# Research Papers — 2026-03 · bundle page 20 of 243 > Full-text markdown of papers #951–1000 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/20 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/19.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/21.md) ### jaxsgp4: GPU-accelerated mega-constellation propagation with batch parallelism Authors: Charlotte Priestley, Will Handley Published: 2026-03-29 Categories: cs.DC, astro-ph.EP, astro-ph.IM, cs.LG arXiv: https://arxiv.org/abs/2603.27830v1 As the population of anthropogenic space objects transitions from sparse clusters to mega-constellations exceeding 100,000 satellites, traditional orbital propagation techniques face a critical bottleneck. Standard CPU-bound implementations of the Simplified General Perturbations 4 (SGP4) algorithm are less well suited to handle the requisite scale of collision avoidance and Space Situational Awareness (SSA) tasks. This paper introduces \texttt{jaxsgp4}, an open-source high-performance reimplementation of SGP4 utilising the \texttt{JAX} library. \texttt{JAX} has gained traction in the landscape of computational research, offering an easy mechanism for Just-In-Time (JIT) compilation, automatic vectorisation and automatic optimisation of code for CPU, GPU and TPU hardware modalities. By refactoring the algorithm into a pure functional paradigm, we leverage these transformations to execute massively parallel propagations on modern GPUs. We demonstrate that \texttt{jaxsgp4} can propagate the entire Starlink constellation (9,341 satellites) each to 1,000 future time steps in under 4 ms on a single A100 GPU, representing a speedup of $1500\times$ over traditional C++ baselines. Furthermore, we argue that the use of 32-bit precision for SGP4 propagation tasks offers a principled trade-off, sacrificing negligible precision loss for a substantial gain in throughput on hardware accelerators. --- ### Improving Clinical Diagnosis with Counterfactual Multi-Agent Reasoning Authors: Zhiwen You, Xi Chen, Aniket Vashishtha, Simo Du, Gabriel Erion-Barner, Hongyuan Mei, Hao Peng, Yue Guo Published: 2026-03-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.27820v2 Clinical diagnosis is a complex reasoning process in which clinicians gather evidence, form hypotheses, and test them against alternative explanations. In medical training, this reasoning is explicitly developed through counterfactual questioning--e.g., asking how a diagnosis would change if a key symptom were absent or altered--to strengthen differential diagnosis skills. As large language model (LLM)-based systems are increasingly used for diagnostic support, ensuring the interpretability of their recommendations becomes critical. However, most existing LLM-based diagnostic agents reason over fixed clinical evidence without explicitly testing how individual findings support or weaken competing diagnoses. In this work, we propose a counterfactual multi-agent diagnostic framework inspired by clinician training that makes hypothesis testing explicit and evidence-grounded. Our framework introduces counterfactual case editing to modify clinical findings and evaluate how these changes affect competing diagnoses. We further define the Counterfactual Probability Gap, a method that quantifies how strongly individual findings support a diagnosis by measuring confidence shifts under these edits. These counterfactual signals guide multi-round specialist discussions, enabling agents to challenge unsupported hypotheses, refine differential diagnoses, and produce more interpretable reasoning trajectories. Across three diagnostic benchmarks and seven LLMs, our method consistently improves diagnostic accuracy over prompting and prior multi-agent baselines, with the largest gains observed in complex and ambiguous cases. Human evaluation further indicates that our framework produces more clinically useful, reliable, and coherent reasoning. These results suggest that incorporating counterfactual evidence verification is an important step toward building reliable AI systems for clinical decision support. --- ### KVSculpt: KV Cache Compression as Distillation Authors: Bo Jiang, Sian Jin Published: 2026-03-29 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.27819v1 KV cache compression is critical for efficient long-context LLM inference. Approaches that reduce the per-pair footprint -- quantization and low-rank decomposition -- are orthogonal to those that reduce the sequence length of the cache. Along the sequence-length dimension, existing methods range from pure eviction -- selecting which KV pairs to keep -- to merging, which combines similar pairs into fewer ones. Both remain anchored to the original cache entries. We propose KVSculpt, which moves to the other end of this spectrum: instead of selecting or combining original pairs, we optimize a smaller set of unconstrained KV pairs in continuous embedding space to preserve each layer's attention behavior. Keys are optimized via L-BFGS and values are solved in closed form via least squares, alternating every few steps. On top of this, we introduce adaptive budget allocation, which uses a cheap pilot compression run to redistribute the compression budget across layers and KV heads based on per-component difficulty. On Qwen2.5-1.5B-Instruct with 2048-token contexts, KVSculpt reduces KL divergence by 3.5-4.1x compared to Select+Fit -- attention-score eviction with least-squares value fitting -- across compression ratios r in {0.3, 0.5, 0.7}. Adaptive allocation provides an additional 1.3x KL reduction at no extra inference cost. Analysis reveals that compression difficulty is highly non-uniform: per-layer pilot MSE varies by up to 100x across layers, and the two KV heads within a single layer can differ by up to 467x -- demonstrating that fine-grained budget allocation is essential. --- ### Benchmarking Multi-View BEV Object Detection with Mixed Pinhole and Fisheye Cameras Authors: Xiangzhong Liu, Hao Shen Published: 2026-03-29 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2603.27818v1 Modern autonomous driving systems increasingly rely on mixed camera configurations with pinhole and fisheye cameras for full view perception. However, Bird's-Eye View (BEV) 3D object detection models are predominantly designed for pinhole cameras, leading to performance degradation under fisheye distortion. To bridge this gap, we introduce a multi-view BEV detection benchmark with mixed cameras by converting KITTI-360 into nuScenes format. Our study encompasses three adaptations: rectification for zero-shot evaluation and fine-tuning of nuScenes-trained models, distortion-aware view transformation modules (VTMs) via the MEI camera model, and polar coordinate representations to better align with radial distortion. We systematically evaluate three representative BEV architectures, BEVFormer, BEVDet and PETR, across these strategies. We demonstrate that projection-free architectures are inherently more robust and effective against fisheye distortion than other VTMs. This work establishes the first real-data 3D detection benchmark with fisheye and pinhole images and provides systematic adaptation and practical guidelines for designing robust and cost-effective 3D perception systems. The code is available at https://github.com/CesarLiu/FishBEVOD.git. --- ### Towards Context-Aware Image Anonymization with Multi-Agent Reasoning Authors: Robert Aufschläger, Jakob Folz, Gautam Savaliya, Manjitha D Vidanalage, Michael Heigl, Martin Schramm Published: 2026-03-29 Categories: cs.CV, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2603.27817v3 Street-level imagery contains personally identifiable information (PII), some of which is context-dependent. Existing anonymization methods either over-process images or miss subtle identifiers, while API-based solutions compromise data sovereignty. We present an agentic framework CAIAMAR (\underline{C}ontext-\underline{A}ware \underline{I}mage \underline{A}nonymization with \underline{M}ulti-\underline{A}gent \underline{R}easoning) for context-aware PII segmentation with diffusion-based anonymization, combining pre-defined processing for high-confidence cases with multi-agent reasoning for indirect identifiers. Three specialized agents coordinate via round-robin speaker selection in a Plan-Do-Check-Act (PDCA) cycle, enabling large vision-language models to classify PII based on spatial context (private vs. public property) rather than rigid category rules. The agents implement spatially-filtered coarse-to-fine detection where a scout-and-zoom strategy identifies candidates, open-vocabulary segmentation processes localized crops, and $IoU$-based deduplication ($30\%$ threshold) prevents redundant processing. Modal-specific diffusion guidance with appearance decorrelation substantially reduces re-identification (Re-ID) risks. On CUHK03-NP, our method reduces person Re-ID risk by $73\%$ ($R1$: $16.9\%$ vs. $62.4\%$ baseline). For image quality preservation on CityScapes, we achieve KID: $0.001$, and FID: $9.1$, significantly outperforming existing anonymization. The agentic workflow detects non-direct PII instances across object categories, and downstream semantic segmentation is preserved. Operating entirely on-premise with open-source models, the framework generates human-interpretable audit trails supporting EU's GDPR transparency requirements while flagging failed cases for human review. --- ### RG-TTA: Regime-Guided Meta-Control for Test-Time Adaptation in Streaming Time Series Authors: Indar Kumar, Akanksha Tiwari, Sai Krishna Jasti, Ankit Hemant Lade Published: 2026-03-29 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2603.27814v1 Test-time adaptation (TTA) enables neural forecasters to adapt to distribution shifts in streaming time series, but existing methods apply the same adaptation intensity regardless of the nature of the shift. We propose Regime-Guided Test-Time Adaptation (RG-TTA), a meta-controller that continuously modulates adaptation intensity based on distributional similarity to previously-seen regimes. Using an ensemble of Kolmogorov-Smirnov, Wasserstein-1, feature-distance, and variance-ratio metrics, RG-TTA computes a similarity score for each incoming batch and uses it to (i) smoothly scale the learning rate -- more aggressive for novel distributions, conservative for familiar ones -- and (ii) control gradient effort via loss-driven early stopping rather than fixed budgets, allowing the system to allocate exactly the effort each batch requires. As a supplementary mechanism, RG-TTA gates