# Research Papers — 2026-03 · bundle page 162 of 243

> Full-text markdown of papers #8051–8100 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/162
[← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/161.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-03/page/163.md)

### UAV traffic scene understanding: A regulation embedded multi-modal network and a unified benchmark

Authors: Yu Zhang, Zhicheng Zhao, Ze Luo, Chenglong Li, Jin Tang
Published: 2026-03-11
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.10722v2

Traffic scene understanding from unmanned aerial vehicle (UAV) platforms is crucial for intelligent transportation systems due to its flexible deployment and wide-area monitoring capabilities. However, existing methods face significant challenges in real-world surveillance, as their heavy reliance on optical imagery leads to severe performance degradation under adverse illumination conditions like nighttime and fog. Furthermore, current Visual Question Answering (VQA) models are restricted to elementary perception tasks, lacking the domain-specific regulatory knowledge required to assess complex traffic behaviors. To address these limitations, we propose a novel Multi-modal Traffic Cognition Network (MTCNet) for robust UAV traffic scene understanding. Specifically, we design a Prototype-Guided Knowledge Embedding (PGKE) module that leverages high-level semantic prototypes from an external Traffic Regulation Memory (TRM) to anchor domain-specific knowledge into visual representations, enabling the model to comprehend complex behaviors and distinguish fine-grained traffic violations. Moreover, we develop a Quality-Aware Spectral Compensation (QASC) module that exploits the complementary characteristics of optical and thermal modalities to perform bidirectional context exchange, effectively compensating for degraded features to ensure robust representation in complex environments. In addition, we construct Traffic-VQA, the first large-scale optical-thermal infrared benchmark for cognitive UAV traffic understanding, comprising 8,180 aligned image pairs and 1.3 million question-answer pairs across 31 diverse types. Extensive experiments demonstrate that MTCNet significantly outperforms state-of-the-art methods in both cognition and perception scenarios. The dataset is available at https://github.com/YuZhang-2004/UAV-traffic-scene-understanding.

---

### Sample-and-Search: An Effective Algorithm for Learning-Augmented k-Median Clustering in High dimensions

Authors: Kangke Cheng, Shihong Song, Guanlin Mo, Hu Ding
Published: 2026-03-11
Categories: cs.DS, cs.LG
arXiv: https://arxiv.org/abs/2603.10721v1

In this paper, we investigate the learning-augmented $k$-median clustering problem, which aims to improve the performance of traditional clustering algorithms by preprocessing the point set with a predictor of error rate $α\in (0,1)$. This preprocessing step assigns potential labels to the points before clustering. We introduce an algorithm for this problem based on a simple yet effective sampling method, which substantially improves upon the time complexities of existing algorithms. Moreover, we mitigate their exponential dependency on the dimensionality of the Euclidean space. Lastly, we conduct experiments to compare our method with several state-of-the-art learning-augmented $k$-median clustering methods. The experimental results suggest that our proposed approach can significantly reduce the computational complexity in practice, while achieving a lower clustering cost.

---

### Riemannian MeanFlow for One-Step Generation on Manifolds

Authors: Zichen Zhong, Haoliang Sun, Yukun Zhao, Yongshun Gong, Yilong Yin
Published: 2026-03-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.10718v3

Flow Matching enables simulation-free training of generative models on Riemannian manifolds, yet sampling typically still relies on numerically integrating a probability-flow ODE. We propose Riemannian MeanFlow (RMF), extending MeanFlow to manifold-valued generation where velocities lie in location-dependent tangent spaces. RMF defines an average-velocity field via parallel transport and derives a Riemannian MeanFlow identity that links average and instantaneous velocities for intrinsic supervision. We make this identity practical in a log-map tangent representation, avoiding trajectory simulation and heavy geometric computations. For stable optimization, we decompose the RMF objective into two terms and apply conflict-aware multi-task learning to mitigate gradient interference. RMF also supports conditional generation via classifier-free guidance. Experiments on spheres, tori, SO(3), and SE(3) demonstrate competitive one-step sampling with improved quality-efficiency trade-offs and substantially reduced sampling cost.

---

### Probabilistic Verification of Voice Anti-Spoofing Models

Authors: Evgeny Kushnir, Alexandr Kozodaev, Dmitrii Korzh, Mikhail Pautov, Oleg Kiriukhin, Oleg Y. Rogov
Published: 2026-03-11
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2603.10713v2

Recent advances in generative models have amplified the risk of malicious misuse of speech synthesis technologies, enabling adversaries to impersonate target speakers and access sensitive resources. Although speech deepfake detection has progressed rapidly, most existing countermeasures lack formal robustness guarantees or fail to generalize to unseen generation techniques. We propose PV-VASM, a probabilistic framework for verifying the robustness of voice anti-spoofing models (VASMs). PV-VASM estimates the probability of misclassification under text-to-speech (TTS), voice cloning (VC), and parametric signal transformations. The approach is model-agnostic and enables robustness verification against unseen speech synthesis techniques and input perturbations. We derive a theoretical upper bound on the error probability and validate the method across diverse experimental settings, demonstrating its effectiveness as a practical robustness verification tool.

---

### PRISM-$Δ$: Differential Subspace Steering for Prompt Highlighting in Large Language Models

Authors: Yuyao Ge, Shenghua Liu, Yiwei Wang, Baolong Bi, Lingrui Mei, Jiayu Yao, Jiafeng Guo, Xueqi Cheng
Published: 2026-03-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.10705v2

Prompt highlighting steers a large language model to prioritize user-specified text spans during generation. A key challenge of existing Key-editing approaches is extracting steering directions that capture the difference between relevant and irrelevant contexts, rather than shared structural patterns common to both. We propose PRISM-$Δ$ (Projection-based Relevance-Informed Steering Method), which decomposes the difference between positive and negative cross-covariance matrices to maximize discriminative energy while eliminating shared directions. Each attention head receives a continuous softplus importance weight, letting weak-but-useful heads contribute at reduced strength. The framework extends naturally to Value representations, capturing content-channel signal that Key-only methods leave unused. Across four benchmarks and five models, our methods match or exceed the best existing method on 19 of 20 configurations, with relative gains up to +13.0%, while halving the fluency cost of steering. Our methods also scale to long-context retrieval, outperforming the best existing method by up to +5.1% relative gain. PRISM-$Δ$ is compatible with FlashAttention and adds negligible memory overhead.

---

### Prism-$Δ$: Differential Subspace Steering for Prompt Highlighting in Large Language Models

Authors: Yuyao Ge, Shenghua Liu, Yiwei Wang, Tianyu Liu, Baolong Bi, Lingrui Mei, Jiayu Yao, Jiafeng Guo, Xueqi Cheng
Published: 2026-03-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.10705v1

Prompt highlighting steers a large language model to prioritize user-specified text spans during generation. A key challenge is extracting steering directions that capture the difference between relevant and irrelevant contexts, rather than shared structural patterns common to both. We propose PRISM-$Δ$ (Projection-based Relevance-Informed Steering Method), which decomposes the difference between positive and negative cross-covariance matrices to maximize discriminative energy while eliminating shared directions. Each attention head receives a continuous softplus importance weight, letting weak-but-useful heads contribute at reduced strength. The framework extends naturally to Value representations, capturing content-channel signal that Key-only methods leave unused. Across four benchmarks and five models, PRISM-$Δ$ matches or exceeds the best existing method on 19 of 20 configurations, with relative gains up to +10.6%, while halving the fluency cost of steering. PRISM-$Δ$ also scales to long-context retrieval, outperforming the best existing method by up to +4.8% relative gain. PRISM-$Δ$ is compatible with FlashAttention and adds negligible memory overhead.

