# Research Papers — 2026-03 · bundle page 144 of 243 > Full-text markdown of papers #7151–7200 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/144 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/143.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/145.md) ### GLEAM: A Multimodal Imaging Dataset and HAMM for Glaucoma Classification Authors: Jiao Wang, Chi Liu, Yiying Zhang, Hongchen Luo, Zhifen Guo, Ying Hu, Ke Xu, Jing Zhou, Hongyan Xu, Ruiting Zhou, Man Tang Published: 2026-03-13 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2603.12800v2 We propose glaucoma lesion evaluation and analysis with multimodal imaging (GLEAM), the first publicly available tri-modal glaucoma dataset comprising scanning laser ophthalmoscopy fundus images, circumpapillary OCT images, and visual field pattern deviation maps, annotated with four disease stages, enabling effective exploitation of multimodal complementary information and facilitating accurate diagnosis and treatment across disease stages. To effectively integrate cross-modal information, we propose hierarchical attentive masked modeling (HAMM) for multimodal glaucoma classification. Our framework employs hierarchical attentive encoders and light decoders to focus cross-modal representation learning on the encoder. --- ### What Makes VLMs Robust? Towards Reconciling Robustness and Accuracy in Vision-Language Models Authors: Sen Nie, Jie Zhang, Zhongqi Wang, Zhaoyang Wei, Shiguang Shan, Xilin Chen Published: 2026-03-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.12799v2 Achieving adversarial robustness in Vision-Language Models (VLMs) inevitably compromises accuracy on clean data, presenting a long-standing and challenging trade-off. In this work, we revisit this trade-off by investigating a fundamental question: What makes VLMs robust? Through a detailed analysis of adversarially fine-tuned models, we examine how robustness mechanisms function internally and how they interact with clean accuracy. Our analysis reveals that adversarial robustness is not uniformly distributed across network depth. Instead, unexpectedly, it is primarily localized within the shallow layers, driven by a low-frequency spectral bias and input-insensitive attention patterns. Meanwhile, updates to the deep layers tend to undermine both clean accuracy and robust generalization. Motivated by these insights, we propose Adversarial Robustness Adaptation (R-Adapt), a simple yet effective framework that freezes all pre-trained weights and introduces minimal, insight-driven adaptations only in the initial layers. This design achieves an exceptional balance between adversarial robustness and clean accuracy. R-Adapt further supports training-free, model-guided, and data-driven paradigms, offering flexible pathways to seamlessly equip standard models with robustness. Extensive evaluations on 18 datasets and diverse tasks demonstrate our state-of-the-art performance under various attacks. Notably, R-Adapt generalizes efficiently to large vision-language models (e.g., LLaVA and Qwen-VL) to enhance their robustness. Our project page is available at https://summu77.github.io/R-Adapt. --- ### Spectral Defense Against Resource-Targeting Attack in 3D Gaussian Splatting Authors: Yang Chen, Yi Yu, Jiaming He, Yueqi Duan, Zheng Zhu, Yap-Peng Tan Published: 2026-03-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.12796v1 Recent advances in 3D Gaussian Splatting (3DGS) deliver high-quality rendering, yet the Gaussian representation exposes a new attack surface, the resource-targeting attack. This attack poisons training images, excessively inducing Gaussian growth to cause resource exhaustion. Although efficiency-oriented methods such as smoothing, thresholding, and pruning have been explored, these spatial-domain strategies operate on visible structures but overlook how stealthy perturbations distort the underlying spectral behaviors of training data. As a result, poisoned inputs introduce abnormal high-frequency amplifications that mislead 3DGS into interpreting noisy patterns as detailed structures, ultimately causing unstable Gaussian overgrowth and degraded scene fidelity. To address this, we propose \textbf{Spectral Defense} in Gaussian and image fields. We first design a 3D frequency filter to selectively prune Gaussians exhibiting abnormally high frequencies. Since natural scenes also contain legitimate high-frequency structures, directly suppressing high frequencies is insufficient, and we further develop a 2D spectral regularization on renderings, distinguishing naturally isotropic frequencies while penalizing anisotropic angular energy to constrain noisy patterns. Experiments show that our defense builds robust, accurate, and secure 3DGS, suppressing overgrowth by up to $5.92\times$, reducing memory by up to $3.66\times$, and improving speed by up to $4.34\times$ under attacks. --- ### SteerRM: Debiasing Reward Models via Sparse Autoencoders Authors: Mengyuan Sun, Zhuohao Yu, Weizheng Gu, Shikun Zhang, Wei Ye Published: 2026-03-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.12795v1 Reward models (RMs) are critical components of alignment pipelines, yet they exhibit biases toward superficial stylistic cues, preferring better-presented responses over semantically superior ones. Existing debiasing methods typically require retraining or architectural modifications, while direct activation suppression degrades performance due to representation entanglement. We propose SteerRM, the first training-free method for debiasing reward models using Sparse Autoencoder (SAE)-based interventions. SteerRM isolates stylistic effects using contrastive paired responses, identifies bias-related SAE features with a strength-stability criterion, and suppresses them at inference time. Across six reward models on RM-Bench, SteerRM improves Hard-split accuracy by 7.3 points on average while preserving overall performance. Results on a Gemma-based reward model and a controlled non-format bias further suggest generalization across RM architectures and bias types. We further find that format-related features are concentrated in shallow layers and transfer across models, revealing shared architecture-level bias encoding patterns. These results show that SAE-based interventions can mitigate reward-model biases without retraining, providing a practical and interpretable solution for alignment pipelines. --- ### A Fractional Fox H-Function Kernel for Support Vector Machines: Robust Classification via Weighted Transmutation Operators Authors: Gustavo Dorrego Published: 2026-03-13 Categories: cs.LG, math.FA arXiv: https://arxiv.org/abs/2603.12794v2 Support Vector Machines (SVMs) rely heavily on the choice of the kernel function to map data into high-dimensional feature spaces. While the Gaussian Radial Basis Function (RBF) is the industry standard, its exponential decay makes it highly susceptible to structural noise and outliers, often leading to severe overfitting in complex datasets. In this paper, we propose a novel class of non-stationary kernels derived from the fundamental solution of the generalized time-space fractional diffusion-wave equation. By leveraging a structure-preserving transmutation method over Weighted Sobolev Spaces, we introduce the Amnesia-Weighted Fox Kernel, an exact analytical Mercer kernel governed by the Fox H-function. Unlike standard kernels, our formulation incorporates an aging weight function (the "Amnesia Effect") to penalize distant outliers and a fractional asymptotic power-law decay to allow for robust, heavy-tailed feature mapping (analogous to Lévy flights). Numerical experiments on both synthetic datasets and real-world high-dimensional radar data (Ionosphere) demonstrate that the proposed Amnesia-Weighted Fox Kernel consistently outperforms the standard Gaussian RBF baseline, reducing the classification error rate by approximately 50\% while maintaining structural robustness against outliers. --- ### Cheers: Decoupling Patch Details from Semantic Representations Enables Unified Multimodal Comprehension and Generation Authors: Yichen Zhang, Da Peng, Zonghao Guo, Zijian Zhang, Xuesong Yang, Tong Sun, Shichu Sun, Yidan Zhang, Yanghao Li, Haiyan Zhao, Wang Xu, Qi Shi et al. Published: 2026-03-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.12793v1 A recent cutting-edge topic in multimodal modeling is to unify visual comprehension and generation within a single model. However, the two tasks demand mismatched decoding regimes and visual representations, making it non-trivial to jointly optimize within a shared feature space. In this work, we present Cheers, a unified multimodal model that decouples patch-level details from semantic representations, thereby stabilizing semantics for multimodal understanding and improving fidelity for image generation via gated detail residuals. Cheers includes three key components: (i) a unified vision tokenizer that encodes and compresses image latent states into semantic tokens for efficient LLM conditioning, (ii) an LLM-based Transformer that unifies autoregressive decoding for text generation and diffusion decoding for image generation, and (iii) a cascaded flow matching head that decodes visual semantics first and then injects semantically gated detail residuals from the vision tokenizer to refine high-frequency content. Experiments on popular benchmarks demonstrate that Cheers matches or surpasses advanced UMMs in both visual understanding and generation. Cheers also achieves 4x token compression, enabling more efficient high-resolution image encoding and generation. Notably, Cheers outperforms the Tar-1.5B on the popular benchmarks GenEval and MMBench, while requiring only 20% of the training cost, indicating effective and efficient (i.e., 4x token compression) unified multimodal modeling. We will release all code and data for future research. --- ### HARMONI: Aligning Human and Scene Priors for Multi-View 4D Reconstruction Authors: Sangmin Kim, Minhyuk Hwang, Geonho Cha, Dongyoon Wee, Jaesik Park Published: 2026-03-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.12789v3 Recent advances in 3D foundation models have enabled joint reconstruction of humans and their surrounding environments. However, combining independently trained human and scene priors often produces misalignment in scale and depth. We observe that the two priors have complementary