checkpoint reuse from a regime memory, loading stored specialist models only when they demonstrably outperform the current model (loss improvement >= 30%). RG-TTA is model-agnostic and strategy-composable: it wraps any forecaster exposing train/predict/save/load interfaces and enhances any gradient-based TTA method. We demonstrate three compositions -- RG-TTA, RG-EWC, and RG-DynaTTA -- and evaluate 6 update policies (3 baselines + 3 regime-guided variants) across 4 compact architectures (GRU, iTransformer, PatchTST, DLinear), 14 datasets (6 real-world multivariate benchmarks + 8 synthetic regime scenarios), and 4 forecast horizons (96, 192, 336, 720) under a streaming evaluation protocol with 3 random seeds (672 experiments total). Regime-guided policies achieve the lowest MSE in 156 of 224 seed-averaged experiments (69.6%), with RG-EWC winning 30.4% and RG-TTA winning 29.0%. Overall, RG-TTA reduces MSE by 5.7% vs TTA while running 5.5% faster; RG-EWC reduces MSE by 14.1% vs standalone EWC. --- ### MuSEAgent: A Multimodal Reasoning Agent with Stateful Experiences Authors: Shijian Wang, Jiarui Jin, Runhao Fu, Zexuan Yan, Xingjian Wang, Mengkang Hu, Eric Wang, Xiaoxi Li, Kangning Zhang, Li Yao, Wenxiang Jiao, Xuelian Cheng et al. Published: 2026-03-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.27813v1 Research agents have recently achieved significant progress in information seeking and synthesis across heterogeneous textual and visual sources. In this paper, we introduce MuSEAgent, a multimodal reasoning agent that enhances decision-making by extending the capabilities of research agents to discover and leverage stateful experiences. Rather than relying on trajectory-level retrieval, we propose a stateful experience learning paradigm that abstracts interaction data into atomic decision experiences through hindsight reasoning. These experiences are organized into a quality-filtered experience bank that supports policy-driven experience retrieval at inference time. Specifically, MuSEAgent enables adaptive experience exploitation through complementary wide- and deep-search strategies, allowing the agent to dynamically retrieve multimodal guidance across diverse compositional semantic viewpoints. Extensive experiments demonstrate that MuSEAgent consistently outperforms strong trajectory-level experience retrieval baselines on both fine-grained visual perception and complex multimodal reasoning tasks. These results validate the effectiveness of stateful experience modeling in improving multimodal agent reasoning. --- ### Tracking without Seeing: Geospatial Inference using Encrypted Traffic from Distributed Nodes Authors: Sadik Yagiz Yetim, Gaofeng Dong, Isaac-Neil Zanoria, Ronit Barman, Maggie Wigness, Tarek Abdelzaher, Mani Srivastava, Suhas Diggavi Published: 2026-03-29 Categories: cs.CV, cs.LG, cs.NI arXiv: https://arxiv.org/abs/2603.27811v1 Accurate observation of dynamic environments traditionally relies on synthesizing raw, signal-level information from multiple distributed sensors. This work investigates an alternative approach: performing geospatial inference using only encrypted packet-level information, without access to the raw sensory data. We further explore how this indirect information can be fused with directly available sensory data to extend overall inference capabilities. We introduce GraySense, a learning-based framework that performs geospatial object tracking by analyzing encrypted wireless video transmission traffic, such as packet sizes, from cameras with inaccessible streams. GraySense leverages the inherent relationship between scene dynamics and transmitted packet sizes to infer object motion. The framework consists of two stages: (1) a Packet Grouping module that identifies frame boundaries and estimates frame sizes from encrypted network traffic, and (2) a Tracker module, based on a Transformer encoder with a recurrent state, which fuses indirect packet-based inputs with optional direct camera-based inputs to estimate the object's position. Extensive experiments with realistic videos from the CARLA simulator and emulated networks under varying conditions show that GraySense achieves 2.33 meters tracking error (Euclidean distance) without raw signal access, within the dimensions of tracked objects (4.61m x 1.93m). To our knowledge, this capability has not been previously demonstrated, expanding the use of latent signals for sensing. --- ### Conversational Agents and the Understanding of Human Language: Reflections on AI, LLMs, and Cognitive Science Authors: Andrei Popescu-Belis Published: 2026-03-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.27809v1 In this paper, we discuss the relationship between natural language processing by computers (NLP) and the understanding of the human language capacity, as studied by linguistics and cognitive science. We outline the evolution of NLP from its beginnings until the age of large language models, and highlight for each of its main paradigms some similarities and differences with theories of the human language capacity. We conclude that the evolution of language technology has not substantially deepened our understanding of how human minds process natural language, despite the impressive language abilities attained by current chatbots using artificial neural networks. --- ### Understanding Teacher Revisions of Large Language Model-Generated Feedback Authors: Conrad Borchers, Luiz Rodrigues, Newarney Torrezão da Costa, Cleon Xavier, Rafael Ferreira Mello Published: 2026-03-29 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2603.27806v1 Large language models (LLMs) increasingly generate formative feedback for students, yet little is known about how teachers revise this feedback before it reaches learners. Teachers' revisions shape what students receive, making revision practices central to evaluating AI classroom tools. We analyze a dataset of 1,349 instances of AI-generated feedback and corresponding teacher-edited explanations from 117 teachers. We examine (i) textual characteristics associated with teacher revisions, (ii) whether revision decisions can be predicted from the AI feedback text, and (iii) how revisions change the pedagogical type of feedback delivered. First, we find that teachers accept AI feedback without modification in about 80% of cases, while edited feedback tends to be significantly longer and subsequently shortened by teachers. Editing behavior varies substantially across teachers: about 50% never edit AI feedback, and only about 10% edit more than two-thirds of feedback instances. Second, machine learning models trained only on the AI feedback text as input features, using sentence embeddings, achieve fair performance in identifying which feedback will be revised (AUC=0.75). Third, qualitative coding shows that when revisions occur, teachers often simplify AI-generated feedback, shifting it away from high-information explanations toward more concise, corrective forms. Together, these findings characterize how teachers engage with AI-generated feedback in practice and highlight opportunities to design feedback systems that better align with teacher priorities while reducing unnecessary editing effort. --- ### Distributed Online Submodular Maximization under Communication Delays: A Simultaneous Decision-Making Approach Authors: Zirui Xu, Vasileios Tzoumas Published: 2026-03-29 Categories: cs.LG, cs.MA, eess.SY, math.OC arXiv: https://arxiv.org/abs/2603.27803v2 We provide a distributed online algorithm for multi-agent submodular maximization under communication delays. We are motivated by the future distributed information-gathering tasks in unknown and dynamic environments, where utility functions naturally exhibit the diminishing-returns property, i.e., submodularity. Existing approaches for online submodular maximization either rely on sequential multi-hop communication, resulting in prohibitive delays and restrictive connectivity assumptions, or restrict each agent's coordination to its one-hop neighborhood only, thereby limiting the coordination performance. To address the issue, we provide the Distributed Online Greedy (DOG) algorithm, which integrates tools from adversarial bandit learning with delayed feedback to enable simultaneous decision-making across arbitrary network topologies. We provide the approximation performance of DOG against an optimal solution, capturing the suboptimality cost due to decentralization as a function of the network structure. Our analyses further reveal a trade-off between coordination performance and convergence time, determined by the magnitude of communication delays. By this trade-off, DOG spans the spectrum between the state-of-the-art fully centralized online coordination approach (1) and fully decentralized one-hop coordination approach (2). --- ### Distributed Online Submodular Maximization under Communication Delays: A Simultaneous Decision-Making Approach Authors: Zirui Xu, Vasileios Tzoumas Published: 2026-03-29 Categories: cs.LG, cs.MA, eess.SY, math.OC arXiv: https://arxiv.org/abs/2603.27803v1 We provide a distributed online algorithm for multi-agent submodular maximization under communication delays. We are motivated by the future distributed information-gathering tasks in unknown and dynamic environments, where utility functions naturally exhibit the diminishing-returns property, i.e., submodularity. Existing approaches for online submodular maximization either rely on sequential multi-hop communication, resulting in prohibitive delays and restrictive connectivity assumptions, or restrict each agent's coordination to its one-hop neighborhood only, thereby limiting the coordination performance. To address the issue, we provide the Distributed Online Greedy (DOG) algorithm, which integrates tools from adversarial bandit learning with delayed feedback to enable simultaneous decision-making across arbitrary network topologies. We provide the approximation performance of DOG against an optimal solution, capturing the suboptimality cost due to decentralization as a function of the network structure. Our analyses further reveal a trade-off between coordination performance and convergence time, determined by the magnitude of communication delays. By this trade-off, DOG spans the spectrum between the state-of-the-art fully centralized online coordination approach (1) and fully decentralized one-hop coordination approach (2). --- ### Engineering Mythology: A Digital-Physical Framework for Culturally-Inspired Public Art Authors: Jnaneshwar Das, Christopher Filkins, Rajesh