---

### WalkGPT: Grounded Vision-Language Conversation with Depth-Aware Segmentation for Pedestrian Navigation

Authors: Rafi Ibn Sultan, Hui Zhu, Xiangyu Zhou, Chengyin Li, Prashant Khanduri, Marco Brocanelli, Dongxiao Zhu
Published: 2026-03-11
Categories: cs.CV, cs.CY
arXiv: https://arxiv.org/abs/2603.10703v1

Ensuring accessible pedestrian navigation requires reasoning about both semantic and spatial aspects of complex urban scenes, a challenge that existing Large Vision-Language Models (LVLMs) struggle to meet. Although these models can describe visual content, their lack of explicit grounding leads to object hallucinations and unreliable depth reasoning, limiting their usefulness for accessibility guidance. We introduce WalkGPT, a pixel-grounded LVLM for the new task of Grounded Navigation Guide, unifying language reasoning and segmentation within a single architecture for depth-aware accessibility guidance. Given a pedestrian-view image and a navigation query, WalkGPT generates a conversational response with segmentation masks that delineate accessible and harmful features, along with relative depth estimation. The model incorporates a Multi-Scale Query Projector (MSQP) that shapes the final image tokens by aggregating them along text tokens across spatial hierarchies, and a Calibrated Text Projector (CTP), guided by a proposed Region Alignment Loss, that maps language embeddings into segmentation-aware representations. These components enable fine-grained grounding and depth inference without user-provided cues or anchor points, allowing the model to generate complete and realistic navigation guidance. We also introduce PAVE, a large-scale benchmark of 41k pedestrian-view images paired with accessibility-aware questions and depth-grounded answers. Experiments show that WalkGPT achieves strong grounded reasoning and segmentation performance. The source code and dataset are available on the \href{https://sites.google.com/view/walkgpt-26/home}{project website}.

---

### UniCom: Unified Multimodal Modeling via Compressed Continuous Semantic Representations

Authors: Yaqi Zhao, Wang Lin, Zijian Zhang, Miles Yang, Jingyuan Chen, Wentao Zhang, Zhao Zhong, Liefeng Bo
Published: 2026-03-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.10702v1

Current unified multimodal models typically rely on discrete visual tokenizers to bridge the modality gap. However, discretization inevitably discards fine-grained semantic information, leading to suboptimal performance in visual understanding tasks. Conversely, directly modeling continuous semantic representations (e.g., CLIP, SigLIP) poses significant challenges in high-dimensional generative modeling, resulting in slow convergence and training instability. To resolve this dilemma, we introduce UniCom, a unified framework that harmonizes multimodal understanding and generation via compressed continuous representation. We empirically demonstrate that reducing channel dimension is significantly more effective than spatial downsampling for both reconstruction and generation. Accordingly, we design an attention-based semantic compressor to distill dense features into a compact unified representation. Furthermore, we validate that the transfusion architecture surpasses query-based designs in convergence and consistency. Experiments demonstrate that UniCom achieves state-of-the-art generation performance among unified models. Notably, by preserving rich semantic priors, it delivers exceptional controllability in image editing and maintains image consistency even without relying on VAE.

---

### AlphaFlowTSE: One-Step Generative Target Speaker Extraction via Conditional AlphaFlow

Authors: Duojia Li, Shuhan Zhang, Zihan Qian, Wenxuan Wu, Shuai Wang, Qingyang Hong, Lin Li, Haizhou Li
Published: 2026-03-11
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2603.10701v1

In target speaker extraction (TSE), we aim to recover target speech from a multi-talker mixture using a short enrollment utterance as reference. Recent studies on diffusion and flow-matching generators have improved target-speech fidelity. However, multi-step sampling increases latency, and one-step solutions often rely on a mixture-dependent time coordinate that can be unreliable for real-world conversations. We present AlphaFlowTSE, a one-step conditional generative model trained with a Jacobian-vector product (JVP)-free AlphaFlow objective. AlphaFlowTSE learns mean-velocity transport along a mixture-to-target trajectory starting from the observed mixture, eliminating auxiliary mixing-ratio prediction, and stabilizes training by combining flow matching with an interval-consistency teacher-student target. Experiments on Libri2Mix and REAL-T confirm that AlphaFlowTSE improves target-speaker similarity and real-mixture generalization for downstream automatic speech recognition (ASR).

---

### Structured Linked Data as a Memory Layer for Agent-Orchestrated Retrieval

Authors: Andrea Volpini, Elie Raad, Beatrice Gamba, David Riccitelli
Published: 2026-03-11
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2603.10700v1

Retrieval-Augmented Generation (RAG) systems typically treat documents as flat text, ignoring the structured metadata and linked relationships that knowledge graphs provide. In this paper, we investigate whether structured linked data, specifically Schema.org markup and dereferenceable entity pages served by a Linked Data Platform, can improve retrieval accuracy and answer quality in both standard and agentic RAG systems. We conduct a controlled experiment across four domains (editorial, legal, travel, e-commerce) using Vertex AI Vector Search 2.0 for retrieval and the Google Agent Development Kit (ADK) for agentic reasoning. Our experimental design tests seven conditions: three document representations (plain HTML, HTML with JSON-LD, and an enhanced agentic-optimized entity page) crossed with two retrieval modes (standard RAG and agentic RAG with multi-hop link traversal), plus an Enhanced+ condition that adds rich navigational affordances and entity interlinking. Our results reveal that while JSON-LD markup alone provides only modest improvements, our enhanced entity page format, incorporating llms.txt-style agent instructions, breadcrumbs, and neural search capabilities, achieves substantial gains: +29.6% accuracy improvement for standard RAG and +29.8% for the full agentic pipeline. The Enhanced+ variant, with richer navigational affordances, achieves the highest absolute scores (accuracy: 4.85/5, completeness: 4.55/5), though the incremental gain over the base enhanced format is not statistically significant. We release our dataset, evaluation framework, and enhanced entity page templates to support reproducibility.

---

### EvoSchema: Towards Text-to-SQL Robustness Against Schema Evolution

Authors: Tianshu Zhang, Kun Qian, Siddhartha Sahai, Yuan Tian, Shaddy Garg, Huan Sun, Yunyao Li
Published: 2026-03-11
Categories: cs.DB, cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2603.10697v1

Neural text-to-SQL models, which translate natural language questions (NLQs) into SQL queries given a database schema, have achieved remarkable performance. However, database schemas frequently evolve to meet new requirements. Such schema evolution often leads to performance degradation for models trained on static schemas. Existing work either mainly focuses on simply paraphrasing some syntactic or semantic mappings among NLQ, DB and SQL, or lacks a comprehensive and controllable way to investigate the model robustness issue under the schema evolution, which is insufficient when facing the increasingly complex and rich database schema changes in reality, especially in the LLM era. To address the challenges posed by schema evolution, we present EvoSchema, a comprehensive benchmark designed to assess and enhance the robustness of text-to-SQL systems under real-world schema changes. EvoSchema introduces a novel schema evolution taxonomy, encompassing ten perturbation types across columnlevel and table-level modifications, systematically simulating the dynamic nature of database schemas. Through EvoSchema, we conduct an in-depth evaluation spanning different open source and closed-source LLMs, revealing that table-level perturbations have a significantly greater impact on model performance compared to column-level changes. Furthermore, EvoSchema inspires the development of more resilient text-to-SQL systems, in terms of both model training and database design. The models trained on EvoSchema's diverse schema designs can force the model to distinguish the schema difference for the same questions to avoid learning spurious patterns, which demonstrate remarkable robustness compared to those trained on unperturbed data on average. This benchmark offers valuable insights into model behavior and a path forward for designing systems capable of thriving in dynamic, real-world environments.

---

### RandMark: On Random Watermarking of Visual Foundation Models

Authors: Anna Chistyakova, Mikhail Pautov
Published: 2026-03-11
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.10695v1

Being trained on large and diverse datasets, visual foundation models (VFMs) can be fine-tuned to achieve remarkable performance and efficiency in various downstream computer vision tasks. The high computational cost of data collection and training makes these models valuable assets, which motivates some VFM owners to distribute them alongside a license to protect their intellectual property rights. In this paper, we propose an approach to ownership verification of visual foundation models that leverages a small encoder-decoder network to embed digital watermarks into an internal representation of a hold-out set of input images. The method is based on random watermark embedding, which makes the watermark statistics detectable in functional copies of the watermarked model. Both theoretically and experimentally, we demonstrate that the proposed method yields a low probability of false detection for non-watermarked models and a low probability of false misdetection for watermarked models.