strengths. The scene prior provides consistent depth but approximate scale, while the human prior provides fixed body scale but less reliable depth. Motivated by this observation, we present HARMONI, a feed-forward framework that reconstructs cameras, scene, and humans with identities from monocular or multi-view video without test-time optimization. We introduce bidirectional anchoring, in which scene depth guides human placement, while human keypoints calibrate the scene scale to match the human body. While most existing approaches target monocular inputs and multi-view methods rely on optimization or re-identification, our approach naturally extends to multiple views. Building on bidirectional anchoring, we introduce a multi-view fusion module that merges per-view estimates, while reducing the influence of unreliable views and visually similar individuals. Experiments show that our framework outperforms previous human-scene methods in global motion and multi-view pose estimation by up to 28% and 64%, while running 28 times faster than optimization-based approaches. Project page: https://nstar1125.github.io/harmoni. --- ### Coherent Human-Scene Reconstruction from Multi-Person Multi-View Video in a Single Pass Authors: Sangmin Kim, Minhyuk Hwang, Geonho Cha, Dongyoon Wee, Jaesik Park Published: 2026-03-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.12789v2 Recent advances in 3D foundation models have led to growing interest in reconstructing humans and their surrounding environments. However, most existing approaches focus on monocular inputs, and extending them to multi-view settings requires additional overhead modules or preprocessed data. To this end, we present CHROMM, a unified framework that jointly estimates cameras, scene point clouds, and human meshes from multi-person multi-view videos without relying on external modules or preprocessing. We integrate strong geometric and human priors from Pi3X and Multi-HMR into a single trainable neural network architecture, and introduce a scale adjustment module to solve the scale discrepancy between humans and the scene. We also introduce a multi-view fusion strategy to aggregate per-view estimates into a single representation at test-time. Finally, we propose a geometry-based multi-person association method, which is more robust than appearance-based approaches. Experiments on EMDB, RICH, EgoHumans, and EgoExo4D show that CHROMM achieves competitive performance in global human motion and multi-view pose estimation while running over 8x faster than prior optimization-based multi-view approaches. Project page: https://nstar1125.github.io/chromm. --- ### Think and Answer ME: Benchmarking and Exploring Multi-Entity Reasoning Grounding in Remote Sensing Authors: Shuchang Lyu, Haiquan Wen, Guangliang Cheng, Meng Li, Zheng Zhou, You Zhou, Dingding Yao, Zhenwei Shi Published: 2026-03-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.12788v2 Recent advances in reasoning language models and reinforcement learning with verifiable rewards have significantly enhanced multi-step reasoning capabilities. This progress motivates the extension of reasoning paradigms to remote sensing visual grounding task. However, existing remote sensing grounding methods remain largely confined to perception-level matching and single-entity formulations, limiting the role of explicit reasoning and inter-entity modeling. To address this challenge, we introduce a new benchmark dataset for Multi-Entity Reasoning Grounding in Remote Sensing (ME-RSRG). Based on ME-RSRG, we reformulate remote sensing grounding as a multi-entity reasoning task and propose an Entity-Aware Reasoning (EAR) framework built upon visual-linguistic foundation models. EAR generates structured reasoning traces and subject-object grounding outputs. It adopts supervised fine-tuning for cold-start initialization and is further optimized via entity-aware reward-driven Group Relative Policy Optimization (GRPO). Extensive experiments on ME-RSRG demonstrate the challenges of multi-entity reasoning and verify the effectiveness of our proposed EAR framework. Our dataset, code, and models will be available at https://github.com/CV-ShuchangLyu/ME-RSRG. --- ### Generalized Recognition of Basic Surgical Actions Enables Skill Assessment and Vision-Language-Model-based Surgical Planning Authors: Mengya Xu, Daiyun Shen, Jie Zhang, Hon Chi Yip, Yujia Gao, Cheng Chen, Dillan Imans, Yonghao Long, Yiru Ye, Yixiao Liu, Rongyun Mai, Kai Chen et al. Published: 2026-03-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.12787v1 Artificial intelligence, imaging, and large language models have the potential to transform surgical practice, training, and automation. Understanding and modeling of basic surgical actions (BSA), the fundamental unit of operation in any surgery, is important to drive the evolution of this field. In this paper, we present a BSA dataset comprising 10 basic actions across 6 surgical specialties with over 11,000 video clips, which is the largest to date. Based on the BSA dataset, we developed a new foundation model that conducts general-purpose recognition of basic actions. Our approach demonstrates robust cross-specialist performance in experiments validated on datasets from different procedural types and various body parts. Furthermore, we demonstrate downstream applications enabled by the BAS foundation model through surgical skill assessment in prostatectomy using domain-specific knowledge, and action planning in cholecystectomy and nephrectomy using large vision-language models. Multinational surgeons' evaluation of the language model's output of the action planning explainable texts demonstrated clinical relevance. These findings indicate that basic surgical actions can be robustly recognized across scenarios, and an accurate BSA understanding model can essentially facilitate complex applications and speed up the realization of surgical superintelligence. --- ### Upper Bounds for Local Learning Coefficients of Three-Layer Neural Networks Authors: Yuki Kurumadani Published: 2026-03-13 Categories: cs.LG, math.ST arXiv: https://arxiv.org/abs/2603.12785v2 Three-layer neural networks are known to form singular learning models, and their Bayesian asymptotic behavior is governed by the learning coefficient, or real log canonical threshold. Although this quantity has been clarified for regular models and for some special singular models, broadly applicable methods for evaluating it in neural networks remain limited. Recently, a formula for the local learning coefficient of semiregular models was proposed, yielding an upper bound on the learning coefficient. However, this formula applies only to nonsingular points in the set of realization parameters and cannot be used at singular points. In particular, for three-layer neural networks, the resulting upper bound has been shown to differ substantially from learning coefficient values already known in some cases. In this paper, we derive a formula for an upper bound on local learning coefficients at a class of singular realization parameters in three-layer neural networks. This formula can be interpreted as a counting rule under budget, demand, and supply constraints. In the non-polynomial real-analytic case, the formula applies in general settings, whereas in the polynomial case it applies under the restriction that the true distribution has no hidden units. In particular, our result covers activation functions such as the swish function and also includes polynomial activation functions under the above restriction, thereby extending previous results to a broader class of activation functions. We further show that, when the input dimension is one, the numerical value given by the right-hand side of our upper-bound formula agrees with the previously known learning coefficient, thereby providing a useful comparison with known exact results. Our result also provides a systematic perspective on how the weight parameters of three-layer neural networks affect the learning coefficient. --- ### The RIGID Framework: Research-Integrated, Generative AI-Mediated Instructional Design Authors: Yerin Kwak, Zachary A. Pardos Published: 2026-03-13 Categories: cs.CY, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2603.12781v1 Instructional Design (ID) often faces challenges in incorporating research-based knowledge and pedagogical best practices. Although educational researchers and government agencies emphasize grounding ID in evidence, integrating research findings into everyday design workflows is often complex, as it requires considering multiple context-specific demands and constraints. To address this persistent gap, this paper explores how research in the learning sciences (LS) can be systematically integrated across ID workflows and how recent advances in generative AI can help operationalize this integration. While ID and LS share a commitment to improving learning experiences through design-oriented approaches in authentic contexts, structured integration between the two fields remains limited, leaving their complementary insights underutilized. We present RIGID (Research-Integrated, Generative AI-Mediated Instructional Design), a unified framework that integrates LS research across ID workflows spanning analysis, design, implementation, and evaluation phases, while leveraging generative AI to mediate this integration at each stage. The RIGID framework provides a systematic approach for enabling research-integrated instructional design that is both operational and context-sensitive, while preserving the central role of human expertise. --- ### Empowering Semantic-Sensitive Underwater Image Enhancement with VLM Authors: Guodong Fan, Shengning Zhou, Genji Yuan, Huiyu Li, Jingchun Zhou, Jinjiang Li Published: 2026-03-13 Categories: cs.CV, cs.AI, eess.IV arXiv: https://arxiv.org/abs/2603.12773v1 In recent years, learning-based underwater image enhancement (UIE) techniques have rapidly evolved. However, distribution shifts between high-quality enhanced outputs and natural images can hinder semantic cue extraction for downstream vision tasks, thereby limiting the adaptability of existing enhancement models. To address this challenge, this work proposes a new learning mechanism that leverages Vision-Language Models (VLMs) to empower UIE models with semantic-sensitive capabilities. To be concrete, our strategy first generates