Moharana, Ekadashi Barik, Bishweshwar Das, David Ayers, Christopher Skiba, Rodney Staggers, Mark Dill, Swig Miller, Daniel Tulberg, Patrick Smith et al. Published: 2026-03-29 Categories: cs.GR, cs.CV, cs.CY, cs.RO arXiv: https://arxiv.org/abs/2603.27801v1 Navagunjara Reborn: The Phoenix of Odisha was built for Burning Man 2025 as both a sculpture and an experiment-a fusion of myth, craft, and computation. This paper describes the digital-physical workflow developed for the project: a pipeline that linked digital sculpting, distributed fabrication by artisans in Odisha (India), modular structural optimization in the U.S., iterative feedback through photogrammetry and digital twins, and finally, one-shot full assembly at the art site in Black Rock Desert, Nevada. The desert installation tested not just materials, but also systems of collaboration: between artisans and engineers, between myth and technology, between cultural specificity and global experimentation. We share the lessons learned in design, fabrication, and deployment and offer a framework for future interdisciplinary projects at the intersection of cultural heritage, STEAM education, and public art. In retrospect, this workflow can be read as a convergence of many knowledge systems-artisan practice, structural engineering, mythic narrative, and environmental constraint-rather than as execution of a single fixed blueprint. --- ### Diversity Matters: Dataset Diversification and Dual-Branch Network for Generalized AI-Generated Image Detection Authors: Nusrat Tasnim, Kutub Uddin, Khalid Malik Published: 2026-03-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.27800v1 The rapid proliferation of AI-generated images, powered by generative adversarial networks (GANs), diffusion models, and other synthesis techniques, has raised serious concerns about misinformation, copyright violations, and digital security. However, detecting such images in a generalized and robust manner remains a major challenge due to the vast diversity of generative models and data distributions. In this work, we present \textbf{Diversity Matters}, a novel framework that emphasizes data diversity and feature domain complementarity for AI-generated image detection. The proposed method introduces a feature-domain similarity filtering mechanism that discards redundant or highly similar samples across both inter-class and intra-class distributions, ensuring a more diverse and representative training set. Furthermore, we propose a dual-branch network that combines CLIP features from the pixel domain and the frequency domain to jointly capture semantic and structural cues, leading to improved generalization against unseen generative models and adversarial conditions. Extensive experiments on benchmark datasets demonstrate that the proposed approach significantly improves cross-model and cross-dataset performance compared to existing methods. \textbf{Diversity Matters} highlights the critical role of data and feature diversity in building reliable and robust detectors against the rapidly evolving landscape of synthetic content. --- ### Towards Emotion Recognition with 3D Pointclouds Obtained from Facial Expression Images Authors: Laura Rayón Ropero, Jasper De Laet, Filip Lemic, Pau Sabater Nácher, Nabeel Nisar Bhat, Sergi Abadal, Jeroen Famaey, Eduard Alarcón, Xavier Costa-Pérez Published: 2026-03-29 Categories: cs.CV, cs.AI, cs.ET, cs.HC, eess.IV arXiv: https://arxiv.org/abs/2603.27798v1 Facial Emotion Recognition is a critical research area within Affective Computing due to its wide-ranging applications in Human Computer Interaction, mental health assessment and fatigue monitoring. Current FER methods predominantly rely on Deep Learning techniques trained on 2D image data, which pose significant privacy concerns and are unsuitable for continuous, real-time monitoring. As an alternative, we propose High-Frequency Wireless Sensing (HFWS) as an enabler of continuous, privacy-aware FER, through the generation of detailed 3D facial pointclouds via on-person sensors embedded in wearables. We present arguments supporting the privacy advantages of HFWS over traditional 2D imaging, particularly under increasingly stringent data protection regulations. A major barrier to adopting HFWS for FER is the scarcity of labeled 3D FER datasets. Towards addressing this issue, we introduce a FLAME-based method to generate 3D facial pointclouds from existing public 2D datasets. Using this approach, we create AffectNet3D, a 3D version of the AffectNet database. To evaluate the quality and usability of the generated data, we design a pointcloud refinement pipeline focused on isolating the facial region, and train the popular PointNet++ model on the refined pointclouds. Fine-tuning the model on a small subset of the unseen 3D FER dataset BU-3DFE yields a classification accuracy exceeding 70%, comparable to oracle-level performance. To further investigate the potential of HFWS-based FER for continuous monitoring, we simulate wearable sensing conditions by masking portions of the generated pointclouds. Experimental results show that models trained on AffectNet3D and fine-tuned with just 25% of BU-3DFE outperform those trained solely on BU-3DFE. These findings highlight the viability of our pipeline and support the feasibility of continuous, privacy-aware FER via wearable HFWS systems. --- ### What-If Explanations Over Time: Counterfactuals for Time Series Classification Authors: Udo Schlegel, Thomas Seidl Published: 2026-03-29 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2603.27792v1 Counterfactual explanations emerge as a powerful approach in explainable AI, providing what-if scenarios that reveal how minimal changes to an input time series can alter the model's prediction. This work presents a survey of recent algorithms for counterfactual explanations for time series classification. We review state-of-the-art methods, spanning instance-based nearest-neighbor techniques, pattern-driven algorithms, gradient-based optimization, and generative models. For each, we discuss the underlying methodology, the models and classifiers they target, and the datasets on which they are evaluated. We highlight unique challenges in generating counterfactuals for temporal data, such as maintaining temporal coherence, plausibility, and actionable interpretability, which distinguish the temporal from tabular or image domains. We analyze the strengths and limitations of existing approaches and compare their effectiveness along key dimensions (validity, proximity, sparsity, plausibility, etc.). In addition, we implemented an open-source implementation library, Counterfactual Explanations for Time Series (CFTS), as a reference framework that includes many algorithms and evaluation metrics. We discuss this library's contributions in standardizing evaluation and enabling practical adoption of explainable time series techniques. Finally, based on the literature and identified gaps, we propose future research directions, including improved user-centered design, integration of domain knowledge, and counterfactuals for time series forecasting. --- ### Inference-time Trajectory Optimization for Structure-Preserving Manga Image Editing Authors: Ryosuke Furuta Published: 2026-03-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.27790v2 We present a lightweight, training-free trajectory correction method that adapts a pretrained image editing model to each input manga image using only the input itself. Despite recent progress in pretrained image editing, such models often underperform on manga because they are trained predominantly on natural-image data, while re-training or fine-tuning them on manga is costly and raises copyright concerns. Many manga image editing tasks encountered in practice are structure-preserving, requiring local details to be modified while the input's global composition is retained. To support this common editing setting, our method corrects the early editing trajectory by anchoring it to an empty-prompt reconstruction trajectory. Experiments indicate improved performance in the main text-removal setting, while qualitative examples suggest better composition preservation in screentone synthesis. With FLUX.1 Kontext on an RTX A6000, the method incurs 11% runtime overhead and 0.1% peak-memory overhead; an additional runtime measurement with Qwen Image Edit 2509 on an NVIDIA H200 shows only a 0.1% increase. --- ### GS3LAM: Gaussian Semantic Splatting SLAM Authors: Linfei Li, Lin Zhang, Zhong Wang, Ying Shen Published: 2026-03-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.27781v1 Recently, the multi-modal fusion of RGB, depth, and semantics has shown great potential in dense Simultaneous Localization and Mapping (SLAM). However, a prerequisite for generating consistent semantic maps is the availability of dense, efficient, and scalable scene representations. Existing semantic SLAM systems based on explicit representations are often limited by resolution and an inability to predict unknown areas. Conversely, implicit representations typically rely on time-consuming ray tracing, failing to meet real-time requirements. Fortunately, 3D Gaussian Splatting (3DGS) has emerged as a promising representation that combines the efficiency of point-based methods with the continuity of geometric structures. To this end, we propose GS3LAM, a Gaussian Semantic Splatting SLAM framework that processes multimodal data to render consistent, dense semantic maps in real-time. GS3LAM models the scene as a Semantic Gaussian Field (SG-Field) and jointly optimizes camera poses and the field via multimodal error constraints. Furthermore, a Depth-adaptive Scale Regularization (DSR) scheme is introduced to resolve misalignments between scale-invariant Gaussians and geometric surfaces. To mitigate catastrophic forgetting, we propose a Random Sampling-based Keyframe Mapping (RSKM) strategy, which demonstrates superior performance over common local covisibility optimization methods. Extensive experiments on benchmark datasets show that GS3LAM achieves increased tracking robustness, superior rendering quality, and enhanced semantic precision compared to state-of-the-art methods. Source code is available at https://github.com/lif314/GS3LAM. --- ### Exploring Student Perception on Gen AI Adoption in Higher Education: A Descriptive Study Authors: Harpreet Singh, Jaspreet Singh, Satwant Singh, Rupinder Singh, Shamim Ibne Shahid, Mohammad Hassan, Tayarani Najaran Published: 2026-03-29 Categories: cs.CY, cs.CV arXiv: https://arxiv.org/abs/2603.27777v1 