Across Contact-Shaped Dialects Authors: Sercan Karakaş Published: 2026-03-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.28033v1 This paper presents new resources and baselines for Dependency Parsing in Pomak, an endangered Eastern South Slavic language with substantial dialectal variation and no widely adopted standard. We focus on the variety spoken in Turkey (Uzunköprü) and ask how well a dependency parser trained on the existing Pomak Universal Dependencies treebank, which was built primarily from the variety that is spoken in Greece, transfers across dialects. We run two experimental phases. First, we train a parser on the Greek-variety UD data and evaluate zero-shot transfer to Turkish-variety Pomak, quantifying the impact of phonological and morphosyntactic differences. Second, we introduce a new manually annotated Turkish-variety Pomak corpus of 650 sentences and show that, despite its small size, targeted fine-tuning substantially improves accuracy; performance is further boosted by cross-variety transfer learning that combines the two dialects. --- ### CARLA-Air: Fly Drones Inside a CARLA World -- A Unified Infrastructure for Air-Ground Embodied Intelligence Authors: Tianle Zeng, Yanci Wen, Hong Zhang Published: 2026-03-30 Categories: cs.RO, cs.AI, cs.CV, cs.HC arXiv: https://arxiv.org/abs/2603.28032v2 The convergence of low-altitude economies, embodied intelligence, and air-ground cooperative systems creates growing demand for simulation infrastructure capable of jointly modeling aerial and ground agents within a single physically coherent environment. Existing open-source platforms remain domain-segregated: driving simulators lack aerial dynamics, while multirotor simulators lack realistic ground scenes. Bridge-based co-simulation introduces synchronization overhead and cannot guarantee strict spatial-temporal consistency. We present CARLA-Air, an open-source infrastructure that unifies high-fidelity urban driving and physics-accurate multirotor flight within a single Unreal Engine process. The platform preserves both CARLA and AirSim native Python APIs and ROS 2 interfaces, enabling zero-modification code reuse. Within a shared physics tick and rendering pipeline, CARLA-Air delivers photorealistic environments with rule-compliant traffic, socially-aware pedestrians, and aerodynamically consistent UAV dynamics, synchronously capturing up to 18 sensor modalities across all platforms at each tick. The platform supports representative air-ground embodied intelligence workloads spanning cooperation, embodied navigation and vision-language action, multi-modal perception and dataset construction, and reinforcement-learning-based policy training. An extensible asset pipeline allows integration of custom robot platforms into the shared world. By inheriting AirSim's aerial capabilities -- whose upstream development has been archived -- CARLA-Air ensures this widely adopted flight stack continues to evolve within a modern infrastructure. Released with prebuilt binaries and full source: https://github.com/louiszengCN/CarlaAir --- ### Effort-Based Criticality Metrics for Evaluating 3D Perception Errors in Autonomous Driving Authors: Sharang Kaul, Simon Bultmann, Mario Berk, Abhinav Valada Published: 2026-03-30 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2603.28029v3 Criticality metrics such as time-to-collision (TTC) quantify collision urgency but do not distinguish the operational consequences of false-positive (FP) and false-negative (FN) perception errors. We formulate two error-specific effort metrics: False Speed Reduction (FSR), the cumulative velocity loss associated with persistent phantom detections, and Maximum Deceleration Rate (MDR), the peak braking demand associated with missed objects under a longitudinal kinematic model. These longitudinal metrics are complemented by Lateral Evasion Acceleration (LEA), adapted from prior lateral-evasion kinematics and coupled with reachability-based collision timing. The collision check quantifies the minimum steering effort required to avoid a predicted collision. A dynamically conservative, semantically unfiltered reachability gate selects candidate interactions before frame-level scoring and track-level aggregation. Evaluation on nuScenes and Argoverse 2 shows that 65% to 93% of errors fall below the chosen criticality thresholds. Correlation and threshold analysis indicate that the proposed metrics provide complementary rankings for screening and mining perception failures and are not substitutes for closed-loop safety validation. --- ### Effort-Based Criticality Metrics for Evaluating 3D Perception Errors in Autonomous Driving Authors: Sharang Kaul, Simon Bultmann, Mario Berk, Abhinav Valada Published: 2026-03-30 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2603.28029v2 Criticality metrics such as time-to-collision (TTC) quantify collision urgency but do not distinguish the operational consequences of false-positive (FP) and false-negative (FN) perception errors. We formulate