textual descriptions of key objects from a degraded image via VLMs. Subsequently, a text-image alignment model remaps these relevant descriptions back onto the image to produce a spatial semantic guidance map. This map then steers the UIE network through a dual-guidance mechanism, which combines cross-attention and an explicit alignment loss. This forces the network to focus its restorative power on semantic-sensitive regions during image reconstruction, rather than pursuing a globally uniform improvement, thereby ensuring the faithful restoration of key object features. Experiments confirm that when our strategy is applied to different UIE baselines, significantly boosts their performance on perceptual quality metrics as well as enhances their performance on detection and segmentation tasks, validating its effectiveness and adaptability. --- ### PVI: Plug-in Visual Injection for Vision-Language-Action Models Authors: Zezhou Zhang, Songxin Zhang, Xiao Xiong, Junjie Zhang, Zejian Xie, Jingyi Xi, Zunyao Mao, Zan Mao, Zhixin Mai, Zhuoyang Song, Jiaxing Zhang Published: 2026-03-13 Categories: cs.CV, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2603.12772v1 VLA architectures that pair a pretrained VLM with a flow-matching action expert have emerged as a strong paradigm for language-conditioned manipulation. Yet the VLM, optimized for semantic abstraction and typically conditioned on static visual observations, tends to attenuate fine-grained geometric cues and often lacks explicit temporal evidence for the action expert. Prior work mitigates this by injecting auxiliary visual features, but existing approaches either focus on static spatial representations or require substantial architectural modifications to accommodate temporal inputs, leaving temporal information underexplored. We propose Plug-in Visual Injection (PVI), a lightweight, encoder-agnostic module that attaches to a pretrained action expert and injects auxiliary visual representations via zero-initialized residual pathways, preserving pretrained behavior with only single-stage fine-tuning. Using PVI, we obtain consistent gains over the base policy and a range of competitive alternative injection strategies, and our controlled study shows that temporal video features (V-JEPA2) outperform strong static image features (DINOv2), with the largest gains on multi-phase tasks requiring state tracking and coordination. Real-robot experiments on long-horizon bimanual cloth folding further demonstrate the practicality of PVI beyond simulation. --- ### SectEval: Evaluating the Latent Sectarian Preferences of Large Language Models Authors: Aditya Maheshwari, Amit Gajkeshwar, Kaushal Sharma, Vivek Patel Published: 2026-03-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.12768v1 As Large Language Models (LLMs) becomes a popular source for religious knowledge, it is important to know if it treats different groups fairly. This study is the first to measure how LLMs handle the differences between the two main sects of Islam: Sunni and Shia. We present a test called SectEval, available in both English and Hindi, consisting of 88 questions, to check the bias-ness of 15 top LLM models, both proprietary and open-weights. Our results show a major inconsistency based on language. In English, many powerful models DeepSeek-v3 and GPT-4o often favored Shia answers. However, when asked the exact same questions in Hindi, these models switched to favoring Sunni answers. This means a user could get completely different religious advice just by changing languages. We also looked at how models react to location. Advanced models Claude-3.5 changed their answers to match the user's country-giving Shia answers to a user from Iran and Sunni answers to a user from Saudi Arabia. In contrast, smaller models (especially in Hindi) ignored the user's location and stuck to a Sunni viewpoint. These findings show that AI is not neutral; its religious ``truth'' changes depending on the language you speak and the country you claim to be from. The data set is available at https://github.com/secteval/SectEval/ --- ### Catalyst4D: High-Fidelity 3D-to-4D Scene Editing via Dynamic Propagation Authors: Shifeng Chen, Yihui Li, Jun Liao, Hongyu Yang, Di Huang Published: 2026-03-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.12766v2 Recent advances in 3D scene editing using NeRF and 3DGS enable high-quality static scene editing. In contrast, dynamic scene editing remains challenging, as methods that directly extend 2D diffusion models to 4D often produce motion artifacts, temporal flickering, and inconsistent style propagation. We introduce Catalyst4D, a framework that transfers high-quality 3D edits to dynamic 4D Gaussian scenes while maintaining spatial and temporal coherence. At its core, Anchor-based Motion Guidance (AMG) builds a set of structurally stable and spatially representative anchors from both original and edited Gaussians. These anchors serve as robust region-level references, and their correspondences are established via optimal transport to enable consistent deformation propagation without cross-region interference or motion drift. Complementarily, Color Uncertainty-guided Appearance Refinement (CUAR) preserves temporal appearance consistency by estimating per-Gaussian color uncertainty and selectively refining regions prone to occlusion-induced artifacts. Extensive experiments demonstrate that Catalyst4D achieves temporally stable, high-fidelity dynamic scene editing and outperforms existing methods in both visual quality and motion coherence. --- ### SAVA-X: Ego-to-Exo Imitation Error Detection via Scene-Adaptive View Alignment and Bidirectional Cross View Fusion Authors: Xiang Li, Heqian Qiu, Lanxiao Wang, Benliu Qiu, Fanman Meng, Linfeng Xu, Hongliang Li Published: 2026-03-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.12764v1 Error detection is crucial in industrial training, healthcare, and assembly quality control. Most existing work assumes a single-view setting and cannot handle the practical case where a third-person (exo) demonstration is used to assess a first-person (ego) imitation. We formalize Ego$\rightarrow$Exo Imitation Error Detection: given asynchronous, length-mismatched ego and exo videos, the model must localize procedural steps on the ego timeline and decide whether each is erroneous. This setting introduces cross-view domain shift, temporal misalignment, and heavy redundancy. Under a unified protocol, we adapt strong baselines from dense video captioning and temporal action detection and show that they struggle in this cross-view regime. We then propose SAVA-X, an Align-Fuse-Detect framework with (i) view-conditioned adaptive sampling, (ii) scene-adaptive view embeddings, and (iii) bidirectional cross-attention fusion. On the EgoMe benchmark, SAVA-X consistently improves AUPRC and mean tIoU over all baselines, and ablations confirm the complementary benefits of its components. Code is available at https://github.com/jack1ee/SAVAX. --- ### TerraFlow: Multimodal, Multitemporal Representation Learning for Earth Observation Authors: Nazar Puriy, Johannes Jakubik, Benedikt Blumenstiel, Konrad Schindler Published: 2026-03-13 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.12762v1 We propose TerraFlow, a novel approach to multimodal, multitemporal learning for Earth observation. TerraFlow builds on temporal training objectives that enable sequence-aware learning across space, time, and modality, while remaining robust to the variable-length inputs commonly encountered in real-world Earth observation data. Our experiments demonstrate superiority of TerraFlow over state-of-the-art foundation models for Earth observation across all temporal tasks of the GEO-Bench-2 benchmark. We additionally demonstrate that TerraFlow is able to make initial steps towards deep-learning based risk map prediction for natural disasters -- a task on which other state-of-the-art foundation models frequently collapse. TerraFlow outperforms state-of-the-art foundation models by up to 50% in F1 score and 24% in Brier score. --- ### HIFICL: High-Fidelity In-Context Learning for Multimodal Tasks Authors: Xiaoyu Li, Yuhang Liu, Xuanshuo Kang, Zheng Luo, Fangqi Lou, Xiaohua Wu, Zihan Xiong Published: 2026-03-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.12760v4 In-Context Learning (ICL) is a significant paradigm for Large Multimodal Models (LMMs), using a few in-context demonstrations (ICDs) for new task adaptation. However, its performance is sensitive to demonstration configurations and computationally expensive. Mathematically, the influence of these demonstrations can be decomposed into a dynamic mixture of the standard attention output and the context values. Current approximation methods simplify this process by learning a "shift vector". Inspired by the exact decomposition, we introduce High-Fidelity In-Context Learning (HIFICL) to more faithfully model the ICL mechanism. HIFICL consists of three key components: 1) a set of "virtual key-value pairs" to act as a learnable context, 2) a low-rank factorization for stable and regularized training, and 3) a simple end-to-end training objective. From another perspective, this mechanism constitutes a form of context-aware Parameter-Efficient Fine-Tuning (PEFT). Extensive experiments show that HiFICL consistently outperforms existing approximation methods on several multimodal benchmarks. The code is available at https://github.com/bbbandari/HiFICL. --- ### SAP: Segment Any 4K Panorama Authors: Lutao Jiang, Zidong Cao, Weikai Chen, Xu Zheng, Yuanhuiyi Lyu, Zhenyang Li, Zeyu HU, Yingda Yin, Keyang Luo, Runze Zhang, Kai Yan, Shengju Qian et al. Published: 2026-03-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.12759v1 Promptable instance segmentation is widely adopted in embodied and AR systems, yet the performance of foundation models trained on perspective imagery often degrades on 360° panoramas. In this paper, we introduce Segment Any 4K Panorama (SAP), a foundation model for 4K high-resolution panoramic instance-level segmentation. We reformulate panoramic segmentation as fixed-trajectory perspective video segmentation, decomposing a panorama into overlapping perspective patches sampled along a continuous spherical traversal. This memory-aligned reformulation preserves native 4K resolution while restoring the smooth viewpoint transitions