The rapid proliferation of Generative Artificial Intelligence (GenAI) is reshaping pedagogical practices and assessment models in higher education. While institutional and educator perspectives on GenAI integration are increasingly documented, the student perspective remains comparatively underexplored. This study examines how students perceive, use, and evaluate GenAI within their academic practices, focusing on usage patterns, perceived benefits, and expectations for institutional support. Data were collected through a questionnaire administered to 436 postgraduate Computer Science students at the University of Hertfordshire and analysed using descriptive methods. The findings reveal a Confidence-Competence Paradox: although more than 60% of students report high familiarity with tools such as ChatGPT, daily academic use remains limited and confidence in effective application is only moderate. Students primarily employ GenAI for cognitive scaffolding tasks, including concept clarification and brainstorming, rather than fully automated content generation. At the same time, respondents express concerns regarding data privacy, reliability of AI-generated information, and the potential erosion of critical thinking skills. The results also indicate strong student support for integrating AI literacy into curricula and programme Knowledge, Skills, and Behaviours (KSBs). Overall, the study suggests that universities should move beyond a policing approach to GenAI and adopt a pedagogical framework that emphasises AI literacy, ethical guidance, and equitable access to AI tools. --- ### RINO: Rotation-Invariant Non-Rigid Correspondences Authors: Maolin Gao, Shao Jie Hu-Chen, Congyue Deng, Riccardo Marin, Leonidas Guibas, Daniel Cremers Published: 2026-03-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.27773v1 Dense 3D shape correspondence remains a central challenge in computer vision and graphics as many deep learning approaches still rely on intermediate geometric features or handcrafted descriptors, limiting their effectiveness under non-isometric deformations, partial data, and non-manifold inputs. To overcome these issues, we introduce RINO, an unsupervised, rotation-invariant dense correspondence framework that effectively unifies rigid and non-rigid shape matching. The core of our method is the novel RINONet, a feature extractor that integrates vector-based SO(3)-invariant learning with orientation-aware complex functional maps to extract robust features directly from raw geometry. This allows for a fully end-to-end, data-driven approach that bypasses the need for shape pre-alignment or handcrafted features. Extensive experiments show unprecedented performance of RINO across challenging non-rigid matching tasks, including arbitrary poses, non-isometry, partiality, non-manifoldness, and noise. --- ### Emergent Risks in Generative Multi-Agent Systems Authors: Yue Huang, Yu Jiang, Wenjie Wang, Haomin Zhuang, Xiaonan Luo, Yuchen Ma, Zhangchen Xu, Zichen Chen, Nuno Moniz, Zinan Lin, Pin-Yu Chen, Nitesh V Chawla et al. Published: 2026-03-29 Categories: cs.MA, cs.CL, cs.CY arXiv: https://arxiv.org/abs/2603.27771v3 Multi-agent systems composed of large generative models are rapidly moving from laboratory prototypes to real-world deployments, where they jointly plan, negotiate, and allocate shared resources to solve complex tasks. While such systems promise unprecedented scalability and autonomy, their collective interaction also gives rise to failure modes that cannot be reduced to individual agents. Understanding these emergent risks is therefore critical. Here, we present a pioneer study of such emergent multi-agent risk in workflows that involve competition over shared resources (e.g., computing resources or market share), sequential handoff collaboration (where downstream agents see only predecessor outputs), collective decision aggregation, and others. Across these settings, we observe that such group behaviors arise frequently across repeated trials and a wide range of interaction conditions, rather than as rare or pathological cases. In particular, phenomena such as collusion-like coordination and conformity emerge with non-trivial frequency under realistic resource constraints, communication protocols, and role assignments, mirroring well-known pathologies in human societies despite no explicit instruction. Moreover, these risks cannot be prevented by existing agent-level safeguards alone. These findings expose the dark side of intelligent multi-agent systems: a social intelligence risk where agent collectives, despite no instruction to do so, spontaneously reproduce familiar failure patterns from human societies. --- ### Emergent Social Intelligence Risks in Generative Multi-Agent Systems Authors: Yue Huang, Yu Jiang, Wenjie Wang, Haomin Zhuang, Xiaonan Luo, Yuchen Ma, Zhangchen Xu, Zichen Chen, Nuno Moniz, Zinan Lin, Pin-Yu Chen, Nitesh V Chawla et al. Published: 2026-03-29 Categories: cs.MA, cs.CL, cs.CY arXiv: https://arxiv.org/abs/2603.27771v2 Multi-agent systems composed of large generative models are rapidly moving from laboratory prototypes to real-world deployments, where they jointly plan, negotiate, and allocate shared resources to solve complex tasks. While such systems promise unprecedented scalability and autonomy, their collective interaction also gives rise to failure modes that cannot be reduced to individual agents. Understanding these emergent risks is therefore critical. Here, we present a pioneer study of such emergent multi-agent risk in workflows that involve competition over shared resources (e.g., computing resources or market share), sequential handoff collaboration (where downstream agents see only predecessor outputs), collective decision aggregation, and others. Across these settings, we observe that such group behaviors arise frequently across repeated trials and a wide range of interaction conditions, rather than as rare or pathological cases. In particular, phenomena such as collusion-like coordination and conformity emerge with non-trivial frequency under realistic resource constraints, communication protocols, and role assignments, mirroring well-known pathologies in human societies despite no explicit instruction. Moreover, these risks cannot be prevented by existing agent-level safeguards alone. These findings expose the dark side of intelligent multi-agent systems: a social intelligence risk where agent collectives, despite no instruction to do so, spontaneously reproduce familiar failure patterns from human societies. --- ### TailNLG: A Multilingual Benchmark Addressing Verbalization of Long-Tail Entities Authors: Lia Draetta, Michael Oliverio, Virginia Ramón-Ferrer, Pier Felice Balestrucci, Flaviana Corallo, Carlos Badenes-Olmedo, Alessandro Mazzei, Marco Antonio Stranisci, Rossana Damiano Published: 2026-03-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.27768v1 The automatic verbalization of structured knowledge is a key task for making knowledge graphs accessible to non-expert users and supporting retrieval-augmented generation systems. Although recent advances in Data-to-Text generation have improved multilingual coverage, little attention has been paid to potential biases in the verbalization of rare entities, frequently known as long-tail entities. In this work, we present the first systematic study of long-tail entities in Data-to-Text generation. We introduce TailNLG, a new multilingual benchmark in English, Italian, and Spanish, built from Wikidata and covering entities with varying levels of popularity. We evaluate three different families of large language models in zero-shot settings and compare their performance on rare versus common entities, as well as against the established WebNLG benchmark. Our results reveal a consistent bias against long-tail entities: embedding-based scores are lower, and model uncertainty is higher for rare entities. We further show that the impact of long-tail entities varies across models and languages, and that existing evaluation metrics do not consistently capture these differences, highlighting the need for more reliable evaluation frameworks. --- ### AutoStan: Autonomous Bayesian Model Improvement via Predictive Feedback Authors: Oliver Dürr Published: 2026-03-29 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2603.27766v1 We present AutoStan, a framework in which a command-line interface (CLI) coding agent autonomously builds and iteratively improves Bayesian models written in Stan. The agent operates in a loop, writing a Stan model file, executing MCMC sampling, then deciding whether to keep or revert each change based on two complementary feedback signals: the negative log predictive density (NLPD) on held-out data and the sampler's own diagnostics (divergences, R-hat, effective sample size). We evaluate AutoStan on five datasets with diverse modeling structures. On a synthetic regression dataset with outliers, the agent progresses from naive linear regression to a model with Student-t robustness, nonlinear heteroscedastic structure, and an explicit contamination mixture, matching or outperforming TabPFN, a state-of-the-art black-box method, while remaining fully interpretable. Across four additional experiments, the same mechanism discovers hierarchical partial pooling, varying-slope models with correlated random effects, and a Poisson attack/defense model for soccer. No search algorithm, critic module, or domain-specific instructions are needed. This is, to our knowledge, the first demonstration that a CLI coding agent can autonomously write and iteratively improve Stan code for diverse Bayesian modeling problems. --- ### Let the Agent Steer: Closed-Loop Ranking Optimization via Influence Exchange Authors: Yin Cheng, Liao Zhou, Xiyu Liang, Dihao Luo, Tewei Lee, Kailun Zheng, Weiwei Zhang, Mingchen Cai, Jian Dong, Andy Zhang Published: 2026-03-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.27765v3 Recommendation ranking is fundamentally an influence allocation problem: a sorting formula distributes ranking influence among competing factors, and the business outcome depends on finding the optimal "exchange rates" among them. However, offline proxy metrics systematically misjudge how influence reallocation translates to online impact, with asymmetric bias across metrics that a single calibration factor cannot correct. We present Sortify, the first fully autonomous LLM-driven ranking optimization agent deployed in a large-scale production recommendation system. The agent reframes ranking optimization