# Research Papers — 2026-04 · bundle page 136 of 233

> Full-text markdown of papers #6751–6800 of 11612 published in 2026-04, newest first. AI-readable mirrors of the full 11612-paper 2026-04 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-04/page/136
[← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/135.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-04/page/137.md)

### TAG-Head: Time-Aligned Graph Head for Plug-and-Play Fine-grained Action Recognition

Authors: Imtiaz Ul Hassan, Nik Bessis, Ardhendu Behera
Published: 2026-04-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.11498v1

Fine-grained human action recognition (FHAR) is challenging because visually similar actions differ by subtle spatio-temporal cues. Many recent systems enhance discriminability with extra modalities (e.g., pose, text, optical flow), but this increases annotation burden and computational cost. We introduce TAG-Head, a lightweight spatio-temporal graph head that upgrades standard 3D backbones (SlowFast, R(2+1)D-34, I3D, etc.) for FHAR using RGB only. Our pipeline first applies a Transformer encoder with learnable 3D positional encodings to the backbone tokens, capturing long-range dependencies across space and time. The resulting features are then refined by a graph in which (i) fully-connected intra-frame edges to resolve subtle appearance differences within frames, and (ii) time-aligned temporal edges that connect features at the same spatial location across frames to stabilise motion cues without over-smoothing. The head is compact (little parameter/FLOP overhead), plug-and-play across backbones, and trained end-to-end with the backbone. Extensive evaluations on FineGym (Gym99 and Gym288) and HAA500 show that TAG-Head sets a new state-of-the-art among RGB-only models and surpasses many recent multimodal approaches (video + pose + text) that rely on privileged information. Ablations disentangle the contributions of the Transformer and the graph topology, and complexity analyses confirm low latency. TAG-Head advances FHAR by explicitly coupling global context with high-resolution spatial interactions and low-variance temporal continuity inside a slim, composable graph head. The simplicity of the design enables straightforward adoption in practical systems that favour RGB-only sensors, while delivering performance gains typically associated with heavier or multimodal models. Code will be released on GitHub.

---

### Revisiting Compositionality in Dual-Encoder Vision-Language Models: The Role of Inference

Authors: Imanol Miranda, Ander Salaberria, Eneko Agirre, Gorka Azkune
Published: 2026-04-13
Categories: cs.CV, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2604.11496v2

Dual-encoder Vision-Language Models (VLMs) such as CLIP are often characterized as bag-of-words systems due to their poor performance on compositional benchmarks. We argue that this limitation may stem less from deficient representations than from the standard inference protocol based on global cosine similarity. First, through controlled diagnostic experiments, we show that explicitly enforcing fine-grained region-segment alignment at inference dramatically improves compositional performance without updating pretrained encoders. We then introduce a lightweight transformer that learns such alignments directly from frozen patch and token embeddings. Comparing against full fine-tuning and prior end-to-end compositional training methods, we find that although these approaches improve in-domain retrieval, their gains do not consistently transfer under distribution shift. In contrast, learning localized alignment over frozen representations matches full fine-tuning on in-domain retrieval while yielding substantial improvements on controlled out-of-domain compositional benchmarks. These results identify global embedding matching as a key bottleneck in dual-encoder VLMs and highlight the importance of alignment mechanisms for robust compositional generalization.

---

### ADD for Multi-Bit Image Watermarking

Authors: An Luo, Jie Ding
Published: 2026-04-13
Categories: stat.ML, cs.AI, cs.LG, math.ST, stat.ME
arXiv: https://arxiv.org/abs/2604.11491v1

As generative models enable rapid creation of high-fidelity images, societal concerns about misinformation and authenticity have intensified. A promising remedy is multi-bit image watermarking, which embeds a multi-bit message into an image so that a verifier can later detect whether the image is generated by someone and further identify the source by decoding the embedded message. Existing approaches often fall short in capacity, resilience to common image distortions, and theoretical justification. To address these limitations, we propose ADD (Add, Dot, Decode), a multi-bit image watermarking method with two stages: learning a watermark to be linearly combined with the multi-bit message and added to the image, and decoding through inner products between the watermarked image and the learned watermark. On the standard MS-COCO benchmark, we demonstrate that for the challenging task of 48-bit watermarking, ADD achieves 100\% decoding accuracy, with performance dropping by at most 2\% under a wide range of image distortions, substantially smaller than the 14\% average drop of state-of-the-art methods. In addition, ADD achieves substantial computational gains, with 2-fold faster embedding and 7.4-fold faster decoding than the fastest existing method. We further provide a theoretical analysis explaining why the learned watermark and the corresponding decoding rule are effective.