---

### Bioinspired CNNs for border completion in occluded images

Authors: Catarina P. Coutinho, Aneeqa Merhab, Janko Petkovic, Ferdinando Zanchetta, Rita Fioresi
Published: 2026-03-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.10694v1

We exploit the mathematical modeling of the border completion problem in the visual cortex to design convolutional neural network (CNN) filters that enhance robustness to image occlusions. We evaluate our CNN architecture, BorderNet, on three occluded datasets (MNIST, Fashion-MNIST, and EMNIST) under two types of occlusions: stripes and grids. In all cases, BorderNet demonstrates improved performance, with gains varying depending on the severity of the occlusions and the dataset.

---

### Repurposing Backdoors for Good: Ephemeral Intrinsic Proofs for Verifiable Aggregation in Cross-silo Federated Learning

Authors: Xian Qin, Xue Yang, Xiaohu Tang
Published: 2026-03-11
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2603.10692v1

While Secure Aggregation (SA) protects update confidentiality in Cross-silo Federated Learning, it fails to guarantee aggregation integrity, allowing malicious servers to silently omit or tamper with updates. Existing verifiable aggregation schemes rely on heavyweight cryptography (e.g., ZKPs, HE), incurring computational costs that scale poorly with model size. In this paper, we propose a lightweight architecture that shifts from extrinsic cryptographic proofs to \textit{Intrinsic Proofs}. We repurpose backdoor injection to embed verification signals directly into model parameters. By harnessing Catastrophic Forgetting, these signals are robust for immediate verification yet ephemeral, naturally decaying to preserve final model utility. We design a randomized, single-verifier auditing framework compatible with SA, ensuring client anonymity and preventing signal collision without trusted third parties. Experiments on SVHN, CIFAR-10, and CIFAR-100 demonstrate high detection probabilities against malicious servers. Notably, our approach achieves over $1000\times$ speedup on ResNet-18 compared to cryptographic baselines, effectively scaling to large models.

---

### Contract And Conquer: How to Provably Compute Adversarial Examples for a Black-Box Model?

Authors: Anna Chistyakova, Mikhail Pautov
Published: 2026-03-11
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.10689v2

Black-box adversarial attacks are widely used as tools to test the robustness of deep neural networks against malicious perturbations of input data aimed at a specific change in the output of the model. Such methods, although they remain empirically effective, usually do not guarantee that an adversarial example can be found for a particular model. In this paper, we propose Contract And Conquer (CAC), an approach to provably compute adversarial examples for neural networks in a black-box manner. The method is based on knowledge distillation of a black-box model on an expanding distillation dataset and precise contraction of the adversarial example search space. CAC is supported by the transferability guarantee: we prove that the method yields an adversarial example for the black-box model within a fixed number of algorithm iterations. Experimentally, we demonstrate that the proposed approach outperforms existing state-of-the-art black-box attack methods on ImageNet dataset for different target models, including vision transformers.

---

### MapGCLR: Geospatial Contrastive Learning of Representations for Online Vectorized HD Map Construction

Authors: Jonas Merkert, Alexander Blumberg, Jan-Hendrik Pauls, Christoph Stiller
Published: 2026-03-11
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2603.10688v2

Autonomous vehicles rely on map information to understand the world around them. However, the creation and maintenance of offline high-definition (HD) maps remains costly. A more scalable alternative lies in online HD map construction, which only requires map annotations at training time. To further reduce the need for annotating vast training labels, self-supervised training provides an alternative. This work focuses on improving the latent birds-eye-view (BEV) feature grid representation within a vectorized online HD map construction model by enforcing geospatial consistency between overlapping BEV feature grids as part of a contrastive loss function. To ensure geospatial overlap for contrastive pairs, we introduce an approach to analyze the overlap between traversals within a given dataset and generate subsidiary dataset splits following adjustable multi-traversal requirements. We train the same model supervised using a reduced set of single-traversal labeled data and self-supervised on a broader unlabeled set of data following our multi-traversal requirements, effectively implementing a semi-supervised approach. Our approach outperforms the supervised baseline across the board, both quantitatively in terms of the downstream tasks vectorized map perception performance and qualitatively in terms of segmentation in the principal component analysis (PCA) visualization of the BEV feature space.

---

### A$^2$-Edit: Precise Reference-Guided Image Editing of Arbitrary Objects and Ambiguous Masks

Authors: Huayu Zheng, Guangzhao Li, Baixuan Zhao, Siqi Luo, Hantao Jiang, Guangtao Zhai, Xiaohong Liu
Published: 2026-03-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.10685v2

We propose A^2-Edit, a unified inpainting framework for arbitrary object categories, which allows users to replace any target region with a reference object using only a coarse mask. To address the issues of severe homogenization and limited category coverage in existing datasets, we construct a large-scale multi-category dataset, UniEdit-500K, which includes 8 major categories, 209 fine-grained subcategories, and a total of 500,104 image pairs. Such rich category diversity poses new challenges for the model, requiring it to automatically learn semantic relationships and distinctions across categories. To this end, we introduce the Mixture of Transformer module, which performs differentiated modeling of various object categories through dynamic expert selection, and further enhances cross-category semantic transfer and generalization through collaboration among experts. In addition, we propose a Mask Annealing Training Strategy (MATS) that progressively relaxes mask precision during training, reducing the model's reliance on accurate masks and improving robustness across diverse editing tasks. Extensive experiments on benchmarks such as VITON-HD and AnyInsertion demonstrate that A^2-Edit consistently outperforms existing approaches across all metrics, providing a new and efficient solution for arbitrary object editing.

---

### A Platform-Agnostic Multimodal Digital Human Modelling Framework: Neurophysiological Sensing in Game-Based Interaction

Authors: Daniel J. Buxton, Mufti Mahmud, Jordan J. Bird, Thomas Hughes-Roberts, David J. Brown
Published: 2026-03-11
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2603.10680v1

Digital Human Modelling (DHM) is increasingly shaped by advances in AI, wearable biosensing, and interactive digital environments, particularly in research addressing accessibility and inclusion. However, many AI-enabled DHM approaches remain tightly coupled to specific platforms, tasks, or interpretative pipelines, limiting reproducibility, scalability, and ethical reuse. This paper presents a platform-agnostic DHM framework designed to support AI-ready multimodal interaction research by explicitly separating sensing, interaction modelling, and inference readiness. The framework integrates the OpenBCI Galea headset as a unified multimodal sensing layer, providing concurrent EEG, EMG, EOG, PPG, and inertial data streams, alongside a reproducible, game-based interaction environment implemented using SuperTux. Rather than embedding AI models or behavioural inference, physiological signals are represented as structured, temporally aligned observables, enabling downstream AI methods to be applied under appropriate ethical approval. Interaction is modelled using computational task primitives and timestamped event markers, supporting consistent alignment across heterogeneous sensors and platforms. Technical verification via author self-instrumentation confirms data integrity, stream continuity, and synchronisation; no human-subjects evaluation or AI inference is reported. Scalability considerations are discussed with respect to data throughput, latency, and extension to additional sensors or interaction modalities. Illustrative use cases demonstrate how the framework can support AI-enabled DHM and HCI studies, including accessibility-oriented interaction design and adaptive systems research, without requiring architectural modifications. The proposed framework provides an emerging-technology-focused infrastructure for future ethics-approved, inclusive DHM research.