as continuous influence exchange, closing the full loop from diagnosis to parameter deployment without human intervention. It addresses structural problems through three mechanisms: (1) a dual-channel framework grounded in Savage's Subjective Expected Utility (SEU) that decouples offline-online transfer correction (Belief channel) from constraint penalty adjustment (Preference channel); (2) an LLM meta-controller operating on framework-level parameters rather than low-level search variables; (3) a persistent Memory DB with 7 relational tables for cross-round learning. Its core metric, Influence Share, provides a decomposable measure where all factor contributions sum to exactly 100%. Sortify has been deployed across two markets. In Country A, the agent pushed GMV from -3.6% to +9.2% within 7 rounds with peak orders reaching +12.5%. In Country B, a cold-start deployment achieved +4.15% GMV/UU and +3.58% Ads Revenue in a 7-day A/B test, leading to full production rollout. --- ### When Surfaces Lie: Exploiting Wrinkle-Induced Attention Shift to Attack Vision-Language Models Authors: Chengyin Hu, Xuemeng Sun, Jiaju Han, Qike Zhang, Xiang Chen, Xin Wang, Yiwei Wei, Jiahua Long Published: 2026-03-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.27759v3 Visual-Language Models (VLMs) have demonstrated exceptional cross-modal understanding across various tasks, including zero-shot classification, image captioning, and visual question answering. However, their robustness to physically plausible non-rigid deformations-such as wrinkles on flexible surfaces-remains poorly understood. In this work, we propose a parametric structural perturbation method inspired by the mechanics of three-dimensional fabric wrinkles. Specifically, our method generates photorealistic non-rigid perturbations by constructing multi-scale wrinkle fields and integrating displacement field distortion with surface-consistent appearance variations. To achieve an optimal balance between visual naturalness and adversarial effectiveness, we design a hierarchical fitness function in a low-dimensional parameter space and employ an optimization-based search strategy. We evaluate our approach using a two-stage framework: perturbations are first optimized on a zero-shot classification proxy task and subsequently assessed for transferability on generative tasks. Experimental results demonstrate that our method significantly degrades the performance of various state-of-the-art VLMs, consistently outperforming baselines in both image captioning and visual question-answering tasks. --- ### RHO: Robust Holistic OSM-Based Metric Cross-View Geo-Localization Authors: Junwei Zheng, Ruize Dai, Ruiping Liu, Zichao Zeng, Yufan Chen, Fangjinhua Wang, Kunyu Peng, Kailun Yang, Jiaming Zhang, Rainer Stiefelhagen Published: 2026-03-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.27758v2 Metric Cross-View Geo-Localization (MCVGL) aims to estimate the 3-DoF camera pose (position and heading) by matching ground and satellite images. In this work, instead of pinhole and satellite images, we study robust MCVGL using holistic panoramas and OpenStreetMap (OSM). To this end, we establish a large-scale MCVGL benchmark dataset, CV-RHO, with over 2.7M images under different weather and lighting conditions, as well as sensor noise. Furthermore, we propose a model termed RHO with a two-branch Pin-Pan architecture for accurate visual localization. A Split-Undistort-Merge (SUM) module is introduced to address the panoramic distortion, and a Position-Orientation Fusion (POF) mechanism is designed to enhance the localization accuracy. Extensive experiments prove the value of our CV-RHO dataset and the effectiveness of the RHO model, with a significant performance gain up to 20% compared with the state-of-the-art baselines. Project page: https://github.com/InSAI-Lab/RHO. --- ### E-TIDE: Fast, Structure-Preserving Motion Forecasting from Event Sequences Authors: Biswadeep Sen, Benoit R. Cottereau, Nicolas Cuperlier, Terence Sim Published: 2026-03-29 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2603.27757v2 Event-based cameras capture visual information as asynchronous streams of per-pixel brightness changes, generating sparse, temporally precise data. Compared to conventional frame-based sensors, they offer significant advantages in capturing high-speed dynamics while consuming substantially less power. Predicting future event representations from past observations is an important problem, enabling downstream tasks such as future semantic segmentation or object tracking without requiring access to future sensor measurements. While recent state-of-the-art approaches achieve strong performance, they often rely on computationally heavy backbones and, in some cases, large-scale pretraining, limiting their applicability in resource-constrained scenarios. In this work, we introduce E-TIDE, a lightweight, end-to-end trainable architecture for event-tensor prediction that is designed to operate efficiently without large-scale pretraining. Our approach employs the TIDE module (Temporal Interaction for Dynamic Events), motivated by efficient spatiotemporal interaction design for sparse event tensors, to capture temporal dependencies via large-kernel mixing and activity-aware gating while maintaining low computational complexity. Experiments on standard event-based datasets demonstrate that our method achieves competitive performance with significantly reduced model size and training requirements, making it well-suited for real-time deployment under tight latency and memory budgets. --- ### Heracles: Bridging Precise Tracking and Generative Synthesis for General Humanoid Control Authors: Zelin Tao, Zeran Su, Peiran Liu, Jingkai Sun, Wenqiang Que, Jiahao Ma, Jialin Yu, Jiahang Cao, Pihai Sun, Hao Liang, Gang Han, Wen Zhao et al. Published: 2026-03-29 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2603.27756v2 Achieving general-purpose humanoid control requires a delicate balance between the precise execution of commanded motions and the flexible, anthropomorphic adaptability needed to recover from unpredictable environmental perturbations. Current general controllers predominantly formulate motion control as a rigid reference-tracking problem. While effective in nominal conditions, these trackers often exhibit brittle, non-anthropomorphic failure modes under severe disturbances, lacking the generative adaptability inherent to human motor control. To overcome this limitation, we propose Heracles, a novel state-conditioned diffusion middleware that bridges precise motion tracking and generative synthesis. Rather than relying on rigid tracking paradigms or complex explicit mode-switching, Heracles operates as an intermediary layer between high-level reference motions and low-level physics trackers. By conditioning on the robot's real-time state, the diffusion model implicitly adapts its behavior: it approximates an identity map when the state closely aligns with the reference, preserving zero-shot tracking fidelity. Conversely, when encountering significant state deviations, it seamlessly transitions into a generative synthesizer to produce natural, anthropomorphic recovery trajectories. Our framework demonstrates that integrating generative priors into the control loop not only significantly enhances robustness against extreme perturbations but also elevates humanoid control from a rigid tracking paradigm to an open-ended, generative general-purpose architecture. --- ### Retromorphic Testing with Hierarchical Verification for Hallucination Detection in RAG Authors: Boxi Yu, Yuzhong Zhang, Liting Lin, Lionel Briand, Emir Muñoz Published: 2026-03-29 Categories: cs.CL, cs.SE arXiv: https://arxiv.org/abs/2603.27752v2 Large language models can still hallucinate in retrieval-augmented generation (RAG), producing claims that are unsupported by or conflict with the retrieved context. Detecting such errors remains challenging when faithfulness is judged solely against the retrieved context: many existing detectors return holistic answer-level scores, while others target open-domain factuality or fail to provide evidence-grounded diagnostics. We present RT4CHART, a retromorphic testing framework for context-faithfulness assessment. RT4CHART decomposes an answer into independently verifiable claims, performs hierarchical local-to-global verification against the retrieved context, and assigns each claim one of three labels: entailed, contradicted, or baseless. It further maps these claim-level decisions back to specific answer spans and returns explicit context-side evidence, enabling fine-grained auditing rather than opaque scoring. We evaluate RT4CHART on RAGTruth++ (408 samples) and our re-annotated RAGTruth-Enhance (2,675 samples). RT4CHART achieves the best answer-level hallucination-detection F1 score among the evaluated baselines. On RAGTruth++, it attains a precision of 0.845, a recall of 0.718, and an F1 score of 0.776, representing an 83% relative improvement over the strongest baseline. It also achieves a span-level F1 score of 47.5% on RAGTruth-Enhance. Ablation studies show that claim-based local processing drives most of the observed improvement, while global verification provides selective benefits across datasets. Finally, our re-annotation identifies 1.68X more hallucination cases than the original labels, suggesting that commonly used benchmarks substantially underestimate the prevalence of hallucination. --- ### SkyNet: Belief-Aware Planning for Partially-Observable Stochastic Games Authors: Adam Haile Published: 2026-03-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.27751v1 In 2019, Google DeepMind released MuZero, a model-based reinforcement learning method that achieves strong results in perfect-information games by combining learned dynamics models with Monte Carlo Tree Search (MCTS). However, comparatively little work has extended MuZero to partially observable, stochastic, multi-player environments, where agents must act under uncertainty about hidden state. Such settings arise not only in card games but in domains such as autonomous negotiation, financial trading, and multi-agent robotics. In the absence of explicit belief modeling, MuZero's latent encoding has no dedicated mechanism for representing uncertainty over unobserved variables. To address this, we introduce SkyNet (Belief-Aware MuZero), which adds ego-conditioned auxiliary heads for winner prediction and rank estimation to the standard MuZero architecture. These objectives encourage the latent state to retain information predictive of outcomes under partial observability, without requiring explicit belief-state tracking or changes to the search algorithm. We evaluate SkyNet on Skyjo, a partially observable, non-zero-sum, stochastic card game, using a decision-granularity environment, transformer-based encoding, and a curriculum of heuristic opponents with self-play. In 1000-game head-to-head evaluations at matched checkpoints, SkyNet achieves a 75.3% peak win rate against the baseline (+194 Elo, $p < 10^{-50}$). SkyNet also outperforms the baseline against heuristic opponents (0.720 vs.