two error-specific effort metrics: False Speed Reduction (FSR), the cumulative velocity loss associated with persistent phantom detections, and Maximum Deceleration Rate (MDR), the peak braking demand associated with missed objects under a longitudinal kinematic model. These longitudinal metrics are complemented by Lateral Evasion Acceleration (LEA), adapted from prior lateral-evasion kinematics and coupled with reachability-based collision timing. The collision check quantifies the minimum steering effort required to avoid a predicted collision. A dynamically conservative, semantically unfiltered reachability gate selects candidate interactions before frame-level scoring and track-level aggregation. Evaluation on nuScenes and Argoverse 2 shows that 65% to 93% of errors fall below the chosen criticality thresholds. Correlation and threshold analysis indicate that the proposed metrics provide complementary rankings for screening and mining perception failures and are not substitutes for closed-loop safety validation. --- ### Efficient Domain Adaptation for Text Line Recognition via Decoupled Language Models Authors: Arundhathi Dev, Justin Zhan Published: 2026-03-30 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.28028v1 Optical character recognition remains critical infrastructure for document digitization, yet state-of-the-art performance is often restricted to well-resourced institutions by prohibitive computational barriers. End-to-end transformer architectures achieve strong accuracy but demand hundreds of GPU hours for domain adaptation, limiting accessibility for practitioners and digital humanities scholars. We present a modular detection-and-correction framework that achieves near-SOTA accuracy with single-GPU training. Our approach decouples lightweight visual character detection (domain-agnostic) from domain-specific linguistic correction using pretrained sequence models including T5, ByT5, and BART. By training the correctors entirely on synthetic noise, we enable annotation-free domain adaptation without requiring labeled target images. Evaluating across modern clean handwriting, cursive script, and historical documents, we identify a critical "Pareto frontier" in architecture selection: T5-Base excels on modern text with standard vocabulary, whereas ByT5-Base dominates on historical documents by reconstructing archaic spellings at the byte level. Our results demonstrate that this decoupled paradigm matches end-to-end transformer accuracy while reducing compute by approximately 95%, establishing a viable, resource-efficient alternative to monolithic OCR architectures. --- ### Adapting SAM to Nuclei Instance Segmentation and Classification via Cooperative Fine-Grained Refinement Authors: Jingze Su, Tianle Zhu, Jiaxin Cai, Zhiyi Wang, Qi Li, Xiao Zhang, Tong Tong, Shu Wang, Wenxi Liu Published: 2026-03-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.28027v1 Nuclei instance segmentation is critical in computational pathology for cancer diagnosis and prognosis. Recently, the Segment Anything Model has demonstrated exceptional performance in various segmentation tasks, leveraging its rich priors and powerful global context modeling capabilities derived from large-scale pre-training on natural images. However, directly applying SAM to the medical imaging domain faces significant limitations: it lacks sufficient perception of the local structural features that are crucial for nuclei segmentation, and full fine-tuning for downstream tasks requires substantial computational costs. To efficiently transfer SAM's robust prior knowledge to nuclei instance segmentation while supplementing its task-aware local perception, we propose a parameter-efficient fine-tuning framework, named Cooperative Fine-Grained Refinement of SAM, consisting of three core components: 1) a Multi-scale Adaptive Local-aware Adapter, which enables effective capability transfer by augmenting the frozen SAM backbone with minimal parameters and instilling a powerful perception of local structures through dynamically generated, multi-scale convolutional kernels; 2) a Hierarchical Modulated Fusion Module, which dynamically aggregates multi-level encoder features to preserve fine-grained spatial details; and 3) a Boundary-Guided Mask Refinement, which integrates multi-context boundary cues with semantic features through explicit supervision, producing a boundary-focused signal to refine initial mask predictions for sharper delineation. These three components work cooperatively to enhance local perception, preserve spatial details, and refine boundaries, enabling SAM to perform accurate nuclei instance segmentation directly. --- ### BUZZY: Contrastive Scoring to Mitigate Text-Induced Bias in Multimodal Multiple-Choice QA Authors: Taeyun Roh, Suhyeong Park, Dongyoung Lee, Wonjune Jang, Junha Jung, Eunyeong Jo, Jaewoo Kang Published: 2026-03-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.28026v4 Multimodal multiple-choice question answering (MCQA) provides a