required for stable cross-view propagation. To enable large-scale supervision, we synthesize 183,440 4K-resolution panoramic images with instance segmentation labels using the InfiniGen engine. Trained under this trajectory-aligned paradigm, SAP generalizes effectively to real-world 360° images, achieving +17.2 zero-shot mIoU gain over vanilla SAM2 of different sizes on real-world 4K panorama benchmark. --- ### FC-Track: Overlap-Aware Post-Association Correction for Online Multi-Object Tracking Authors: Cheng Ju, Zejing Zhao, Akio Namiki Published: 2026-03-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.12758v1 Reliable multi-object tracking (MOT) is essential for robotic systems operating in complex and dynamic environments. Despite recent advances in detection and association, online MOT methods remain vulnerable to identity switches caused by frequent occlusions and object overlap, where incorrect associations can propagate over time and degrade tracking reliability. We present a lightweight post-association correction framework (FC-Track) for online MOT that explicitly targets overlap-induced mismatches during inference. The proposed method suppresses unreliable appearance updates under high-overlap conditions using an Intersection over Area (IoA)-based filtering strategy, and locally corrects detection-to-tracklet mismatches through appearance similarity comparison within overlapped tracklet pairs. By preventing short-term mismatches from propagating, our framework effectively mitigates long-term identity switches without resorting to global optimization or re-identification. The framework operates online without global optimization or re-identification, making it suitable for real-time robotic applications. We achieve 81.73 MOTA, 82.81 IDF1, and 66.95 HOTA on the MOT17 test set with a running speed of 5.7 FPS, and 77.52 MOTA, 80.90 IDF1, and 65.67 HOTA on the MOT20 test set with a running speed of 0.6 FPS. Specifically, our framework FC-Track produces only 29.55% long-term identity switches, which is substantially lower than existing online trackers. Meanwhile, our framework maintains state-of-the-art performance on the MOT20 benchmark. --- ### AI Model Modulation with Logits Redistribution Authors: Zihan Wang, Zhongkui Ma, Xinguo Feng, Zhiyang Mei, Ethan Ma, Derui Wang, Minhui Xue, Guangdong Bai Published: 2026-03-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.12755v1 Large-scale models are typically adapted to meet the diverse requirements of model owners and users. However, maintaining multiple specialized versions of the model is inefficient. In response, we propose AIM, a novel model modulation paradigm that enables a single model to exhibit diverse behaviors to meet the specific end requirements. AIM enables two key modulation modes: utility and focus modulations. The former provides model owners with dynamic control over output quality to deliver varying utility levels, and the latter offers users precise control to shift model's focused input features. AIM introduces a logits redistribution strategy that operates in a training data-agnostic and retraining-free manner. We establish a formal foundation to ensure AIM's regulation capability, based on the statistical properties of logits ordering via joint probability distributions. Our evaluation confirms AIM's practicality and versatility for Al model modulation, with tasks spanning image classification, semantic segmentation and text generation, and prevalent architectures including ResNet, SegFormer and Llama. --- ### A Method for Learning Large-Scale Computational Construction Grammars from Semantically Annotated Corpora Authors: Paul Van Eecke, Katrien Beuls Published: 2026-03-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.12754v2 We present a method for learning large-scale, broad-coverage construction grammars from corpora of language use. Starting from utterances annotated with constituency structure and semantic frames, the method facilitates the learning of human-interpretable computational construction grammars that capture the intricate relationship between syntactic structures and the semantic relations they express. The resulting grammars consist of networks of tens of thousands of constructions formalised within the Fluid Construction Grammar framework. Not only do these grammars support the frame-semantic analysis of open-domain text, they also house a trove of information about the syntactico-semantic usage patterns present in the data they were learnt from. The method and learnt grammars contribute to the scaling of usage-based, constructionist approaches to language, as they corroborate the scalability of a number of fundamental construction grammar conjectures while also providing a practical instrument for the constructionist study of English argument structure in broad-coverage corpora. --- ### Taming the Long Tail: Efficient Item-wise Sharpness-Aware Minimization for LLM-based Recommender Systems Authors: Jiaming Zhang, Yuyuan Li, Xiaohua Feng, Li Zhang, Longfei Li, Jun Zhou, Chaochao Chen Published: 2026-03-13 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2603.12752v1 Large Language Model-based Recommender Systems (LRSs) have recently emerged as a new paradigm in sequential recommendation by directly adopting LLMs as backbones. While LRSs demonstrate strong knowledge utilization and instruction-following abilities, they have not been systematically studied under the long-standing long-tail problem. In this paper, we conduct an empirical study and reveal that LRSs face two distinct types of long-tail: i) prior long-tail, inherited implicitly from pretraining corpora, and ii) data long-tail, originating from skewed recommendation datasets. Our analysis shows that both contribute to the performance disparity between head and tail items, with the intersection of the two heads exhibiting an even stronger head effect. Nevertheless, the overall performance distribution in LRSs, especially on the tail, remains dominated by the data long-tail. To address this challenge, we propose Efficient Item-wise Sharpness-Aware Minimization (EISAM), a novel optimization framework that improves tail-item performance by adaptively regularizing the loss landscape at the item level. EISAM introduces an efficient penalty design that captures fine-grained item-specific sharpness while maintaining computational scalability for LLMs. In addition, we derive a generalization bound for EISAM. Our theoretical analysis shows that the bound decreases at a faster rate under our item-wise regularization, offering theoretical support for its effectiveness. Extensive experiments on three real-world datasets demonstrate that EISAM significantly boosts tail-item recommendation performance while preserving overall quality, establishing the first systematic solution to the long-tail problem in LRSs. --- ### Show, Don't Tell: Detecting Novel Objects by Watching Human Videos Authors: James Akl, Jose Nicolas Avendano Arbelaez, James Barabas, Jennifer L. Barry, Kalie Ching, Noam Eshed, Jiahui Fu, Michel Hidalgo, Andrew Hoelscher, Tushar Kusnur, Andrew Messing, Zachary Nagler et al. Published: 2026-03-13 Categories: cs.CV, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2603.12751v1 How can a robot quickly identify and recognize new objects shown to it during a human demonstration? Existing closed-set object detectors frequently fail at this because the objects are out-of-distribution. While open-set detectors (e.g., VLMs) sometimes succeed, they often require expensive and tedious human-in-the-loop prompt engineering to uniquely recognize novel object instances. In this paper, we present a self-supervised system that eliminates the need for tedious language descriptions and expensive prompt engineering by training a bespoke object detector on an automatically created dataset, supervised by the human demonstration itself. In our approach, "Show, Don't Tell," we show the detector the specific objects of interest during the demonstration, rather than telling the detector about these objects via complex language descriptions. By bypassing language altogether, this paradigm enables us to quickly train bespoke detectors tailored to the relevant objects observed in human task demonstrations. We develop an integrated on-robot system to deploy our "Show, Don't Tell" paradigm of automatic dataset creation and novel object-detection on a real-world robot. Empirical results demonstrate that our pipeline significantly outperforms state-of-the-art detection and recognition methods for manipulated objects, leading to improved task completion for the robot. --- ### SLICE: Semantic Latent Injection via Compartmentalized Embedding for Image Watermarking Authors: Zheng Gao, Yifan Yang, Xiaoyu Li, Xiaoyan Feng, Haoran Fan, Yang Song, Jiaojiao Jiang Published: 2026-03-13 Categories: cs.CV, cs.CR, cs.LG arXiv: https://arxiv.org/abs/2603.12749v1 Watermarking the initial noise of diffusion models has emerged as a promising approach for image provenance, but content-independent noise patterns can be forged via inversion and regeneration attacks. Recent semantic-aware watermarking methods improve robustness by conditioning verification on image semantics. However, their reliance on a single global semantic binding makes them vulnerable to localized but globally coherent semantic edits. To address this limitation and provide a trustworthy semantic-aware watermark, we propose $\underline{\textbf{S}}$emantic $\underline{\textbf{L}}$atent $\underline{\textbf{I}}$njection via $\underline{\textbf{C}}$ompartmentalized $\underline{\textbf{E}}$mbedding ($\textbf{SLICE}$). Our framework decouples image semantics into four semantic factors (subject, environment, action, and detail) and precisely anchors them to distinct regions in the initial Gaussian noise. This fine-grained semantic binding enables advanced watermark verification where semantic tampering is detectable and localizable. We theoretically justify why SLICE enables robust and reliable tamper localization and provides statistical guarantees on false-accept rates. Experimental results demonstrate that SLICE significantly outperforms existing baselines against advanced semantic-guided regeneration attacks, substantially reducing attack success while preserving image quality and semantic fidelity. Overall, SLICE offers a practical, training-free provenance