\ 0.466 win rate). Critically, the belief-aware model initially underperforms the baseline but decisively surpasses it once training throughput is sufficient, suggesting that belief-aware auxiliary supervision improves learned representations under partial observability, but only given adequate data flow. --- ### AI-Powered Facial Mask Removal Is Not Suitable For Identification Authors: Emily A Cooper, Hany Farid Published: 2026-03-29 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.27747v2 Recently, crowd-sourced online criminal investigations have used generative-AI to enhance low-quality visual evidence. In one high-profile case, social-media users circulated an "AI-unmasked" image of a federal agent involved in a fatal shooting, fueling a wide-spread misidentification. In response to this and similar incidents, we conducted a large-scale analysis evaluating the efficacy and risks of commercial AI-powered facial unmasking, specifically assessing whether the resulting faces can be reliably matched to true identities. --- ### Needle in the Repo: A Benchmark for Maintainability in AI-Generated Repository Edits Authors: Haichao Zhu, Qian Zhang, Jiyuan Wang, Zhaorui Yang, Yuxin Qiu Published: 2026-03-29 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2603.27745v1 AI coding agents can now complete complex programming tasks, but existing evaluations largely emphasize behavioral correctness and often overlook maintainability risks such as weak modularity or testability. We present Needle in the Repo (NITR), a diagnostic probe-and-oracle framework for evaluating whether behaviorally correct repository edits preserve maintainable structure. NITR distills recurring software engineering wisdom into controlled probes embedded in small, realistic multi-file codebases, each designed so that success depends primarily on one targeted maintainability dimension. Each probe is paired with a hidden evaluation harness that combines functional tests for required behavior with structural oracles that encode the targeted maintainability constraint and return interpretable diagnoses. Using NITR, we evaluate 23 coding configurations across GPT, Claude, Gemini, and Qwen families in both direct-inference and agent-based settings. Current AI coding systems remain far from robust: on average, configurations solve only 36.2% of cases, the best reaches 57.1%, and performance drops from 53.5% on micro cases to 20.6% on multi-step cases. The hardest pressures are architectural rather than local edits, especially dependency control (4.3%) and responsibility decomposition (15.2%). Moreover, 64/483 outcomes (13.3%) pass all functional tests yet fail the structural oracle. Under our harness, agent-mode configurations improve average performance from 28.2% to 45.0%, but do not eliminate these architectural failures. These results show that progress in code generation is not yet progress in maintainable code evolution, and that NITR exposes a critical failure surface missed by conventional evaluation. --- ### Data Organization Matters in Multimodal Instruction Tuning: A Controlled Study of Capability Trade-offs Authors: Guowei Tang Published: 2026-03-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.27744v1 Recent multimodal large language models (MLLMs) perform strongly on general visual understanding, diagram and chart reasoning, and document-centric perception. However, these abilities are learned from heterogeneous supervision sources with very different task structures and learning demands, and the effect of their temporal organization during training remains underexplored. We study whether data organization affects the trade-off among general understanding, structured reasoning, and fine-grained OCR/document understanding in multimodal instruction tuning. To isolate this factor, we use a controlled three-stage training framework in which the backbone, trainable modules, and optimization pipeline are fixed across all runs, and only the temporal arrangement of post-alignment supervision is changed. We compare four strategies: direct mixture, curriculum training, balanced sampling, and reverse curriculum. Experiments on general visual instruction following, diagram reasoning, chart reasoning, scene-text question answering, and document question answering show that data organization is a first-order design variable in multimodal adaptation. Curriculum training gives the best overall trade-off and the strongest structured reasoning performance. Balanced sampling is better for OCR-oriented capability but weakens the broader capability balance. Reverse curriculum performs worst in both final performance and optimization stability. Training-dynamics analysis further suggests that building general understanding and reasoning before introducing OCR-intensive supervision leads to smoother optimization and faster convergence. These findings highlight data scheduling as an explicit design dimension for multimodal model adaptation. --- ### Empirical Likelihood for Nonsmooth Functionals Authors: Hongseok Namkoong Published: 2026-03-29 Categories: stat.ME, cs.LG arXiv: https://arxiv.org/abs/2603.27743v1 Empirical likelihood is an attractive inferential framework that respects natural parameter boundaries, but existing approaches typically require smoothness of the functional and miscalibrate substantially when these assumptions are violated. For the optimal-value functional central to policy evaluation, smoothness holds only when the optimum is unique -- a condition that fails exactly when rigorous inference is most needed where more complex policies have modest gains. In this work, we develop a bootstrap empirical likelihood method for partially nonsmooth functionals. Our analytic workhorse is a geometric reduction of the profile likelihood to the distance between the score mean and a level set whose shape (a tangent cone given by nonsmoothness patterns) determines the asymptotic distribution. Unlike the classical proof technology based on Taylor expansions on the dual optima, our geometric approach leverages properties of a deterministic convex program and can directly apply to nonsmooth functionals. Since the ordinary bootstrap is not valid in the presence of nonsmoothness, we derive a corrected multiplier bootstrap approach that adapts to the unknown level-set geometry. --- ### TIR-Agent: Training an Explorative and Efficient Agent for Image Restoration Authors: Guoli Jia, Yisheng Zhang, Haote Hu, Shanxu Zhao, Kaikai Zhao, Long Sun, Xinwei Long, Kai Tian, Che Jiang, Zhaoxiang Liu, Kai Wang, Shiguo Lian et al. Published: 2026-03-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.27742v2 Vision-language agents that orchestrate specialized tools for image restoration (IR) have emerged as a promising method, yet most existing frameworks operate in a training-free manner. They rely on heuristic task scheduling and exhaustive tool traversal, resulting in sub-optimal restoration paths and prohibitive computational cost. We argue that the core bottleneck lies in the absence of a learned policy to make decision, as a vision-language model cannot efficiently handle degradation-aware task ordering and tool composition. To this end, we propose TIR-Agent, a trainable image restoration agent that performs a direct tool-calling policy through a two-stage training pipeline of supervised fine-tuning (SFT) followed by reinforcement learning (RL). Two key designs underpin effective RL training: (i) a random perturbation strategy applied to the SFT data, which broadens the policy's exploration over task schedules and tool compositions, and (ii) a multi-dimensional adaptive reward mechanism that dynamically re-weights heterogeneous image quality metrics to mitigate reward hacking. To support high-throughput, asynchronous GPU-based tool invocation during training, we further develop a globally shared model-call pool. Experiments on both in-domain and out-of-domain degradations show that TIR-Agent outperforms 12 baselines, including 6 all-in-one models, 3 training-free agents, and 3 proprietary models, and achieves over 2.5$\times$ inference speedup by eliminating redundant tool executions. --- ### Segmenting Superbubbles in a Simulated Multiphase Interstellar Medium using Computer Vision Authors: Jing-Wen Chen, Alex S. Hill, Anna Ordog, Rebecca A. Booth, Mohamed S. Shehata Published: 2026-03-29 Categories: astro-ph.GA, cs.CV arXiv: https://arxiv.org/abs/2603.27741v1 We developed a computer vision-based methodology to achieve precise 3D segmentation and tracking of superbubbles within magnetohydrodynamic simulations of the supernova-driven interstellar medium. Leveraging advanced 3D transformer models, our approach effectively captures the complex morphology and dynamic evolution of these astrophysical structures. To demonstrate the technique, we specifically focused on a superbubble exhibiting interesting interactions with its surrounding medium, driven by a series of successive supernova explosions. Our model successfully generated detailed 3D segmentation masks, enabling us to visualize and analyze the bubble's structural evolution over time. The results reveal insights into the superbubble's growth patterns, energy retention, and interactions with surrounding interstellar matter. This interdisciplinary approach not only enhances our understanding of superbubble dynamics but also offers a robust framework for investigating other complex phenomena in the cosmos. --- ### TianJi:An autonomous AI meteorologist for discovering physical mechanisms in atmospheric science Authors: Kaikai Zhang, Xiang Wang, Haoluo Zhao, Nan Chen, Mengyang Yu Jing-Jia Luo, Tao Song, Fan Meng Published: 2026-03-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.27738v1 Artificial intelligence (AI) has achieved breakthroughs comparable to traditional numerical models in data-driven weather forecasting, yet it remains essentially statistical fitting and struggles to uncover the physical causal