standardized and objectively measurable setting for evaluating vision-language models (VLMs). However, because the MCQA format incorporates the candidate choices into the input context, it introduces several unintended biases. Previous work has primarily focused on structural biases, such as preferences for certain choices. Instead, we argue that the choices act as textual priors, causing models to favor linguistically plausible options regardless of the visual content. We hypothesize and empirically verify that a model genuinely relies on visual evidence only when its multimodal distribution significantly diverges from its text-only distribution. Based on this observation we propose BUZZY,a training-free decoding method that corrects multimodal predictions by subtracting the text-only distribution. Experiments with five VLMs on five multimodal MCQA benchmarks demonstrate that BUZZY achieves the highest average accuracy among state-of-the-art methods while reducing inference latency by over 28% compared to prior contrastive decoding approaches. Overall, these results suggest that amplifying the visual signal by penalizing text-only preferences is key to efficient and robust multimodal MCQA reasoning. Code and additional resources are provided https://txxnrd.github.io/buzzy/. --- ### When Choices Become Priors: Contrastive Decoding for Scientific Figure Multiple-Choice QA Authors: Taeyun Roh, Eun-yeong Jo, Wonjune Jang, Jaewoo Kang Published: 2026-03-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.28026v1 Scientific figure multiple-choice question answering (MCQA) requires models to reason over diverse visual evidence, ranging from charts and multipanel figures to microscopy and biomedical images. However, this setting suffers from a distinctive bias: answer choices themselves can act as priors, steering multimodal models toward scientifically plausible options even when the figure supports a different answer. We investigate this failure mode through a simple question: what if decoding explicitly discounts what the model would prefer from text alone, so as to favor figure-grounded evidence? To this end, we propose SCICON, a training-free decoding method that scores each candidate by subtracting a text-only option score from its image-conditioned counterpart. Unlike prior contrastive decoding approaches that mitigate hallucinations by contrasting original inputs with distorted images or perturbed instructions, SCICON directly targets the choice-induced prior encoded in candidate text. Across three scientific figure QA benchmarks and three model backbones, SCICON consistently improves accuracy over standard decoding baselines. These results show that decoding against choice-induced priors is an effective and simple way to improve figure-grounded reasoning in scientific MCQA. --- ### SegRGB-X: General RGB-X Semantic Segmentation Model Authors: Jiong Liu, Yingjie Xu, Xingcheng Zhou, Rui Song, Walter Zimmer, Alois Knoll, Hu Cao Published: 2026-03-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.28023v1 Semantic segmentation across arbitrary sensor modalities faces significant challenges due to diverse sensor characteristics, and the traditional configurations for this task result in redundant development efforts. We address these challenges by introducing a universal arbitrary-modal semantic segmentation framework that unifies segmentation across multiple modalities. Our approach features three key innovations: (1) the Modality-aware CLIP (MA-CLIP), which provides modality-specific scene understanding guidance through LoRA fine-tuning; (2) Modality-aligned Embeddings for capturing fine-grained features; and (3) the Domain-specific Refinement Module (DSRM) for dynamic feature adjustment. Evaluated on five diverse datasets with different complementary modalities (event, thermal, depth, polarization, and light field), our model surpasses specialized multi-modal methods and achieves state-of-the-art performance with a mIoU of 65.03%. The codes will be released upon acceptance. --- ### Physically Inspired Gaussian Splatting for HDR Novel View Synthesis Authors: Huimin Zeng, Yue Bai, Hailing Wang, Yun Fu Published: 2026-03-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.28020v1 High dynamic range novel view synthesis (HDR-NVS) reconstructs scenes with dynamic details by fusing multi-exposure low dynamic range (LDR) views, yet it struggles to capture ambient illumination-dependent appearance. Implicitly supervising HDR content by constraining tone-mapped results fails in correcting abnormal HDR values, and results in limited gradients for Gaussians in under/over-exposed regions. To this end, we introduce PhysHDR-GS, a physically inspired HDR-NVS framework that models scene appearance via intrinsic reflectance and adjustable ambient illumination. PhysHDR-GS employs a complementary image-exposure (IE) branch and Gaussian-illumination (GI) branch to faithfully reproduce standard camera observations and capture illumination-dependent appearance