solution that is both fine-grained in diagnosis and robust to realistic adversarial manipulations. --- ### Thinking in Dynamics: How Multimodal Large Language Models Perceive, Track, and Reason Dynamics in Physical 4D World Authors: Yuzhi Huang, Kairun Wen, Rongxin Gao, Dongxuan Liu, Yibin Lou, Jie Wu, Jing Xu, Jian Zhang, Zheng Yang, Yunlong Lin, Chenxin Li, Panwang Pan et al. Published: 2026-03-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.12746v1 Humans inhabit a physical 4D world where geometric structure and semantic content evolve over time, constituting a dynamic 4D reality (spatial with temporal dimension). While current Multimodal Large Language Models (MLLMs) excel in static visual understanding, can they also be adept at "thinking in dynamics", i.e., perceive, track and reason about spatio-temporal dynamics in evolving scenes? To systematically assess their spatio-temporal reasoning and localized dynamics perception capabilities, we introduce Dyn-Bench, a large-scale benchmark built from diverse real-world and synthetic video datasets, enabling robust and scalable evaluation of spatio-temporal understanding. Through multi-stage filtering from massive 2D and 4D data sources, Dyn-Bench provides a high-quality collection of dynamic scenes, comprising 1k videos, 7k visual question answering (VQA) pairs, and 3k dynamic object grounding pairs. We probe general, spatial and region-level MLLMs to express how they think in dynamics both linguistically and visually, and find that existing models cannot simultaneously maintain strong performance in both spatio-temporal reasoning and dynamic object grounding, often producing inconsistent interpretations of motion and interaction. Notably, conventional prompting strategies (e.g., chain-of-thought or caption-based hints) provide limited improvement, whereas structured integration approaches, including Mask-Guided Fusion and Spatio-Temporal Textual Cognitive Map (ST-TCM), significantly enhance MLLMs' dynamics perception and spatio-temporal reasoning in the physical 4D world. Code and benchmark are available at https://dyn-bench.github.io/. --- ### TaoBench: Do Automated Theorem Prover LLMs Generalize Beyond MathLib? Authors: Alexander K Taylor, Junyi Zhang, Ethan Ji, Vigyan Sahai, Haikang Deng, Yuanzhou Chen, Yifan Yuan, Di Wu, Jia-Chen Gu, Kai-Wei Chang, Nanyun Peng, Amit Sahai et al. Published: 2026-03-13 Categories: cs.LG, cs.AI, cs.LO arXiv: https://arxiv.org/abs/2603.12744v1 Automated theorem proving (ATP) benchmarks largely consist of problems formalized in MathLib, so current ATP training and evaluation are heavily biased toward MathLib's definitional framework. However, frontier mathematics is often exploratory and prototype-heavy, relying on bespoke constructions that deviate from standard libraries. In this work, we evaluate the robustness of current ATP systems when applied to a novel definitional framework, specifically examining the performance gap between standard library problems and bespoke mathematical constructions. We introduce TaoBench, an undergraduate-level benchmark derived from Terence Tao's Analysis I, which formalizes analysis by constructing core mathematical concepts from scratch, without relying on standard Mathlib definitions, as well as by mixing from-scratch and MathLib constructions. For fair evaluation, we build an agentic pipeline that automatically extracts a compilable, self-contained local environment for each problem. To isolate the effect of definitional frameworks, we additionally translate every problem into a mathematically equivalent Mathlib formulation, yielding paired TaoBench-Mathlib statements for direct comparison. While state-of-the-art ATP models perform capably within the MathLib framework, performance drops by an average of roughly 26% on the definitionally equivalent Tao formulation. This indicates that the main bottleneck is limited generalization across definitional frameworks rather than task difficulty. TaoBench thus highlights a gap between benchmark performance and applicability, and provides a concrete foundation for developing and testing provers better aligned with research mathematics. --- ### MoKus: Leveraging Cross-Modal Knowledge Transfer for Knowledge-Aware Concept Customization Authors: Chenyang Zhu, Hongxiang Li, Xiu Li, Long Chen Published: 2026-03-13 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.12743v1 Concept customization typically binds rare tokens to a target concept. Unfortunately, these approaches often suffer from unstable performance as the pretraining data seldom contains these rare tokens. Meanwhile, these rare tokens fail to convey the inherent knowledge of the target concept. Consequently, we introduce Knowledge-aware Concept Customization, a novel task aiming at binding diverse textual knowledge to target visual concepts. This task requires the model to identify the knowledge within the text prompt to perform high-fidelity customized generation. Meanwhile, the model should efficiently bind all the textual knowledge to the target concept. Therefore, we propose MoKus, a novel framework for knowledge-aware concept customization. Our framework relies on a key observation: cross-modal knowledge transfer, where modifying knowledge within the text modality naturally transfers to the visual modality during generation. Inspired by this observation, MoKus contains two stages: (1) In visual concept learning, we first learn the anchor representation to store the visual information of the target concept. (2) In textual knowledge updating, we update the answer for the knowledge queries to the anchor representation, enabling high-fidelity customized generation. To further comprehensively evaluate our proposed MoKus on the new task, we introduce the first benchmark for knowledge-aware concept customization: KnowCusBench. Extensive evaluations have demonstrated that MoKus outperforms state-of-the-art methods. Moreover, the cross-model knowledge transfer allows MoKus to be easily extended to other knowledge-aware applications like virtual concept creation and concept erasure. We also demonstrate the capability of our method to achieve improvements on world knowledge benchmarks. --- ### ToolTree: Efficient LLM Agent Tool Planning via Dual-Feedback Monte Carlo Tree Search and Bidirectional Pruning Authors: Shuo Yang, Soyeon Caren Han, Yihao Ding, Shuhe Wang, Eduard Hoy Published: 2026-03-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.12740v1 Large Language Model (LLM) agents are increasingly applied to complex, multi-step tasks that require interaction with diverse external tools across various domains. However, current LLM agent tool planning methods typically rely on greedy, reactive tool selection strategies that lack foresight and fail to account for inter-tool dependencies. In this paper, we present ToolTree, a novel Monte Carlo tree search-inspired planning paradigm for tool planning. ToolTree explores possible tool usage trajectories using a dual-stage LLM evaluation and bidirectional pruning mechanism that enables the agent to make informed, adaptive decisions over extended tool-use sequences while pruning less promising branches before and after the tool execution. Empirical evaluations across both open-set and closed-set tool planning tasks on 4 benchmarks demonstrate that ToolTree consistently improves performance while keeping the highest efficiency, achieving an average gain of around 10\% compared to the state-of-the-art planning paradigm. --- ### SRAM-Based Compute-in-Memory Accelerator for Linear-decay Spiking Neural Networks Authors: Hongyang Shang, Shuai Dong, Yahan Yang, Junyi Yang, Peng Zhou, Arindam Basu Published: 2026-03-13 Categories: cs.NE, cs.AI, cs.AR arXiv: https://arxiv.org/abs/2603.12739v1 Spiking Neural Networks (SNNs) have emerged as a biologically inspired alternative to conventional deep networks, offering event-driven and energy-efficient computation. However, their throughput remains constrained by the serial update of neuron membrane states. While many hardware accelerators and Compute-in-Memory (CIM) architectures efficiently parallelize the synaptic operation (W x I) achieving O(1) complexity for matrix-vector multiplication, the subsequent state update step still requires O(N) time to refresh all neuron membrane potentials. This mismatch makes state update the dominant latency and energy bottleneck in SNN inference. To address this challenge, we propose an SRAM-based CIM for SNN with Linear Decay Leaky Integrate-and-Fire (LD-LIF) Neuron that co-optimizes algorithm and hardware. At the algorithmic level, we replace the conventional exponential membrane decay with a linear decay approximation, converting costly multiplications into simple additions while accuracy drops only around 1%. At the architectural level, we introduce an in-memory parallel update scheme that performs in-place decay directly within the SRAM array, eliminating the need for global sequential updates. Evaluated on benchmark SNN workloads, the proposed method achieves a 1.1 x to 16.7 x reduction of SOP energy consumption, while providing 15.9 x to 69 x more energy efficiency, with negligible accuracy loss relative to original decay models. This work highlights that beyond accelerating the (W x I) computation, optimizing state-update dynamics within CIM architectures is essential for scalable, low-power, and real-time neuromorphic processing. --- ### VecMol: Vector-Field Representations for 3D Molecule Generation Authors: Yuchen Hua, Xingang Peng, Jianzhu Ma, Muhan Zhang Published: 2026-03-13 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2603.12734v1 Generative modeling of three-dimensional (3D) molecules is a fundamental yet challenging problem in drug discovery and materials science. Existing approaches typically represent molecules as 3D graphs and co-generate discrete atom types with continuous atomic coordinates, leading to intrinsic learning difficulties such as heterogeneous modality entanglement and geometry-chemistry coherence constraints. We propose VecMol, a paradigm-shifting framework that reimagines molecular representation by modeling 3D molecules as continuous vector fields over Euclidean space, where vectors point toward nearby atoms and implicitly encode molecular structure. The vector field is parameterized by a neural field and generated using a latent diffusion model, avoiding explicit