mechanisms of the atmosphere. Physics-oriented mechanism research still heavily relies on domain knowledge and cumbersome engineering operations of human scientists, becoming a bottleneck restricting the efficiency of Earth system science exploration. Here, we propose TianJi - the first "AI meteorologist" system capable of autonomously driving complex numerical models to verify physical mechanisms. Powered by a large language model-driven multi-agent architecture, TianJi can autonomously conduct literature research and generate scientific hypotheses. We further decouple scientific research into cognitive planning and engineering execution: the meta-planner interprets hypotheses and devises experimental roadmaps, while a cohort of specialized worker agents collaboratively complete data preparation, model configuration, and multi-dimensional result analysis. In two classic atmospheric dynamic scenarios (squall-line cold pools and typhoon track deflections), TianJi accomplishes expert-level end-to-end experimental operations with zero human intervention, compressing the research cycle to a few hours. It also delivers detailed result analyses and autonomously judges and explains the validity of the hypotheses from outputs. TianJi reveals that the role of AI in Earth system science is transitioning from a "black-box predictor" to an "interpretable scientific collaborator", offering a new paradigm for high-throughput exploration of scientific mechanisms. --- ### Synergizing Discriminative Exemplars and Self-Refined Experience for MLLM-based In-Context Learning in Medical Diagnosis Authors: Wenkai Zhao, Zipei Wang, Mengjie Fang, Di Dong, Jie Tian, Lingwei Zhang Published: 2026-03-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.27737v2 General Multimodal Large Language Models (MLLMs) often underperform in capturing domain-specific nuances in medical diagnosis, trailing behind fully supervised baselines. Although fine-tuning provides a remedy, the high costs of expert annotation and massive computational overhead limit its scalability. To bridge this gap without updating the weights of the pre-trained backbone of the MLLM, we propose a Clinician Mimetic Workflow. This is a novel In-Context Learning (ICL) framework designed to synergize Discriminative Exemplar Coreset Selection (DECS) and Self-Refined Experience Summarization (SRES). Specifically, DECS simulates a clinician's ability to reference "anchor cases" by selecting discriminative visual coresets from noisy data at the computational level; meanwhile, SRES mimics the cognition and reflection in clinical diagnosis by distilling diverse rollouts into a dynamic textual Experience Bank. Extensive evaluation across all 12 datasets of the MedMNIST 2D benchmark demonstrates that our method outperforms zero-shot general and medical MLLMs. Simultaneously, it achieves performance levels comparable to fully supervised vision models and domain-specific fine-tuned MLLMs, setting a new benchmark for parameter-efficient medical in-context learning. Our code is available at an anonymous repository: https://anonymous.4open.science/r/Synergizing-Discriminative-Exemplars-and-Self-Refined-Experience-ED74. --- ### Synergizing Discriminative Exemplars and Self-Refined Experience for MLLM-based In-Context Learning in Medical Diagnosis Authors: Wenkai Zhao, Zipei Wang, Mengjie Fang, Di Dong, Jie Tian, Lingwei Zhang Published: 2026-03-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.27737v1 General Multimodal Large Language Models (MLLMs) often underperform in capturing domain-specific nuances in medical diagnosis, trailing behind fully supervised baselines. Although fine-tuning provides a remedy, the high costs of expert annotation and massive computational overhead limit its scalability. To bridge this gap without updating the weights of the pre-trained backbone of the MLLM, we propose a Clinician Mimetic Workflow. This is a novel In-Context Learning (ICL) framework designed to synergize Discriminative Exemplar Coreset Selection (DECS) and Self-Refined Experience Summarization (SRES). Specifically, DECS simulates a clinician's ability to reference "anchor cases" by selecting discriminative visual coresets from noisy data at the computational level; meanwhile, SRES mimics the cognition and reflection in clinical diagnosis by distilling diverse rollouts into a dynamic textual Experience Bank. Extensive evaluation across all 12 datasets of the MedMNIST 2D benchmark demonstrates that our method outperforms zero-shot general and medical MLLMs. Simultaneously, it achieves performance levels comparable to fully supervised vision models and domain-specific fine-tuned MLLMs, setting a new benchmark for parameter-efficient medical in-context learning. Our code is available at an anonymous repository: https://anonymous.4open.science/r/Synergizing-Discriminative-Exemplars-and-Self-Refined-Experience-ED74. --- ### Robust Smart Contract Vulnerability Detection via Contrastive Learning-Enhanced Granular-ball Training Authors: Zeli Wang, Qingxuan Yang, Shuyin Xia, Yueming Wu, Bo Liu, Longlong Lin Published: 2026-03-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.27734v1 Deep neural networks (DNNs) have emerged as a prominent approach for detecting smart contract vulnerabilities, driven by the growing contract datasets and advanced deep learning techniques. However, DNNs typically require large-scale labeled datasets to model the relationships between contract features and vulnerability labels. In practice, the labeling process often depends on existing open-sourced tools, whose accuracy cannot be guaranteed. Consequently, label noise poses a significant challenge for the accuracy and robustness of the smart contract, which is rarely explored in the literature. To this end, we propose Contrastive learning-enhanced Granular-Ball smart Contracts training, CGBC, to enhance the robustness of contract vulnerability detection. Specifically, CGBC first introduces a Granular-ball computing layer between the encoder layer and the classifier layer, to group similar contracts into Granular-Balls (GBs) and generate new coarse-grained representations (i.e., the center and the label of GBs) for them, which can correct noisy labels based on the most correct samples. An inter-GB compactness loss and an intra-GB looseness loss are combined to enhance the effectiveness of clustering. Then, to improve the accuracy of GBs, we pretrain the model through unsupervised contrastive learning supported by our novel semantic-consistent smart contract augmentation method. This procedure can discriminate contracts with different labels by dragging the representation of similar contracts closer, assisting CGBC in clustering. Subsequently, we leverage the symmetric cross-entropy loss function to measure the model quality, which can combat the label noise in gradient computations. Finally, extensive experiments show that the proposed CGBC can significantly improve the robustness and effectiveness of the smart contract vulnerability detection when contrasted with baselines. --- ### Suppression of $^{14}\mathrm{C}$ photon hits in large liquid scintillator detectors via spatiotemporal deep learning Authors: Junle Li, Zhaoxiang Wu, Guanda Gong, Zhaohan Li, Wuming Luo, Jiahui Wei, Wenxing Fang, Hehe Fan Published: 2026-03-29 Categories: physics.ins-det, cs.AI, hep-ex arXiv: https://arxiv.org/abs/2603.27727v1 Liquid scintillator detectors are widely used in neutrino experiments due to their low energy threshold and high energy resolution. Despite the tiny abundance of $^{14}$C in LS, the photons induced by the $β$ decay of the $^{14}$C isotope inevitably contaminate the signal, degrading the energy resolution. In this work, we propose three models to tag $^{14}$C photon hits in $e^+$ events with $^{14}$C pile-up, thereby suppressing its impact on the energy resolution at the hit level: a gated spatiotemporal graph neural network and two Transformer-based models with scalar and vector charge encoding. For a simulation dataset in which each event contains one $^{14}$C and one $e^+$ with kinetic energy below 5 MeV, the models achieve $^{14}$C recall rates of 25%-48% while maintaining $e^+$ to $^{14}$C misidentification below 1%, leading to a large improvement in the resolution of total charge for events where $e^+$ and $^{14}$C photon hits strongly overlap in space and time. --- ### TMTE: Effective Multimodal Graph Learning with Task-aware Modality and Topology Co-evolution Authors: Yinlin Zhu, Xunkai Li, Di Wu, Wang Luo, Miao Hu, Guocong Quan Published: 2026-03-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.27723v2 Multimodal-attributed graphs (MAGs) are a fundamental data structure for multimodal graph learning (MGL), enabling both graph-centric and modality-centric tasks. However, our empirical analysis reveals inherent topology quality limitations in real-world MAGs, including noisy interactions, missing connections, and task-agnostic relational structures. A single graph derived from generic relationships is therefore unlikely to be universally optimal for diverse downstream tasks. To address this challenge, we propose Task-aware Modality and Topology co-Evolution (TMTE), a novel MGL framework that jointly and iteratively optimizes graph topology and multimodal representations toward the target task. TMTE is motivated by the bidirectional coupling between modality and topology: multimodal attributes induce relational structures, while graph topology shapes modality representations. Concretely, TMTE casts topology evolution as multi-perspective metric learning over modality embeddings with an anchor-based approximation, and formulates modality evolution as smoothness-regularized fusion with cross-modal alignment, yielding a closed-loop task-aware co-evolution process. Extensive experiments on 9 MAG datasets and 1 non-graph multimodal dataset across 6 graph-centric and modality-centric tasks show that TMTE consistently achieves state-of-the-art performance. Our code is available at https://anonymous.4open.science/r/TMTE-1873. --- ### TMTE: Effective Multimodal Graph Learning with Task-aware Modality and Topology Co-evolution Authors: Yinlin Zhu, Xunkai Li, Di Wu, Wang Luo, Miao Hu, Di Wu Published: 2026-03-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.27723v1 Multimodal-attributed graphs (MAGs) are a fundamental data structure for multimodal graph learning (MGL), enabling both graph-centric and modality-centric tasks. However, our empirical analysis reveals inherent topology quality limitations in real-world MAGs, including