---

### Surrogate models for nuclear fusion with parametric Shallow Recurrent Decoder Networks: applications to magnetohydrodynamics

Authors: M. Lo Verso, C. Introini, E. Cervi, L. Savoldi, J. N. Kutz, A. Cammi
Published: 2026-03-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.10678v1

Magnetohydrodynamic (MHD) effects play a key role in the design and operation of nuclear fusion systems, where electrically conducting fluids (such as liquid metals or molten salts in reactor blankets) interact with magnetic fields of varying intensity and orientation, which affect the resulting flow. The numerical resolution of MHD models involves highly nonlinear multiphysics systems of equations and can become computationally expensive, particularly in multi-query, parametric, or real-time contexts. This work investigates a fully data-driven framework for MHD state reconstruction that combines dimensionality reduction via Singular Value Decomposition (SVD) with the SHallow REcurrent Decoder (SHRED), a neural network architecture designed to recover the full spatio-temporal state from sparse time-series measurements of a limited number of observables. The methodology is applied to a parametric MHD test case involving compressible lead-lithium flow in a stepped channel subjected to thermal gradients and magnetic fields spanning a broad range of intensities. To improve efficiency, the full-order dataset is first compressed using SVD, yielding a reduced representation used as reference truth for training. Only temperature measurements from three sensors are provided as input, while the network reconstructs the full fields of velocity, pressure, and temperature. To assess robustness with respect to sensor placement, thirty randomly generated sensor configurations are tested in ensemble mode. Results show that SHRED accurately reconstructs the full MHD state even for magnetic field intensities not included in the training set. These findings demonstrate the potential of SHRED as a computationally efficient surrogate modeling strategy for fusion-relevant multiphysics problems, enabling low-cost state estimation with possible applications in real-time monitoring and control.

---

### Emulating Clinician Cognition via Self-Evolving Deep Clinical Research

Authors: Ruiyang Ren, Yuhao Wang, Yunsen Liang, Lan Luo, Jing Liu, Haifeng Wang, Cong Feng, Yinan Zhang, Chunyan Miao, Ji-Rong Wen, Wayne Xin Zhao
Published: 2026-03-11
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2603.10677v1

Clinical diagnosis is a complex cognitive process, grounded in dynamic cue acquisition and continuous expertise accumulation. Yet most current artificial intelligence (AI) systems are misaligned with this reality, treating diagnosis as single-pass retrospective prediction while lacking auditable mechanisms for governed improvement. We developed DxEvolve, a self-evolving diagnostic agent that bridges these gaps through an interactive deep clinical research workflow. The framework autonomously requisitions examinations and continually externalizes clinical experience from increasing encounter exposure as diagnostic cognition primitives. On the MIMIC-CDM benchmark, DxEvolve improved diagnostic accuracy by 11.2% on average over backbone models and reached 90.4% on a reader-study subset, comparable to the clinician reference (88.8%). DxEvolve improved accuracy on an independent external cohort by 10.2% (categories covered by the source cohort) and 17.1% (uncovered categories) compared to the competitive method. By transforming experience into a governable learning asset, DxEvolve supports an accountable pathway for the continual evolution of clinical AI.

---

### Spatio-Temporal Attention Graph Neural Network: Explaining Causalities With Attention

Authors: Kosti Koistinen, Kirsi Hellsten, Joni Herttuainen, Kimmo K. Kaski
Published: 2026-03-11
Categories: cs.LG, cs.CE
arXiv: https://arxiv.org/abs/2603.10676v2

Industrial Control Systems (ICS) underpin critical infrastructure and face growing cyber-physical threats due to the convergence of operational technology and networked environments. While machine learning-based anomaly detection approaches in ICS shows strong theoretical performance, deployment is often limited by poor explainability, high false-positive rates, and sensitivity to evolving system behavior, i.e., baseline drifting. We propose a Spatio-Temporal Attention Graph Neural Network (STA-GNN) for unsupervised and explainable anomaly detection in ICS that models both temporal dynamics and relational structure of the system. Sensors, controllers, and network entities are represented as nodes in a dynamically learned graph, enabling the model to capture inter-dependencies across physical processes and communication patterns. Attention mechanisms provide influential relationships, supporting inspection of correlations and potential causal pathways behind detected events. The approach supports multiple data modalities, including SCADA point measurements, network flow features, and payload features, and thus enables unified cyber-physical analysis. To address operational requirements, we incorporate a conformal prediction strategy to control false alarm rates and monitor performance degradation under drifting of the environment. Our findings highlight the possibilities and limitations of model evaluation and common pitfalls in anomaly detection in ICS. Our findings emphasise the importance of explainable, drift-aware evaluation for reliable deployment of learning-based security monitoring systems.

---

### An FPGA Implementation of Displacement Vector Search for Intra Pattern Copy in JPEG XS

Authors: Qiyue Chen, Yao Li, Jie Tao, Song Chen, Li Li, Dong Liu
Published: 2026-03-11
Categories: cs.AR, cs.CV, eess.IV
arXiv: https://arxiv.org/abs/2603.10671v1

Recently, progress has been made on the Intra Pattern Copy (IPC) tool for JPEG XS, an image compression standard designed for low-latency and low-complexity coding. IPC performs wavelet-domain intra compensation predictions to reduce spatial redundancy in screen content. A key module of IPC is the displacement vector (DV) search, which aims to solve the optimal prediction reference offset. However, the DV search process is computationally intensive, posing challenges for practical hardware deployment. In this paper, we propose an efficient pipelined FPGA architecture design for the DV search module to promote the practical deployment of IPC. Optimized memory organization, which leverages the IPC computational characteristics and data inherent reuse patterns, is further introduced to enhance the performance. Experimental results show that our proposed architecture achieves a throughput of 38.3 Mpixels/s with a power consumption of 277 mW, demonstrating its feasibility for practical hardware implementation in IPC and other predictive coding tools, and providing a promising foundation for ASIC deployment.

---

### FAME: Formal Abstract Minimal Explanation for Neural Networks

Authors: Ryma Boumazouza, Raya Elsaleh, Melanie Ducoffe, Shahaf Bassan, Guy Katz
Published: 2026-03-11
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.10661v1

We propose FAME (Formal Abstract Minimal Explanations), a new class of abductive explanations grounded in abstract interpretation. FAME is the first method to scale to large neural networks while reducing explanation size. Our main contribution is the design of dedicated perturbation domains that eliminate the need for traversal order. FAME progressively shrinks these domains and leverages LiRPA-based bounds to discard irrelevant features, ultimately converging to a formal abstract minimal explanation. To assess explanation quality, we introduce a procedure that measures the worst-case distance between an abstract minimal explanation and a true minimal explanation. This procedure combines adversarial attacks with an optional VERIX+ refinement step. We benchmark FAME against VERIX+ and demonstrate consistent gains in both explanation size and runtime on medium- to large-scale neural networks.

---

### How to Embed Matters: Evaluation of EO Embedding Design Choices

Authors: Luis Gilch, Isabelle Wittmann, Maximilian Nitsche, Johannes Jakubik, Arne Ewald, Thomas Brunschwiler
Published: 2026-03-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.10658v2

Earth observation (EO) missions produce petabytes of multispectral imagery, increasingly analyzed using large Geospatial Foundation Models (GeoFMs). Alongside end-to-end adaptation, workflows make growing use of intermediate representations as task-agnostic embeddings, enabling models to compute representations once and reuse them across downstream tasks. Consequently, when GeoFMs act as feature extractors, decisions about how representations are obtained, aggregated, and combined affect downstream performance and pipeline scalability. Understanding these trade-offs is essential for scalable embedding-based EO workflows, where compact embeddings can replace raw data while remaining broadly useful. We present a systematic analysis of embedding design in GeoFM-based EO workflows. Leveraging NeuCo-Bench, we study how backbone architecture, pretraining strategy, representation depth, spatial aggregation, and representation combination influence EO task performance. We demonstrate the usability of GeoFM embeddings by aggregating them into fixed-size representations more than 500x smaller than the raw input data. Across models, we find consistent trends: transformer backbones with mean pooling provide strong default embeddings, intermediate ResNet layers can outperform final layers, self-supervised objectives exhibit task-specific strengths, and combining embeddings from different objectives often improves robustness.

---

### Are Video Reasoning Models Ready to Go Outside?

Authors: Yangfan He, Changgyu Boo, Jaehong Yoon
Published: 2026-03-11
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.10652v3

In real-world deployment, vision-language models often encounter disturbances such as weather, occlusion, and camera motion. Under such conditions, their understanding and reasoning degrade substantially, revealing a gap between clean, controlled (i.e., unperturbed) evaluation settings and real-world robustness. To address this limitation, we propose ROVA, a novel training framework that improves robustness by modeling a robustness-aware consistency reward under spatio-temporal corruptions. ROVA introduces a difficulty-aware online training strategy that prioritizes informative samples based on the model's evolving capability. Specifically, it continuously re-estimates sample difficulty via self-reflective evaluation, enabling adaptive training with a robustness-aware consistency reward. We also introduce PVRBench, a new benchmark that injects real-world perturbations into embodied video datasets to assess both accuracy and reasoning quality under realistic disturbances. We evaluate ROVA and baselines on PVRBench, UrbanVideo, and VisBench, where open-source and proprietary models suffer up to 35% and 28% drops in accuracy and reasoning under realistic perturbations. ROVA effectively mitigates performance degradation, boosting relative accuracy by at least 24% and reasoning by over 9% compared with baseline models (QWen2.5/3-VL, InternVL2.5, Embodied-R). These gains transfer to clean standard benchmarks, yielding consistent improvements.