changes, respectively. During training, the proposed cross-branch HDR consistency loss provides explicit supervision for HDR content, while an illumination-guided gradient scaling strategy mitigates exposure-biased gradient starvation and reduces under-densified representations. Experimental results across realistic and synthetic datasets demonstrate our superiority in reconstructing HDR details (e.g., a PSNR gain of 2.04 dB over HDR-GS), while maintaining real-time rendering speed (up to 76 FPS). Code and models are available at https://huimin-zeng.github.io/PhysHDR-GS/. --- ### What an Autonomous Agent Discovers About Molecular Transformer Design: Does It Transfer? Authors: Edward Wijaya Published: 2026-03-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.28015v1 Deep learning models for drug-like molecules and proteins overwhelmingly reuse transformer architectures designed for natural language, yet whether molecular sequences benefit from different designs has not been systematically tested. We deploy autonomous architecture search via an agent across three sequence types (SMILES, protein, and English text as control), running 3,106 experiments on a single GPU. For SMILES, architecture search is counterproductive: tuning learning rates and schedules alone outperforms the full search (p = 0.001). For natural language, architecture changes drive 81% of improvement (p = 0.009). Proteins fall between the two. Surprisingly, although the agent discovers distinct architectures per domain (p = 0.004), every innovation transfers across all three domains with <1% degradation, indicating that the differences reflect search-path dependence rather than fundamental biological requirements. We release a decision framework and open-source toolkit for molecular modeling teams to choose between autonomous architecture search and simple hyperparameter tuning. --- ### Kill-Chain Canaries: Stage-Level Tracking of Prompt Injection Across Attack Surfaces and Model Safety Tiers Authors: Haochuan Kevin Wang, Zechen Zhang Published: 2026-03-30 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.28013v3 Multi-agent LLM systems are entering production -- processing documents, managing workflows, acting on behalf of users -- yet their resilience to prompt injection is still evaluated with a single binary: did the attack succeed? This leaves architects without the diagnostic information needed to harden real pipelines. We introduce a kill-chain canary methodology that tracks a cryptographic token through four stages (EXPOSED -> PERSISTED -> RELAYED -> EXECUTED) across 950 runs, five frontier LLMs, six attack surfaces, and five defense conditions. The results reframe prompt injection as a pipeline-architecture problem: every model is fully exposed, yet outcomes diverge downstream -- Claude blocks all injections at memory-write (0/164 ASR), GPT-4o-mini propagates at 53%, and DeepSeek exhibits 0%/100% across surfaces from the same model. Three findings matter for deployment: (1) write-node placement is the highest-leverage safety decision -- routing writes through a verified model eliminates propagation; (2) all four defenses fail on at least one surface due to channel mismatch alone, no adversarial adaptation required; (3) invisible whitefont PDF payloads match or exceed visible-text ASR, meaning rendered-layer screening is insufficient. These dynamics apply directly to production: institutional investors and financial firms already run NLP pipelines over earnings calls, SEC filings, and analyst reports -- the document-ingestion workflows now migrating to LLM agents. Code, run logs, and tooling are publicly released. --- ### HeteroHub: An Applicable Data Management Framework for Heterogeneous Multi-Embodied Agent System Authors: Xujia Li, Xin Li, Junquan Huang, Beirong Cui, Zibin Wu, Lei Chen Published: 2026-03-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.28010v1 Heterogeneous Multi-Embodied Agent Systems involve coordinating multiple embodied agents with diverse capabilities to accomplish tasks in dynamic environments. This process requires the collection, generation, and consumption of massive, heterogeneous data, which primarily falls into three categories: static knowledge regarding the agents, tasks, and environments; multimodal training datasets tailored for various AI models; and high-frequency sensor streams. However, existing frameworks lack a unified data management infrastructure to support the real-world deployment of such systems. To address this gap, we present \textbf{HeteroHub}, a data-centric framework that integrates static metadata, task-aligned training corpora, and real-time data streams. The framework supports task-aware model training, context-sensitive execution, and closed-loop control driven by real-world feedback. In our demonstration, HeteroHub successfully coordinates multiple embodied AI agents to execute complex tasks, illustrating how a robust data management framework can enable scalable, maintainable, and evolvable embodied AI systems. ---