noisy interactions, missing connections, and task-agnostic relational structures. A single graph derived from generic relationships is therefore unlikely to be universally optimal for diverse downstream tasks. To address this challenge, we propose Task-aware Modality and Topology co-Evolution (TMTE), a novel MGL framework that jointly and iteratively optimizes graph topology and multimodal representations toward the target task. TMTE is motivated by the bidirectional coupling between modality and topology: multimodal attributes induce relational structures, while graph topology shapes modality representations. Concretely, TMTE casts topology evolution as multi-perspective metric learning over modality embeddings with an anchor-based approximation, and formulates modality evolution as smoothness-regularized fusion with cross-modal alignment, yielding a closed-loop task-aware co-evolution process. Extensive experiments on 9 MAG datasets and 1 non-graph multimodal dataset across 6 graph-centric and modality-centric tasks show that TMTE consistently achieves state-of-the-art performance. Our code is available at https://anonymous.4open.science/r/TMTE-1873. --- ### Look, Compare and Draw: Differential Query Transformer for Automatic Oil Painting Authors: Lingyu Liu, Yaxiong Wang, Li Zhu, Lizi Liao, Zhedong Zheng Published: 2026-03-29 Categories: cs.CV, cs.MM arXiv: https://arxiv.org/abs/2603.27720v1 This work introduces a new approach to automatic oil painting that emphasizes the creation of dynamic and expressive brushstrokes. A pivotal challenge lies in mitigating the duplicate and common-place strokes, which often lead to less aesthetic outcomes. Inspired by the human painting process, \ie, observing, comparing, and drawing, we incorporate differential image analysis into a neural oil painting model, allowing the model to effectively concentrate on the incremental impact of successive brushstrokes. To operationalize this concept, we propose the Differential Query Transformer (DQ-Transformer), a new architecture that leverages differentially derived image representations enriched with positional encoding to guide the stroke prediction process. This integration enables the model to maintain heightened sensitivity to local details, resulting in more refined and nuanced stroke generation. Furthermore, we incorporate adversarial training into our framework, enhancing the accuracy of stroke prediction and thereby improving the overall realism and fidelity of the synthesized paintings. Extensive qualitative evaluations, complemented by a controlled user study, validate that our DQ-Transformer surpasses existing methods in both visual realism and artistic authenticity, typically achieving these results with fewer strokes. The stroke-by-stroke painting animations are available on our project website. --- ### The role of neuromorphic principles in the future of biomedicine and healthcare Authors: Grace M. Hwang, Jessica D. Falcone, Joseph D. Monaco, Courtney R. Pinard, Jessica A. Mollick, Roger L. Miller, Stephanie L. Gage, Andrey V. Kanaev, Margaret Kim, R. Ale Lukaszew, Steven M. Zehnder, David Rampulla Published: 2026-03-29 Categories: cs.NE, cs.AI, q-bio.NC arXiv: https://arxiv.org/abs/2603.27716v1 Neuromorphic engineering has matured over the past four decades and is currently experiencing explosive growth with the potential to transform biomedical engineering and neurotechnologies. Participants at the Neuromorphic Principles in Biomedicine and Healthcare (NPBH) Workshop (October 2024) -- representing a broad cross-section of the community, including early-career and established scholars, engineers, scientists, clinicians, industry, and funders -- convened to discuss the state of the field, current and future challenges, and strategies for advancing neuromorphic research and development for biomedical applications. Publicly approved recordings with transcripts (https://2024.neuro-med.org/program/session-video-and-transcripts) and slides (https://2024.neuro-med.org/program/session-slides) can be found at the workshop website. --- ### Low-Rank Adaptation Reduces Catastrophic Forgetting in Sequential Transformer Encoder Fine-Tuning: Controlled Empirical Evidence and Frozen-Backbone Representation Probes Authors: Ashish Pandey Published: 2026-03-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.27707v1 Sequential fine-tuning of pretrained language encoders often overwrites previously acquired capabilities, but the forgetting behavior of parameter-efficient updates remains under-characterized. We present a controlled empirical study of Low-Rank Adaptation (LoRA) in sequential transformer encoder fine-tuning with companion representation probes that test a frozen-backbone explanation of its robustness. In five full-validation BERT-base reruns on an RTE->MRPC->CoLA->SST-2 sequence, full fine-tuning yields 19.9%+/-4.8% average forgetting, whereas standard LoRA (r=8, query/value modules) yields 0.6%+/-1.4% (paired t-test, p=0.002, Cohen's d_s=3.12). Task-level analyses confirm this reduction is not merely an aggregate effect. Secondary experiments on RoBERTa-base show the same pattern, and the strongest EWC baseline remains at 15.5%+/-1.4% forgetting. A six-task extension reveals that low average forgetting can hide strong task-level heterogeneity. Fine-grained freezing ablations show a marked forgetting drop once frozen parameters exceed roughly 95%, with classifier-only and shallow-adapter baselines approaching LoRA. Companion task-similarity probes in GPT-2 and RoBERTa show the same directional story: frozen-backbone regimes preserve higher inter-task similarity than full fine-tuning, gradual unfreezing weakens stability, and full fine-tuning exhibits its clearest divergence at the final transformer layer. These results support a restrained mechanistic interpretation: LoRA helps largely because backbone freezing preserves a more stable shared feature scaffold. We position standard LoRA as both a strong empirical baseline for sequential encoder adaptation and a useful probe of how selective plasticity shapes interference in transformer continual learning. --- ### RAP: Retrieve, Adapt, and Prompt-Fit for Training-Free Few-Shot Medical Image Segmentation Authors: Zhihao Mao, Bangpu Chen Published: 2026-03-29 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.27705v1 Few-shot medical image segmentation (FSMIS) has achieved notable progress, yet most existing methods mainly rely on semantic correspondences from scarce annotations while under-utilizing a key property of medical imagery: anatomical targets exhibit repeatable high-frequency morphology (e.g., boundary geometry and spatial layout) across patients and acquisitions. We propose RAP, a training-free framework that retrieves, adapts, and prompts Segment Anything Model 2 (SAM2) for FSMIS. First, RAP retrieves morphologically compatible supports from an archive using DINOv3 features to reduce brittleness in single-support choice. Second, it adapts the retrieved support mask to the query by fitting boundary-aware structural cues, yielding an anatomy-consistent pre-mask under domain shifts. Third, RAP converts the pre-mask into prompts by sampling positive points via Voronoi partitioning and negative points via sector-based sampling, and feeds them into SAM2 for final refinement without any fine-tuning. Extensive experiments on multiple medical segmentation benchmarks show that RAP consistently surpasses prior FSMIS baselines and achieves state-of-the-art performance. Overall, RAP demonstrates that explicit structural fitting combined with retrieval-augmented prompting offers a simple and effective route to robust training-free few-shot medical segmentation. --- ### KAT-Coder-V2 Technical Report Authors: Fengxiang Li, Han Zhang, Haoyang Huang, Jinghui Wang, Jinhua Hao, Kun Yuan, Mengtong Li, Minglei Zhang, Pengcheng Xu, Wenhao Zhuang, Yizhen Shao, Zongxian Feng et al. Published: 2026-03-29 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.27703v1 We present KAT-Coder-V2, an agentic coding model developed by the KwaiKAT team at Kuaishou. KAT-Coder-V2 adopts a "Specialize-then-Unify" paradigm that decomposes agentic coding into five expert domains - SWE, WebCoding, Terminal, WebSearch, and General - each undergoing independent supervised fine-tuning and reinforcement learning, before being consolidated into a single model via on-policy distillation. We develop KwaiEnv, a modular infrastructure sustaining tens of thousands of concurrent sandbox instances, and scale RL training along task complexity, intent alignment, and scaffold generalization. We further propose MCLA for stabilizing MoE RL training and Tree Training for eliminating redundant computation over tree-structured trajectories with up to 6.2x speedup. KAT-Coder-V2 achieves 79.6% on SWE-bench Verified (vs. Claude Opus 4.6 at 80.8%), 88.7 on PinchBench (surpassing GLM-5 and MiniMax M2.7), ranks first across all three frontend aesthetics scenarios, and maintains strong generalist scores on Terminal-Bench Hard (46.8) and tau^2-Bench (93.9). Our model is publicly available at https://streamlake.com/product/kat-coder. --- ### Ink Detection from Surface Topography of the Herculaneum Papyri Authors: Giorgio Angelotti, Federica Nicolardi, Paul Henderson, W. Brent Seales Published: 2026-03-29 Categories: cs.CV, cs.DL arXiv: https://arxiv.org/abs/2603.27698v1 Reading the Herculaneum papyri is challenging because both the scrolls and the ink, which is carbon-based, are carbonized. In X-ray radiography and tomography, ink detection typically relies on density- or composition-driven contrast, but carbon ink on carbonized papyrus provides little attenuation contrast. Building on the morphological hypothesis, we show that the surface morphology of written regions contains enough signal to distinguish ink from papyrus. To this end, we train machine learning models on three-dimensional optical profilometry from mechanically opened Herculaneum papyri to separate inked and uninked areas. We further quantify how lateral sampling governs learnability and how a native-resolution model behaves on coarsened inputs. We show that high-resolution topography alone contains a usable signal for ink detection. Diminishing segmentation performance with decreasing lateral resolution provides insight into the characteristic spatial scales that must be resolved on our dataset to exploit the morphological signal. These findings inform spatial resolution targets for morphology-based reading of closed scrolls through X-ray tomography. ---