---

### Interleaving Scheduling and Motion Planning with Incremental Learning of Symbolic Space-Time Motion Abstractions

Authors: Elisa Tosello, Arthur Bit-Monnot, Davide Lusuardi, Alessandro Valentini, Andrea Micheli
Published: 2026-03-11
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2603.10651v2

Task and Motion Planning combines high-level task sequencing (what to do) with low-level motion planning (how to do it) to generate feasible, collision-free execution plans. However, in many real-world domains, such as automated warehouses, tasks are predefined, shifting the challenge to if, when, and how to execute them safely and efficiently under resource, time and motion constraints. In this paper, we formalize this as the Scheduling and Motion Planning problem for multi-object navigation in shared workspaces. We propose a novel solution framework that interleaves off-the-shelf schedulers and motion planners in an incremental learning loop. The scheduler generates candidate plans, while the motion planner checks feasibility and returns symbolic feedback, i.e., spatial conflicts and timing adjustments, to guide the scheduler towards motion-feasible solutions. We validate our proposal on logistics and job-shop scheduling benchmarks augmented with motion tasks, using state-of-the-art schedulers and sampling-based motion planners. Our results show the effectiveness of our framework in generating valid plans under complex temporal and spatial constraints, where synchronized motion is critical.

---

### Less is More: Compact-Token Masked Feature Prediction for Skeleton Representation Learning

Authors: Jeonghyeok Do, Yun Chen, Geunhyuk Youk, Munchurl Kim
Published: 2026-03-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.10648v3

Current skeleton representation learning paradigms face distinct limitations: Contrastive Learning (CL) often overlooks fine-grained motion details, while Masked Auto-Encoders (MAE) rely on coordinate-level reconstruction. This reconstruction inherently demands dense token sequences and heavy decoders, wasting pre-training computation on discarded components and forcing downstream inference to process dense token grids. To resolve these bottlenecks, we propose SLiM (Skeleton Less is More), a compact-token framework that unifies masked feature prediction and contrastive learning via a shared encoder. By shifting the objective from raw coordinate reconstruction to decoder-free, teacher-guided feature prediction, SLiM breaks the reliance on dense tokenization and enables effective learning with a highly compact token grid. Crucially, to prevent trivial shortcut learning arising from strong inter-joint dependencies of human, we introduce Semantic Tube Masking together with Skeleton-Aware Augmentations to enforce deep skeletal-temporal reasoning and anatomical consistency. Extensive experiments across multiple downstream protocols demonstrate that SLiM achieves state-of-the-art performance while structurally reducing inference computation by 7.89$\times$ compared to dense-token MAE baselines.

---

### Detecting and Eliminating Neural Network Backdoors Through Active Paths with Application to Intrusion Detection

Authors: Eirik Høyheim, Magnus Wiik Eckhoff, Gudmund Grov, Robert Flood, David Aspinall
Published: 2026-03-11
Categories: cs.CR, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.10641v1

Machine learning backdoors have the property that the machine learning model should work as expected on normal inputs, but when the input contains a specific $\textit{trigger}$, it behaves as the attacker desires. Detecting such triggers has been proven to be extremely difficult. In this paper, we present a novel and explainable approach to detect and eliminate such backdoor triggers based on active paths found in neural networks. We present promising experimental evidence of our approach, which involves injecting backdoors into a machine learning model used for intrusion detection.

---

### Making Bielik LLM Reason (Better): A Field Report

Authors: Adam Trybus, Bartosz Bartnicki, Remigiusz Kinas
Published: 2026-03-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.10640v1

This paper presents a research program dedicated to evaluating and advancing the reasoning capabilities of Bielik, a Polish large language model. The study describes a number of stages of work: initial benchmarking and creation of evaluation methodology, analyzing of comparative results with other LLMs and outlining of future prospects that take into account the limitations of the analyses conducted so far and aims to keep Bielik in the race give the ever-changing -- and competitive -- AI landscape.

---

### Splat2Real: Novel-view Scaling for Physical AI with 3D Gaussian Splatting

Authors: Hansol Lim, Jongseong Brad Choi
Published: 2026-03-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.10638v1

Physical AI faces viewpoint shift between training and deployment, and novel-view robustness is essential for monocular RGB-to-3D perception. We cast Real2Render2Real monocular depth pretraining as imitation-learning-style supervision from a digital twin oracle: a student depth network imitates expert metric depth/visibility rendered from a scene mesh, while 3DGS supplies scalable novel-view observations. We present Splat2Real, centered on novel-view scaling: performance depends more on which views are added than on raw view count. We introduce CN-Coverage, a coverage+novelty curriculum that greedily selects views by geometry gain and an extrapolation penalty, plus a quality-aware guardrail fallback for low-reliability teachers. Across 20 TUM RGB-D sequences with step-matched budgets (N=0 to 2000 additional rendered views, with N unique <= 500 and resampling for larger budgets), naive scaling is unstable; CN-Coverage mitigates worst-case regressions relative to Robot/Coverage policies, and GOL-Gated CN-Coverage provides the strongest medium-high-budget stability with the lowest high-novelty tail error. Downstream control-proxy results versus N provides embodied-relevance evidence by shifting safety/progress trade-offs under viewpoint shift.

---

### Reinforcement Learning with Conditional Expectation Reward

Authors: Changyi Xiao, Caijun Xu, Yixin Cao
Published: 2026-03-11
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2603.10624v1

Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective in enhancing the reasoning capabilities of large language models, particularly in domains such as mathematics where reliable rule-based verifiers can be constructed. However, the reliance on handcrafted, domain-specific verification rules substantially limits the applicability of RLVR to general reasoning domains with free-form answers, where valid answers often exhibit significant variability, making it difficult to establish complete and accurate rules. To address this limitation, we propose Conditional Expectation Reward (CER), which leverages the large language model itself as an implicit verifier, and is therefore applicable to general domains and eliminates the need for external verifiers or auxiliary models. CER is defined as the expected likelihood of generating the reference answer conditioned on the generated answer. In contrast to rule-based verifiers that yield binary feedback, CER provides a soft, graded reward signal that reflects varying degrees of correctness, making it better suited to tasks where answers vary in correctness. Experimental results demonstrate that CER is effective across a wide range of reasoning tasks, spanning both mathematical and general domains, indicating that CER serves as a flexible and general verification mechanism. The code is available at https://github.com/changyi7231/CER.

---

### Geo-ATBench: A Benchmark for Geospatial Audio Tagging with Geospatial Semantic Context

Authors: Yuanbo Hou, Yanru Wu, Qiaoqiao Ren, Shengchen Li, Stephen Roberts, Dick Botteldooren
Published: 2026-03-11
Categories: eess.AS, cs.LG, cs.SD
arXiv: https://arxiv.org/abs/2603.10623v1

Environmental sound understanding in computational auditory scene analysis (CASA) is often formulated as an audio-only recognition problem. This formulation leaves a persistent drawback in multi-label audio tagging (AT): acoustic similarity can make certain events difficult to separate from waveforms alone. In such cases, disambiguating cues often lie outside the waveform. Geospatial semantic context (GSC), derived from geographic information system data, e.g., points of interest (POI), provides location-tied environmental priors that can help reduce this ambiguity. A systematic study of this direction is enabled through the proposed geospatial audio tagging (Geo-AT) task, which conditions multi-label sound event tagging on GSC alongside audio. To benchmark Geo-AT, Geo-ATBench is introduced as a polyphonic audio benchmark with geographical annotations, containing 10.71 hours of audio across 28 event categories; each clip is paired with a GSC representation from 11 semantic context categories. GeoFusion-AT is proposed as a unified geo-audio fusion framework that evaluates feature-, representation-, and decision-level fusion on representative audio backbones, with audio- and GSC-only baselines. Results show that incorporating GSC improves AT performance, especially on acoustically confounded labels, indicating geospatial semantics provide effective priors beyond audio alone. A crowdsourced listening study with 10 participants on 579 samples shows that there is no significant difference in performance between models on Geo-ATBench labels and aggregated human labels, supporting Geo-ATBench as a human-aligned benchmark. The Geo-AT task, benchmark Geo-ATBench, and reproducible geo-audio fusion framework GeoFusion-AT provide a foundation for studying AT with geospatial semantic context within the CASA community. Dataset, code, models are on homepage (https://github.com/WuYanru2002/Geo-ATBench).