graph generation and decoupling structure learning from discrete atom instantiation. Experiments on the QM9 and GEOM-Drugs benchmarks validate the feasibility of this novel approach, suggesting vector-field-based representations as a promising new direction for 3D molecular generation. --- ### On Using Machine Learning to Early Detect Catastrophic Failures in Marine Diesel Engines Authors: Francesco Maione, Paolo Lino, Giuseppe Giannino, Guido Maione Published: 2026-03-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.12733v1 Catastrophic failures of marine engines imply severe loss of functionality and destroy or damage the systems irreversibly. Being sudden and often unpredictable events, they pose a severe threat to navigation, crew, and passengers. The abrupt nature makes early detection the only effective countermeasure. However, research has concentrated on modeling the gradual degradation of components, with limited attention to sudden and anomalous phenomena. This work proposes a new method for early detection of catastrophic failures. Based on real data from a failed engine, the approach evaluates the derivatives of the deviation between actual sensor readings and expected values of engine variables. Predictions are obtained by a Random Forest, which is the most suitable Machine Learning algorithm among the tested ones. Traditional methods focus on deviations of monitored signals, whereas the proposed approach employs the derivatives of the deviations to provide earlier indications of abnormal dynamics, and to alert that a rapid and dangerous event is breaking out within the system. The method allows the detection of anomalies before measurements reach critical thresholds and alarms are triggered, which is the common method in industry. Consequently, operators can be warned in advance and shut down the engine, then prevent damage and unexpected power loss. Moreover, they have the time to safely change the ship route and avoid potential obstacles. Simulation results conf irm the effectiveness of the proposed approach in anticipating occurrence of catastrophic failures. Validation on real-world data further reinforces the robustness and practical applicability of the method. It is worth noting that data acquisition to train the predictive algorithm is not a problem, since a Deep Learning-based data augmentation procedure is used. --- ### Anchored Alignment: Preventing Positional Collapse in Multimodal Recommender Systems Authors: Yonghun Jeong, David Yoon Suk Kang, Yeon-Chang Lee Published: 2026-03-13 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2603.12726v1 Multimodal recommender systems (MMRS) leverage images, text, and interaction signals to enrich item representations. However, recent alignment based MMRSs that enforce a unified embedding space often blur modality specific structures and exacerbate ID dominance. Therefore, we propose AnchorRec, a multimodal recommendation framework that performs indirect, anchor based alignment in a lightweight projection domain. By decoupling alignment from representation learning, AnchorRec preserves each modality's native structure while maintaining cross modal consistency and avoiding positional collapse. Experiments on four Amazon datasets show that AnchorRec achieves competitive top N recommendation accuracy, while qualitative analyses demonstrate improved multimodal expressiveness and coherence. The codebase of AnchorRec is available at https://github.com/hun9008/AnchorRec. --- ### Graph In-Context Operator Networks for Generalizable Spatiotemporal Prediction Authors: Chenghan Wu, Zongmin Yu, Boai Sun, Liu Yang Published: 2026-03-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.12725v3 In-context operator learning enables neural networks to infer solution operators from contextual examples without weight updates. While prior work has demonstrated the effectiveness of this paradigm in leveraging vast datasets, a systematic comparison against single-operator learning using identical training data has been absent. We address this gap through controlled experiments comparing in-context operator learning against classical operator learning (single-operator models trained without contextual examples), under the same training steps and dataset. To enable this investigation on real-world spatiotemporal systems, we propose GICON (Graph In-Context Operator Network), combining graph message passing for geometric generalization with example-aware positional encoding for cardinality generalization. Experiments on air quality prediction across two Chinese regions show that in-context operator learning outperforms classical operator learning on complex tasks, generalizing across spatial domains and scaling robustly from few training examples to 100 at inference. --- ### SciDesignBench: Benchmarking and Improving Language Models for Scientific Inverse Design Authors: David van Dijk, Ivan Vrkic Published: 2026-03-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.12724v1 Many of the most important problems in science and engineering are inverse problems: given a desired outcome, find a design that achieves it. Evaluating whether a candidate meets the spec is often routine; a binding energy can be computed, a reactor yield simulated, a pharmacokinetic profile predicted. But searching a combinatorial design space for inputs that satisfy those targets is fundamentally harder. We introduce SciDesignBench, a benchmark of 520 simulator-grounded tasks across 14 scientific domains and five settings spanning single-shot design, short-horizon feedback, long-horizon refinement, and seed-design optimization. On the 10-domain shared-core subset, the best zero-shot model reaches only 29.0% success despite substantially higher parse rates. Simulator feedback helps, but the leaderboard changes with horizon: Sonnet 4.5 is strongest in one-turn de novo design, whereas Opus 4.6 is strongest after 20 turns of simulator-grounded refinement. Providing a starting seed design reshuffles the leaderboard again, demonstrating that constrained modification requires a fundamentally different capability from unconstrained de novo generation. We then introduce RLSF, a simulator-feedback training recipe. An RLSF-tuned 8B model raises single-turn success rates by 8-17 percentage points across three domains. Together, these results position simulator-grounded inverse design as both a benchmark for scientific reasoning and a practical substrate for amortizing expensive test-time compute into model weights. --- ### CognitionCapturerPro: Towards High-Fidelity Visual Decoding from EEG/MEG via Multi-modal Information and Asymmetric Alignment Authors: Kaifan Zhang, Lihuo He, Junjie Ke, Yuqi Ji, Lukun Wu, Lizi Wang, Xinbo Gao Published: 2026-03-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.12722v1 Visual stimuli reconstruction from EEG remains challenging due to fidelity loss and representation shift. We propose CognitionCapturerPro, an enhanced framework that integrates EEG with multi-modal priors (images, text, depth, and edges) via collaborative training. Our core contributions include an uncertainty-weighted similarity scoring mechanism to quantify modality-specific fidelity and a fusion encoder for integrating shared representations. By employing a simplified alignment module and a pre-trained diffusion model, our method significantly outperforms the original CognitionCapturer on the THINGS-EEG dataset, improving Top-1 and Top-5 retrieval accuracy by 25.9% and 10.6%, respectively. Code is available at: https://github.com/XiaoZhangYES/CognitionCapturerPro. --- ### CMHANet: A Cross-Modal Hybrid Attention Network for Point Cloud Registration Authors: Dongxu Zhang, Yingsen Wang, Yiding Sun, Haoran Xu, Peilin Fan, Jihua Zhu Published: 2026-03-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.12721v1 Robust point cloud registration is a fundamental task in 3D computer vision and geometric deep learning, essential for applications such as large-scale 3D reconstruction, augmented reality, and scene understanding. However, the performance of established learning-based methods often degrades in complex, real world scenarios characterized by incomplete data, sensor noise, and low overlap regions. To address these limitations, we propose CMHANet, a novel Cross-Modal Hybrid Attention Network. Our method integrates the fusion of rich contextual information from 2D images with the geometric detail of 3D point clouds, yielding a comprehensive and resilient feature representation. Furthermore, we introduce an innovative optimization function based on contrastive learning, which enforces geometric consistency and significantly improves the model's robustness to noise and partial observations. We evaluated CMHANet on the 3DMatch and the challenging 3DLoMatch datasets. \rev{Additionally, zero-shot evaluations on the TUM RGB-D SLAM dataset verify the model's generalization capability to unseen domains.