---

### Disentangling Similarity and Relatedness in Topic Models

Authors: Hanlin Xiao, Yang Wang, Mauricio A. Álvarez, Rainer Breitling
Published: 2026-03-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.10619v3

The recent success of large pre-trained language models (PLMs) has motivated their integration into topic modeling. However, PLM-augmented topic models differ from classical co-occurrence models such as Latent Dirichlet Allocation (LDA) not only in performance, but also in the type of semantic structure they capture. We formalize this distinction along two psycholinguistic axes: thematic relatedness (dog/bone) and taxonomic similarity (dog/wolf). To measure both axes over topic words, we construct a large synthetic benchmark of word pairs using LLM-based annotation and train a neural scorer on it. Across multiple corpora and model families, the scorer places different topic-model families at distinct positions within the joint similarity-relatedness space. The two scores further predict downstream task performance: tasks requiring similarity benefit from similarity-rich topics, whereas tasks requiring relatedness benefit from the converse, and excessive emphasis on either axis degrades performance on tasks aligned with the opposing semantic structure. Neither axis is uniformly beneficial. Measuring both therefore provides a practical, model-agnostic diagnostic for evaluating the semantic structure captured by topic models.

---

### MUNIChus: Multilingual News Image Captioning Benchmark

Authors: Yuji Chen, Alistair Plum, Hansi Hettiarachchi, Diptesh Kanojia, Saroj Basnet, Marcos Zampieri, Tharindu Ranasinghe
Published: 2026-03-11
Categories: cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2603.10613v1

The goal of news image captioning is to generate captions by integrating news article content with corresponding images, highlighting the relationship between textual context and visual elements. The majority of research on news image captioning focuses on English, primarily because datasets in other languages are scarce. To address this limitation, we create the first multilingual news image captioning benchmark, MUNIChus, comprising 9 languages, including several low-resource languages such as Sinhala and Urdu. We evaluate various state-of-the-art neural news image captioning models on MUNIChus and find that news image captioning remains challenging. We also make MUNIChus publicly available with over 20 models already benchmarked. MUNIChus opens new avenues for further advancements in developing and evaluating multilingual news image captioning models.

---

### HyPER-GAN: Hybrid Patch-Based Image-to-Image Translation for Real-Time Photorealism Enhancement in Game Engines

Authors: Stefanos Pasios, Nikos Nikolaidis
Published: 2026-03-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.10604v3

Generative models are increasingly used in video game engines to enhance the photorealism of rendered images for visual synthetic data generation and simulation applications. However, they often introduce artifacts that alter the content of the original rendered scenes and require high computational resources, which limit their utilization for the photorealism enhancement of training and evaluation data, as well as their integration in the rendering pipelines of game engines. In this paper, we propose Hybrid Patch Enhanced Realism Generative Adversarial Network (HyPER-GAN), a hybrid image-to-image translation framework that is based on a lightweight U-Net-style generator capable of performing real-time inference. The framework is trained using paired rendered and photorealism-enhanced images, complemented by a novel hybrid training strategy that incorporates matched patches from unpaired real-world images to improve content preservation and further enhance the visual realism that can be achieved by the lightweight generator. Experimental results demonstrate that HyPER-GAN achieves a 6x increase in frames per second at 1080p in comparison with state-of-the-art lightweight paired image-to-image translation methods, while also increasing, in both within- and cross-engine evaluations, the photorealism of the rendered images without significantly compromising semantic consistency. Moreover, it is illustrated that HyPER-GAN maintains temporal consistency and that the proposed hybrid training strategy improves content preservation and visual realism in within-engine and increases the robustness in cross-engine evaluations compared to training the framework solely with paired rendered and photorealism-enhanced images. Code and pretrained models are publicly available at: https://github.com/stefanos50/HyPER-GAN

---

### Trajectory-Informed Memory Generation for Self-Improving Agent Systems

Authors: Gaodan Fang, Vatche Isahagian, K. R. Jayaram, Ritesh Kumar, Vinod Muthusamy, Punleuk Oum, Gegi Thomas
Published: 2026-03-11
Categories: cs.AI, cs.DB, cs.IR
arXiv: https://arxiv.org/abs/2603.10600v1

LLM-powered agents face a persistent challenge: learning from their execution experiences to improve future performance. While agents can successfully complete many tasks, they often repeat inefficient patterns, fail to recover from similar errors, and miss opportunities to apply successful strategies from past executions. We present a novel framework for automatically extracting actionable learnings from agent execution trajectories and utilizing them to improve future performance through contextual memory retrieval. Our approach comprises four components: (1) a Trajectory Intelligence Extractor that performs semantic analysis of agent reasoning patterns, (2) a Decision Attribution Analyzer that identifies which decisions and reasoning steps led to failures, recoveries, or inefficiencies, (3) a Contextual Learning Generator that produces three types of guidance -- strategy tips from successful patterns, recovery tips from failure handling, and optimization tips from inefficient but successful executions, and (4) an Adaptive Memory Retrieval System that injects relevant learnings into agent prompts based on multi-dimensional similarity. Unlike existing memory systems that store generic conversational facts, our framework understands execution patterns, extracts structured learnings with provenance, and retrieves guidance tailored to specific task contexts. Evaluation on the AppWorld benchmark demonstrates consistent improvements, with up to 14.3 percentage point gains in scenario goal completion on held-out tasks and particularly strong benefits on complex tasks (28.5~pp scenario goal improvement, a 149\% relative increase).

---

### Self-Scaled Broyden Family of Quasi-Newton Methods in JAX

Authors: Ivan Bioli, Mikel Mendibe Abarrategi
Published: 2026-03-11
Categories: cs.MS, cs.LG
arXiv: https://arxiv.org/abs/2603.10599v1

We present a JAX implementation of the Self-Scaled Broyden family of quasi-Newton methods, fully compatible with JAX and building on the Optimistix~\cite{rader_optimistix_2024} optimisation library. The implementation includes BFGS, DFP, Broyden and their Self-Scaled variants(SSBFGS, SSDFP, SSBroyden), together with a Zoom line search satisfying the strong Wolfe conditions. This is a short technical note, not a research paper, as it does not claim any novel contribution; its purpose is to document the implementation and ease the adoption of these optimisers within the JAX community. The code is available at https://github.com/IvanBioli/ssbroyden_optimistix.git.

---

### Layer Consistency Matters: Elegant Latent Transition Discrepancy for Generalizable Synthetic Image Detection

Authors: Yawen Yang, Feng Li, Shuqi Kong, Yunfeng Diao, Xinjian Gao, Zenglin Shi, Meng Wang
Published: 2026-03-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.10598v2

Recent rapid advancement of generative models has significantly improved the fidelity and accessibility of AI-generated synthetic images. While enabling various innovative applications, the unprecedented realism of these synthetics makes them increasingly indistinguishable from authentic photographs, posing serious security risks, such as media credibility and content manipulation. Although extensive efforts have been dedicated to detecting synthetic images, most existing approaches suffer from poor generalization to unseen data due to their reliance on model-specific artifacts or low-level statistical cues. In this work, we identify a previously unexplored distinction that real images maintain consistent semantic attention and structural coherence in their latent representations, exhibiting more stable feature transitions across network layers, whereas synthetic ones present discernible distinct patterns. Therefore, we propose a novel approach termed latent transition discrepancy (LTD), which captures the inter-layer consistency differences of real and synthetic images. LTD adaptively identifies the most discriminative layers and assesses the transition discrepancies across layers. Benefiting from the proposed inter-layer discriminative modeling, our approach exceeds the base model by 14.35\% in mean Acc across three datasets containing diverse GANs and DMs. Extensive experiments demonstrate that LTD outperforms recent state-of-the-art methods, achieving superior detection accuracy, generalizability, and robustness. The code is available at https://github.com/yywencs/LTD

---

### Recover to Predict: Progressive Retrospective Learning for Variable-Length Trajectory Prediction

Authors: Hao Zhou, Lu Qi, Jason Li, Jie Zhang, Yi Liu, Xu Yang, Mingyu Fan, Fei Luo
Published: 2026-03-11
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2603.10597v1

Trajectory prediction is critical for autonomous driving, enabling safe and efficient planning in dense, dynamic traffic. Most existing methods optimize prediction accuracy under fixed-length observations. However, real-world driving often yields variable-length, incomplete observations, posing a challenge to these methods. A common strategy is to directly map features from incomplete observations to those from complete ones. This one-shot mapping, however, struggles to learn accurate representations for short trajectories due to significant information gaps. To address this issue, we propose a Progressive Retrospective Framework (PRF), which gradually aligns features from incomplete observations with those from complete ones via a cascade of retrospective units. Each unit consists of a Retrospective Distillation Module (RDM) and a Retrospective Prediction Module (RPM), where RDM distills features and RPM recovers previous timesteps using the distilled features. Moreover, we propose a Rolling-Start Training Strategy (RSTS) that enhances data efficiency during PRF training. PRF is plug-and-play with existing methods. Extensive experiments on datasets Argoverse 2 and Argoverse 1 demonstrate the effectiveness of PRF. Code is available at https://github.com/zhouhao94/PRF.

---

### Gradient Flow Drifting: Generative Modeling via Wasserstein Gradient Flows of KDE-Approximated Divergences

Authors: Jiarui Cao, Zixuan Wei, Yuxin Liu
Published: 2026-03-11
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.10592v1

We reveal a precise mathematical framework about a new family of generative models which we call Gradient Flow Drifting. With this framework, we prove an equivalence between the recently proposed Drifting Model and the Wasserstein gradient flow of the forward KL divergence under kernel density estimation (KDE) approximation. Specifically, we prove that the drifting field of drifting model (arXiv:2602.04770) equals, up to a bandwidth-squared scaling factor, the difference of KDE log-density gradients $\nabla \log p_{\mathrm{kde}} - \nabla \log q_{\mathrm{kde}}$, which is exactly the particle velocity field of the Wasserstein-2 gradient flow of $KL(q\|p)$ with KDE-approximated densities. Besides that, this broad family of generative models can also include MMD-based generators, which arises as special cases of Wasserstein gradient flows of different divergences under KDE approximation. We provide a concise identifiability proof, and a theoretically grounded mixed-divergence strategy. We combine reverse KL and $χ^2$ divergence gradient flows to simultaneously avoid mode collapse and mode blurring, and extend this method onto Riemannian manifold which loosens the constraints on the kernel function, and makes this method more suitable for the semantic space. Preliminary experiments on synthetic benchmarks validate the framework.

---

### Does LLM Alignment Really Need Diversity? An Empirical Study of Adapting RLVR Methods for Moral Reasoning

Authors: Zhaowei Zhang, Xiaohan Liu, Xuekai Zhu, Junchao Huang, Ceyao Zhang, Zhiyuan Feng, Yaodong Yang, Xiaoyuan Yi, Xing Xie
Published: 2026-03-11
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2603.10588v1

Reinforcement learning with verifiable rewards (RLVR) has achieved remarkable success in logical reasoning tasks, yet whether large language model (LLM) alignment requires fundamentally different approaches remains unclear. Given the apparent tolerance for multiple valid responses in moral reasoning, a natural hypothesis is that alignment tasks inherently require diversity-seeking distribution-matching algorithms rather than reward-maximizing policy-based methods. We conduct the first comprehensive empirical study comparing both paradigms on MoReBench. To enable stable RLVR training, we build a rubric-grounded reward pipeline by training a Qwen3-1.7B judge model. Contrary to our hypothesis, we find that distribution-matching approaches do not demonstrate significant advantages over reward-maximizing methods as expected on alignment tasks. Through semantic visualization mapping high-reward responses to semantic space, we demonstrate that moral reasoning exhibits more concentrated high-reward distributions than mathematical reasoning, where diverse solution strategies yield similarly high rewards. This counter-intuitive finding explains why mode-seeking optimization proves equally or more effective for alignment tasks. Our results suggest that alignment tasks do not inherently require diversity-preserving algorithms, and standard reward-maximizing RLVR methods can effectively transfer to moral reasoning without explicit diversity mechanisms.

---

### Need for Speed: Zero-Shot Depth Completion with Single-Step Diffusion

Authors: Jakub Gregorek, Paraskevas Pegios, Nando Metzger, Konrad Schindler, Theodora Kontogianni, Lazaros Nalpantidis
Published: 2026-03-11
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2603.10584v2

We introduce Marigold-SSD, a single-step, late-fusion depth completion framework that leverages strong diffusion priors while eliminating the costly test-time optimization typically associated with diffusion-based methods. By shifting computational burden from inference to finetuning, our approach enables efficient and robust 3D perception under real-world latency constraints. Marigold-SSD achieves significantly faster inference with a training cost of only 4.5 GPU days. We evaluate our method across four indoor and two outdoor benchmarks, demonstrating strong cross-domain generalization and zero-shot performance compared to existing depth completion approaches. Our approach significantly narrows the efficiency gap between diffusion-based and discriminative models. Finally, we challenge common evaluation protocols by analyzing performance under varying input sparsity levels. Page: https://dtu-pas.github.io/marigold-ssd/

---

### Attribution as Retrieval: Model-Agnostic AI-Generated Image Attribution

Authors: Hongsong Wang, Renxi Cheng, Chaolei Han, Jie Gui
Published: 2026-03-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.10583v1

With the rapid advancement of AIGC technologies, image forensics will encounter unprecedented challenges. Traditional methods are incapable of dealing with increasingly realistic images generated by rapidly evolving image generation techniques. To facilitate the identification of AI-generated images and the attribution of their source models, generative image watermarking and AI-generated image attribution have emerged as key research focuses in recent years. However, existing methods are model-dependent, requiring access to the generative models and lacking generality and scalability to new and unseen generators. To address these limitations, this work presents a new paradigm for AI-generated image attribution by formulating it as an instance retrieval problem instead of a conventional image classification problem. We propose an efficient model-agnostic framework, called Low-bIt-plane-based Deepfake Attribution (LIDA). The input to LIDA is produced by Low-Bit Fingerprint Generation module, while the training involves Unsupervised Pre-Training followed by subsequent Few-Shot Attribution Adaptation. Comprehensive experiments demonstrate that LIDA achieves state-of-the-art performance for both Deepfake detection and image attribution under zero- and few-shot settings. The code is at https://github.com/hongsong-wang/LIDA

---

### HAPEns: Hardware-Aware Post-Hoc Ensembling for Tabular Data

Authors: Jannis Maier, Lennart Purucker
Published: 2026-03-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.10582v2

Ensembling is commonly used in machine learning on tabular data to boost predictive performance and robustness, but larger ensembles often lead to increased hardware demand. We introduce HAPEns, a post-hoc ensembling method that explicitly balances accuracy against hardware efficiency. Inspired by multi-objective and quality diversity optimization, HAPEns constructs a diverse set of ensembles along the Pareto front of predictive performance and resource usage. Existing hardware-aware post-hoc ensembling baselines are not available, highlighting the novelty of our approach. Experiments on 83 tabular classification datasets show that HAPEns significantly outperforms baselines, finding superior trade-offs for ensemble performance and deployment cost. Ablation studies also reveal that memory usage is a particularly effective objective metric. Further, we show that even a greedy ensembling algorithm can be significantly improved in this task with static multi-objective weighting.