} The experimental results demonstrate that our method achieves substantial improvements in both registration accuracy and overall robustness, outperforming current techniques. We also release our code in \href{https://github.com/DongXu-Zhang/CMHANet}{https://github.com/DongXu-Zhang/CMHANet}. --- ### IGASA: Integrated Geometry-Aware and Skip-Attention Modules for Enhanced Point Cloud Registration Authors: Dongxu Zhang, Jihua Zhu, Shiqi Li, Wenbiao Yan, Haoran Xu, Peilin Fan, Huimin Lu Published: 2026-03-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.12719v1 Point cloud registration (PCR) is a fundamental task in 3D vision and provides essential support for applications such as autonomous driving, robotics, and environmental modeling. Despite its widespread use, existing methods often fail when facing real-world challenges like heavy noise, significant occlusions, and large-scale transformations. These limitations frequently result in compromised registration accuracy and insufficient robustness in complex environments. In this paper, we propose IGASA as a novel registration framework constructed upon a Hierarchical Pyramid Architecture (HPA) designed for robust multi-scale feature extraction and fusion. The framework integrates two pivotal components consisting of the Hierarchical Cross-Layer Attention (HCLA) module and the Iterative Geometry-Aware Refinement (IGAR) module. The HCLA module utilizes skip attention mechanisms to align multi-resolution features and enhance local geometric consistency. Simultaneously, the IGAR module is designed for the fine matching phase by leveraging reliable correspondences established during coarse matching. This synergistic integration within the architecture allows IGASA to adapt effectively to diverse point cloud structures and intricate transformations. We evaluate the performance of IGASA on four widely recognized benchmark datasets including 3D(Lo)Match, KITTI, and nuScenes. Our extensive experiments consistently demonstrate that IGASA significantly surpasses state-of-the-art methods and achieves notable improvements in registration accuracy. This work provides a robust foundation for advancing point cloud registration techniques while offering valuable insights for practical 3D vision applications. The code for IGASA is available in \href{https://github.com/DongXu-Zhang/IGASA}{https://github.com/DongXu-Zhang/IGASA}. --- ### The COTe score: A decomposable framework for evaluating Document Layout Analysis models Authors: Jonathan Bourne, Mwiza Simbeye, Ishtar Govia Published: 2026-03-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.12718v2 Document Layout analysis (DLA), is the process by which a page is parsed into meaningful elements, often using machine learning models. Typically, the quality of a model is judged using general object detection metrics such as IoU, F1 or mAP. However, these metrics are designed for images that are 2D projections of 3D space, not for the natively 2D imagery of printed media. This discrepancy can result in misleading or uninformative interpretation of model performance by the metrics. To encourage more robust, comparable, and nuanced DLA, we introduce: The Structural Semantic Unit (SSU) a relational labelling approach that shifts the focus from the physical to the semantic structure of the content; and the Coverage, Overlap, Trespass, and Excess (COTe) score, a decomposable metric for measuring page parsing quality. We demonstrate the value of these methods through case studies and by evaluating 5 common DLA models on 3 DLA datasets. We show that the COTe score is more informative than traditional metrics and reveals distinct failure modes across models, such as breaching semantic boundaries or repeatedly parsing the same region. In addition, the COTe score reduces the interpretation-performance gap by up to 76% relative to the F1. Notably, we find that the COTe's granularity robustness largely holds even without explicit SSU labelling, lowering the barriers to entry for using the system. Finally, we release an SSU labelled dataset and a Python library for applying COTe in DLA projects. --- ### Altered Thoughts, Altered Actions: Reasoning Chain as Control Surface for a Vision-Language-Action Policy Authors: Tuan Duong Trinh, Basim Azam, Mohammed Ishaq Ansari, Mohammed Yaqoob Ansari, Naveed Akhtar Published: 2026-03-13 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.12717v2 Vision-language-action policies map camera images and natural-language instructions to a robot's motor actions. Some of these policies are designed to reason in text before acting, generating a reasoning chain and decoding actions conditioned on that chain. The works introducing this design offer the reasoning chain as an oversight interface: text a person can read and edit to correct the policy. What an edited reasoning chain does to the policy's motor actions, whether it repairs them or corrupts them, remains an open question. We measure both directions, repair and corruption, with our deterministic entity swap applied to the instruction the policy receives and to the reasoning chain it generates. A forty-task observed backdrop across all four LIBERO simulation suites reveals that the cost of corrupting the reasoning chain concentrates where language alone determines the goal. There, on LIBERO-Goal, we run the decisive counterfactual intervention with DeepThinkVLA, chosen because its reasoning chain is exposed as plain text. The policy receives a corrupted instruction, paired with the reasoning chain it generates when that instruction is clean. This counterfactually correct reasoning chain recovers 47.8 pp of the lost success, our pre-registered confirmatory test. Had the chain merely restated what the camera image already determines, the injection could have changed nothing. Instead, all 10 tasks move in the predicted direction. The reasoning chain is therefore a working control surface: text written into it steers the robot, repairing behaviour when the text is right and corrupting it when the text is wrong. Whether to expose such a control surface is a real deployment tradeoff, and it can now be measured. --- ### Altered Thoughts, Altered Actions: Probing Chain-of-Thought Vulnerabilities in VLA Robotic Manipulation Authors: Tuan Duong Trinh, Naveed Akhtar, Basim Azam Published: 2026-03-13 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.12717v1 Recent Vision-Language-Action (VLA) models increasingly adopt chain-of-thought (CoT) reasoning, generating a natural-language plan before decoding motor commands. This internal text channel between the reasoning module and the action decoder has received no adversarial scrutiny. We ask: which properties of this intermediate plan does the action decoder actually rely on, and can targeted corruption of the reasoning trace alone -- with all inputs left intact -- degrade a robot's physical task performance? We design a taxonomy of seven text corruptions organized into three attacker tiers (blind noise, mechanical-semantic, and LLM-adaptive) and apply them to a state-of-the-art reasoning VLA across 40 LIBERO tabletop manipulation tasks. Our results reveal a striking asymmetry: substituting object names in the reasoning trace reduces overall success rate by 8.3~percentage points (pp) -- reaching $-$19.3~pp on goal-conditioned tasks and $-$45~pp on individual tasks -- whereas sentence reordering, spatial-direction reversal, token noise, and even a 70B-parameter LLM crafting plausible-but-wrong plans all have negligible impact (within $\pm$4~pp). This asymmetry indicates that the action decoder depends on entity-reference integrity rather than reasoning quality or sequential structure. Notably, a sophisticated LLM-based attacker underperforms simple mechanical object-name substitution, because preserving plausibility inadvertently retains the entity-grounding structure the decoder needs. A cross-architecture control using a non-reasoning VLA confirms the vulnerability is exclusive to reasoning-augmented models, while instruction-level attacks degrade both architectures -- establishing that the internal reasoning trace is a distinct and stealthy threat vector invisible to input-validation defenses. --- ### UNIStainNet: Foundation-Model-Guided Virtual Staining of H&E to IHC Authors: Jillur Rahman Saurav, Thuong Le Hoai Pham, Pritam Mukherjee, Paul Yi, Brent A. Orr, Jacob M. Luber Published: 2026-03-13 Categories: cs.CV, cs.LG, eess.IV arXiv: https://arxiv.org/abs/2603.12716v1 Virtual immunohistochemistry (IHC) staining from hematoxylin and eosin (H&E) images can accelerate diagnostics by providing preliminary molecular insight directly from routine sections, reducing the need for repeat sectioning when tissue is limited. Existing methods improve realism through contrastive objectives, prototype matching, or domain alignment, yet the generator itself receives no direct guidance from pathology foundation models. We present UNIStainNet, a SPADE-UNet conditioned on dense spatial tokens from a frozen pathology foundation model (UNI), providing tissue-level semantic guidance for stain translation. A misalignment-aware loss suite preserves stain quantification accuracy, and learned stain embeddings enable a single model to serve multiple IHC markers simultaneously. On MIST, UNIStainNet achieves state-of-the-art distributional metrics on all four stains (HER2, Ki67, ER, PR) from a single unified model, where prior methods typically train separate per-stain models. On BCI, it also achieves the best distributional metrics. A tissue-type stratified failure analysis reveals that remaining errors are systematic, concentrating in non-tumor tissue. Code is available at https://github.com/facevoid/UNIStainNet. --- ### Deep Learning Based Estimation of Blood Glucose Levels from Multidirectional Scleral Blood Vessel Imaging Authors: Muhammad Ahmed Khan, Manqiang Peng, Ding Lin, Saif Ur Rehman Khan Published: 2026-03-13 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2603.12715v1 Regular monitoring of glycemic status is essential for diabetes management, yet conventional blood-based testing can be burdensome for frequent assessment. The sclera contains superficial microvasculature that may exhibit diabetes related alterations and is readily visible on the ocular surface. We propose ScleraGluNet, a multiview deep-learning framework for three-class metabolic status classification (normal, controlled diabetes, and high-glucose diabetes) and continuous fasting plasma glucose (FPG) estimation from multidirectional scleral vessel images. The dataset comprised 445 participants (150/140/155) and 2,225 anterior-segment images acquired from five gaze directions per participant. After vascular enhancement, features were extracted using parallel convolutional branches, refined with Manta Ray Foraging Optimization (MRFO), and fused via transformer-based cross-view attention. Performance was evaluated using subject-wise five-fold cross-validation, with all images from each participant assigned to the same fold. ScleraGluNet achieved 93.8% overall accuracy, with one-vs-rest AUCs of 0.971,0.956, and 0.982 for normal, controlled diabetes, and high-glucose diabetes, respectively. For FPG estimation, the model achieved MAE = 6.42 mg/dL and RMSE = 7.91 mg/dL, with strong correlation to laboratory measurements (r = 0.983; R2 = 0.966). Bland Altman analysis showed a mean bias of +1.45 mg/dL with 95% limits of agreement from -8.33 to +11.23$ mg/dL. These results support multidirectional scleral vessel imaging with multiview learning as a promising noninvasive approach for glycemic assessment, warranting multicenter validation before clinical deployment. --- ### Design-Specification Tiling for ICL-based CAD Code Generation Authors: Yali Du, San-Zhuo Xi, Hui Sun, Ming Li Published: 2026-03-13 Categories: cs.SE, cs.LG arXiv: https://arxiv.org/abs/2603.12712v2 Large language models~(LLMs) have demonstrated remarkable capabilities in code generation, yet their performance remains limited on domain-specific tasks such as Computer-Aided Design~(CAD) code generation, largely due to the scarcity of high-quality training data. In-Context Learning~(ICL) provides a training-free alternative by prompting LLMs with task-specific exemplars, but its effectiveness critically depends on how exemplars are selected. Existing selection strategies mainly rely on similarity or point-wise diversity, often overlooking the compositional nature of CAD design specifications, where a query may involve multiple functional requirements, geometric constraints, and design primitives. As a result, selected exemplars can be individually relevant but collectively redundant, providing insufficient coverage for complex design requirements. In this work, we propose \emph{knowledge sufficiency} as a principled objective for exemplar selection, aiming to select a compact set of exemplars that maximally satisfies the requirements contained in a target design specification. To instantiate this objective, we introduce \emph{Design-Specification Tiling~(DST)}, which estimates knowledge sufficiency through a surrogate tiling ratio by decomposing design specifications into multi-granular components and measuring the proportion of query components covered by selected exemplars. We further show that optimizing this objective can be formulated as a submodular maximization problem, and develop a polynomial-time greedy algorithm tailored to this setting with a $(1-1/e)$-approximation guarantee. Extensive experiments across multiple LLMs demonstrate that DST substantially improves CAD code generation quality and consistently outperforms existing ICL exemplar selection strategies, highlighting the importance of requirement-level knowledge coverage for domain-specific code generation. --- ### Text-Phase Synergy Network with Dual Priors for Unsupervised Cross-Domain Image Retrieval Authors: Jing Yang, Hui Xue, Shipeng Zhu, Pengfei Fang Published: 2026-03-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.12711v2 This paper studies unsupervised cross-domain image retrieval (UCDIR), which aims to retrieve images of the same category across different domains without relying on labeled data. Existing methods typically utilize pseudo-labels, derived from clustering algorithms, as supervisory signals for intra-domain representation learning and cross-domain feature alignment. However, these discrete pseudo-labels often fail to provide accurate and comprehensive semantic guidance. Moreover, the alignment process frequently overlooks the entanglement between domain-specific and semantic information, leading to semantic degradation in the learned representations and ultimately impairing retrieval performance. This paper addresses the limitations by proposing a Text-Phase Synergy Network with Dual Priors(TPSNet). Specifically, we first employ CLIP to generate a set of class-specific prompts per domain, termed as domain prompt, serving as a text prior that offers more precise semantic supervision. In parallel, we further introduce a phase prior, represented by domain-invariant phase features, which is integrated into the original image representations to bridge the domain distribution gaps while preserving semantic integrity. Leveraging the synergy of these dual priors, TPSNet significantly outperforms state-of-the-art methods on UCDIR benchmarks. --- ### AI Planning Framework for LLM-Based Web Agents Authors: Orit Shahnovsky, Rotem Dror Published: 2026-03-13 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.12710v1 Developing autonomous agents for web-based tasks is a core challenge in AI. While Large Language Model (LLM) agents can interpret complex user requests, they often operate as black boxes, making it difficult to diagnose why they fail or how they plan. This paper addresses this gap by formally treating web tasks as sequential decision-making processes. We introduce a taxonomy that maps modern agent architectures to traditional planning paradigms: Step-by-Step agents to Breadth-First Search (BFS), Tree Search agents to Best-First Tree Search, and Full-Plan-in-Advance agents to Depth-First Search (DFS). This framework allows for a principled diagnosis of system failures like context drift and incoherent task decomposition. To evaluate these behaviors, we propose five novel evaluation metrics that assess trajectory quality beyond simple success rates. We support this analysis with a new dataset of 794 human-labeled trajectories from the WebArena benchmark. Finally, we validate our evaluation framework by comparing a baseline Step-by-Step agent against a novel Full-Plan-in-Advance implementation. Our results reveal that while the Step-by-Step agent aligns more closely with human gold trajectories (38% overall success), the Full-Plan-in-Advance agent excels in technical measures such as element accuracy (89%), demonstrating the necessity of our proposed metrics for selecting appropriate agent architectures based on specific application constraints. --- ### HFP-SAM: Hierarchical Frequency Prompted SAM for Efficient Marine Animal Segmentation Authors: Pingping Zhang, Tianyu Yan, Yuhao Wang, Yang Liu, Tongdan Tang, Yili Ma, Long Lv, Feng Tian, Weibing Sun, and Huchuan Lu Published: 2026-03-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.12708v1 Marine Animal Segmentation (MAS) aims at identifying and segmenting marine animals from complex marine environments. Most of previous deep learning-based MAS methods struggle with the long-distance modeling issue. Recently, Segment Anything Model (SAM) has gained popularity in general image segmentation. However, it lacks of perceiving fine-grained details and frequency information. To this end, we propose a novel learning framework, named Hierarchical Frequency Prompted SAM (HFP-SAM) for high-performance MAS. First, we design a Frequency Guided Adapter (FGA) to efficiently inject marine scene information into the frozen SAM backbone through frequency domain prior masks. Additionally, we introduce a Frequency-aware Point Selection (FPS) to generate highlighted regions through frequency analysis. These regions are combined with the coarse predictions of SAM to generate point prompts and integrate into SAM's decoder for fine predictions. Finally, to obtain comprehensive segmentation masks, we introduce a Full-View Mamba (FVM) to efficiently extract spatial and channel contextual information with linear computational complexity. Extensive experiments on four public datasets demonstrate the superior performance of our approach. The source code is publicly available at https://github.com/Drchip61/TIP-HFP-SAM. --- ### Cost-Efficient Multimodal LLM Inference via Cross-Tier GPU Heterogeneity Authors: Donglin Yu Published: 2026-03-13 Categories: cs.LG, cs.AI, cs.DC arXiv: https://arxiv.org/abs/2603.12707v1 Multimodal large language model (MLLM) inference splits into two phases with opposing hardware demands: vision encoding is compute-bound, while language generation is memory-bandwidth-bound. We show that under standard transformer KV caching, the modality boundary (between vision encoder and language model) minimizes cross-device transfer among all partition points that preserve standard stage-based execution. Partitioning here reduces transfer complexity from $O(L * s_ctx)$ bytes (GB-scale KV caches under stage-level disaggregation) to $O(N_v * d)$ bytes (MB-scale embeddings), an O(L) reduction where L is the transformer depth. The result holds across attention mechanisms (MHA/GQA), dynamic vision resolutions, and model scales, and the advantage grows as models deepen. A direct implication is that existing stage-level disaggregation systems are constrained to high-bandwidth interconnects (e.g., NVLink), whereas modality-level disaggregation enables cross-tier heterogeneous serving over commodity PCIe. A closed-form cost model shows that heterogeneous deployment is cost-optimal under phase-separable workloads (predicts 31.4% savings; observed 40.6%). We build HeteroServe, a phase-aware runtime with modality-level partitioning and cross-tier scheduling, and evaluate it on LLaVA-1.5-7B and Qwen2.5-VL against vLLM v0.3.0. On identical 4xA100 hardware, engine optimizations raise throughput by up to 54%. Under a fixed budget, a heterogeneous cluster (\$38k) improves Tokens/\$ by 37% over a homogeneous baseline (\$64k) without degrading latency. --- ### SVCBench: A Streaming Video Counting Benchmark for Spatial-Temporal State Maintenance Authors: Pengyiang Liu, Zhongyue Shi, Hongye Hao, Qi Fu, Xueting Bi, Siwei Zhang, Xiaoyang Hu, Zitian Wang, Linjiang Huang, Si Liu Published: 2026-03-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.12703v3 Video understanding requires models to continuously track and update world state during playback. Although existing benchmarks have advanced video understanding evaluation across multiple dimensions, they provide limited visibility into how models maintain world state over time. We propose SVCBench, a Streaming Video Counting Benchmark that repositions counting as a minimal, controlled probe for diagnosing models' world-state maintenance capability. We decompose this capability into object counting and event counting, forming 8 fine-grained subcategories. Object counting covers tracking currently visible objects and cumulative unique identities, while event counting covers detecting instantaneous actions and tracking complete activity cycles. SVCBench contains 406 videos with frame-by-frame annotations of 10,071 event occurrences and object state changes, yielding 1,000 streaming QA pairs with 4,576 query points distributed along video timelines. By observing state maintenance trajectories through streaming multi-point queries, we design three complementary metrics to diagnose numerical precision, trajectory consistency, and temporal awareness. Evaluations of mainstream video-language models show that current models still exhibit significant deficiencies in spatial-temporal state maintenance, with especially poor performance on periodic event counting. SVCBench provides a diagnostic framework for measuring and improving state maintenance in video understanding systems. Our code and data are available at https://buaa-colalab.github.io/SVCBench. ---