---

### R4-CGQA: Retrieval-based Vision Language Models for Computer Graphics Image Quality Assessment

Authors: Zhuangzi Li, Jian Jin, Shilv Cai, Weisi Lin
Published: 2026-03-11
Categories: cs.CV, cs.DB
arXiv: https://arxiv.org/abs/2603.10578v1

Immersive Computer Graphics (CGs) rendering has become ubiquitous in modern daily life. However, comprehensively evaluating CG quality remains challenging for two reasons: First, existing CG datasets lack systematic descriptions of rendering quality; and second existing CG quality assessment methods cannot provide reasonable text-based explanations. To address these issues, we first identify six key perceptual dimensions of CG quality from the user perspective and construct a dataset of 3500 CG images with corresponding quality descriptions. Each description covers CG style, content, and perceived quality along the selected dimensions. Furthermore, we use a subset of the dataset to build several question-answer benchmarks based on the descriptions in order to evaluate the responses of existing Vision Language Models (VLMs). We find that current VLMs are not sufficiently accurate in judging fine-grained CG quality, but that descriptions of visually similar images can significantly improve a VLM's understanding of a given CG image. Motivated by this observation, we adopt retrieval-augmented generation and propose a two-stream retrieval framework that effectively enhances the CG quality assessment capabilities of VLMs. Experiments on several representative VLMs demonstrate that our method substantially improves their performance on CG quality assessment.

---

### CUAAudit: Meta-Evaluation of Vision-Language Models as Auditors of Autonomous Computer-Use Agents

Authors: Marta Sumyk, Oleksandr Kosovan
Published: 2026-03-11
Categories: cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2603.10577v2

Computer-Use Agents (CUAs) are emerging as a new paradigm in human-computer interaction, enabling autonomous execution of tasks in desktop environment by perceiving high-level natural-language instructions. As such agents become increasingly capable and are deployed across diverse desktop environments, evaluating their behavior in a scalable and reliable manner becomes a critical challenge. Existing evaluation pipelines rely on static benchmarks, rule-based success checks, or manual inspection, which are brittle, costly, and poorly aligned with real-world usage. In this work, we study Vision-Language Models (VLMs) as autonomous auditors for assessing CUA task completion directly from observable interactions and conduct a large-scale meta-evaluation of five VLMs that judge task success given a natural-language instruction and the final environment state. Our evaluation spans three widely used CUA benchmarks across macOS, Windows, and Linux environments and analyzes auditor behavior along three complementary dimensions: accuracy, calibration of confidence estimates, and inter-model agreement. We find that while state-of-the-art VLMs achieve strong accuracy and calibration, all auditors exhibit notable performance degradation in more complex or heterogeneous environments, and even high-performing models show significant disagreement in their judgments. These results expose fundamental limitations of current model-based auditing approaches and highlight the need to explicitly account for evaluator reliability, uncertainty, and variance when deploying autonomous CUAs in real-world settings.

---

### Implicit Statistical Inference in Transformers: Approximating Likelihood-Ratio Tests In-Context

Authors: Faris Chaudhry, Siddhant Gadkari
Published: 2026-03-11
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.10573v1

In-context learning (ICL) allows Transformers to adapt to novel tasks without weight updates, yet the underlying algorithms remain poorly understood. We adopt a statistical decision-theoretic perspective by investigating simple binary hypothesis testing, where the optimal policy is determined by the likelihood-ratio test. Notably, this setup provides a mathematically rigorous setting for mechanistic interpretability where the target algorithmic ground truth is known. By training Transformers on tasks requiring distinct geometries (linear shifted means vs. nonlinear variance estimation), we demonstrate that the models approximate the Bayes-optimal sufficient statistics from context up to some monotonic transformation, matching the performance of an ideal oracle estimator in nonlinear regimes. Leveraging this analytical ground truth, mechanistic analysis via logit lens and circuit alignment suggests that the model does not rely on a fixed kernel smoothing heuristic. Instead, it appears to adapt the point at which decisions become linearly decodable: exhibiting patterns consistent with a voting-style ensemble for linear tasks while utilizing a deeper sequential computation for nonlinear tasks. These findings suggest that ICL emerges from the construction of task-adaptive statistical estimators rather than simple similarity matching.

---

### End-to-End Chatbot Evaluation with Adaptive Reasoning and Uncertainty Filtering

Authors: Nhi Dang, Tung Le, Huy Tien Nguyen
Published: 2026-03-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.10570v1

Large language models (LLMs) combined with retrieval augmented generation have enabled the deployment of domain-specific chatbots, but these systems remain prone to generating unsupported or incorrect answers. Reliable evaluation is therefore critical, yet manual review is costly and existing frameworks often depend on curated test sets and static metrics, limiting scalability. We propose an end-to-end automatic evaluator designed to substantially reduce human effort. Our system generates Q\&A pairs directly from the underlying knowledge base, uses LLMs to judge chatbot responses against reference answers, and applies confidence-based filtering to highlight uncertain cases. Applied to a Vietnamese news dataset, the evaluator achieves high agreement with human judgments while significantly lowering review overhead. The framework is modular and language-agnostic, making it readily adaptable to diverse domains. This work introduces a practical, scalable solution for evaluating chatbots with minimal reliance on manual intervention.

---

### UniStitch: Unifying Semantic and Geometric Features for Image Stitching

Authors: Yuan Mei, Lang Nie, Kang Liao, Yunqiu Xu, Chunyu Lin, Bin Xiao
Published: 2026-03-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.10568v2

Traditional image stitching methods estimate warps from hand-crafted geometric features, whereas recent learning-based solutions leverage semantic features from neural networks instead. These two lines of research have largely diverged along separate evolution, with virtually no meaningful convergence to date. In this paper, we take a pioneering step to bridge this gap by unifying semantic and geometric features with UniStitch, a unified image stitching framework from multimodal features. To align discrete geometric features (i.e., keypoint) with continuous semantic feature maps, we present a Neural Point Transformer (NPT) module, which transforms unordered, sparse 1D geometric keypoints into ordered, dense 2D semantic maps. Then, to integrate the advantages of both representations, an Adaptive Mixture of Experts (AMoE) module is designed to fuse geometric and semantic representations. It dynamically shifts focus toward more reliable features during the fusion process, allowing the model to handle complex scenes, especially when either modality might be compromised. The fused representation can be adopted into common deep stitching pipelines, delivering significant performance gains over any single feature. Experiments show that UniStitch outperforms existing state-of-the-art methods with a large margin, paving the way for a unified paradigm between traditional and learning-based image stitching.

---

### Adaptive RAN Slicing Control via Reward-Free Self-Finetuning Agents

Authors: Yuanhao Li, Haozhe Wang, Geyong Min, Nektarios Georgalas, Wang Miao
Published: 2026-03-11
Categories: cs.AI, cs.NI
arXiv: https://arxiv.org/abs/2603.10564v1

The integration of Generative AI models into AI-native network systems offers a transformative path toward achieving autonomous and adaptive control. However, the application of such models to continuous control tasks is impeded by intrinsic architectural limitations, including finite context windows, the lack of explicit reward signals, and the degradation of the long context. This paper posits that the key to unlocking robust continuous control is enabling agents to internalize experience by distilling it into their parameters, rather than relying on prompt-based memory. To this end, we propose a novel self-finetuning framework that enables agentic systems to learn continuously through direct interaction with the environment, bypassing the need for handcrafted rewards. Our framework implements a bi-perspective reflection mechanism that generates autonomous linguistic feedback to construct preference datasets from interaction history. A subsequent preference-based fine-tuning process distills long-horizon experiences into the model's parameters. We evaluate our approach on a dynamic Radio Access Network (RAN) slicing task, a challenging multi-objective control problem that requires the resolution of acute trade-offs between spectrum efficiency, service quality, and reconfiguration stability under volatile network conditions. Experimental results show that our framework outperforms standard Reinforcement Learning (RL) baselines and existing Large Language Model (LLM)-based agents in sample efficiency, stability, and multi-metric optimization. These findings demonstrate the potential of self-improving generative agents for continuous control tasks, paving the way for future AI-native network infrastructure.

---