---

### Anthropogenic Regional Adaptation in Multimodal Vision-Language Model

Authors: Samuel Cahyawijaya, Peerat Limkonchotiwat, Tack Hwa Wong, Hitesh Laxmichand Patel, Amit Agarwal, Manuel Antonio Rufino, Carlos Rafael Catalan, Muhammad Reza Qorib, Vicky Feliren, Holy Lovenia, Aye Hninn Khine, Frederikus Hudi et al.
Published: 2026-04-13
Categories: cs.AI, cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2604.11490v2

While the field of vision-language (VL) has achieved remarkable success in integrating visual and textual information across multiple languages and domains, there is still no dedicated framework for assessing human-centric alignment in vision-language systems. We offer two contributions to address this gap. First, we introduce Anthropogenic Regional Adaptation: a novel paradigm that aims to optimize model relevance to specific regional contexts while ensuring the retention of global generalization capabilities. Second, we present a simple, but effective adaptation method named Geographical-generalization-made-easy (GG-EZ), which utilizes regional data filtering and model merging. Through comprehensive experiments on 3 VL architectures: large vision-language models, text-to-image diffusion models, and vision-language embedding models, and a case study in Southeast Asia (SEA) regional adaptation, we demonstrate the importance of Anthropogenic Regional Adaptation and the effectiveness of GG-EZ, showing 5-15% gains in cultural relevance metrics across SEA while maintaining over 98% of global performance and even occasionally surpassing it. Our findings establish Anthropogenic Regional Alignment as a foundational paradigm towards applicability of multimodal vision-language models in diverse regions and demonstrate a simple-yet-effective baseline method that optimizes regional value alignment while preserving global generalization.

---

### NTIRE 2026 Challenge on Robust AI-Generated Image Detection in the Wild

Authors: Aleksandr Gushchin, Khaled Abud, Ekaterina Shumitskaya, Artem Filippov, Georgii Bychkov, Sergey Lavrushkin, Mikhail Erofeev, Anastasia Antsiferova, Changsheng Chen, Shunquan Tan, Radu Timofte, Dmitry Vatolin et al.
Published: 2026-04-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.11487v1

This paper presents an overview of the NTIRE 2026 Challenge on Robust AI-Generated Image Detection in the Wild, held in conjunction with the NTIRE workshop at CVPR 2026. The goal of this challenge was to develop detection models capable of distinguishing real images from generated ones in realistic scenarios: the images are often transformed (cropped, resized, compressed, blurred) for practical usage, and therefore, the detection models should be robust to such transformations. The challenge is based on a novel dataset consisting of 108,750 real and 185,750 AI-generated images from 42 generators comprising a large variety of open-source and closed-source models of various architectures, augmented with 36 image transformations. Methods were evaluated using ROC AUC on the full test set, including both transformed and untransformed images. A total of 511 participants registered, with 20 teams submitting valid final solutions. This report provides a comprehensive overview of the challenge, describes the proposed solutions, and can be used as a valuable reference for researchers and practitioners in increasing the robustness of the detection models to real-world transformations.

---

### PACO: Proxy-Task Alignment and Online Calibration for On-the-Fly Category Discovery

Authors: Weidong Tang, Bohan Zhang, Zhixiang Chi, ZiZhang Wu, Yang Wang, Yanan Wu
Published: 2026-04-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.11484v1

On-the-Fly Category Discovery (OCD) requires a model, trained on an offline support set, to recognize known classes while discovering new ones from an online streaming sequence. Existing methods focus heavily on offline training. They aim to learn discriminative representations on the support set so that novel classes can be separated at test time. However, their discovery mechanism at inference is typically reduced to a single threshold. We argue that this paradigm is fundamentally flawed as OCD is not a static classification problem, but a dynamic process. The model must continuously decide 1) whether a sample belongs to a known class, 2) matches an existing novel category, or 3) should initiate a new one. Moreover, prior methods treat the support set as fixed knowledge. They do not update their decision boundaries as new evidence arrives during inference. This leads to unstable and inconsistent category formation. Our experiments confirm these issues. With properly calibrated and adaptive thresholds, substantial improvements can be achieved, even without changing the representation. Motivated by this, we propose PACO, a support-set-calibrated, tree-structured online decision framework. The framework models inference as a sequence of hierarchical decisions, including known-class routing, birth-aware novel assignment, and attach-versus-create operations over a dynamic prototype memory. Furthermore, we simulate the proxy discovery process to initialize the thresholds during offline training to align with inference. Thresholds are continuously updated during inference using mature novel prototypes. Importantly, PACO requires no heavy training and no dataset-specific tuning. It can be directly integrated into existing OCD pipelines as an inference-time module. Extensive experiments show significant improvements over SOTA baselines across seven benchmarks.

---

### CAGenMol: Condition-Aware Diffusion Language Model for Goal-Directed Molecular Generation

Authors: Yanting Li, Zhuoyang Jiang, Enyan Dai, Lei Wang, Wen-Cai Ye, Li Liu
Published: 2026-04-13
Categories: cs.LG, q-bio.QM
arXiv: https://arxiv.org/abs/2604.11483v1

Goal-directed molecular generation requires satisfying heterogeneous constraints such as protein--ligand compatibility and multi-objective drug-like properties, yet existing methods often optimize these constraints in isolation, failing to reconcile conflicting objectives (e.g., affinity vs. safety), and struggle to navigate the non-differentiable chemical space without compromising structural validity. To address these challenges, we propose CAGenMol, a condition-aware discrete diffusion framework over molecular sequences that formulates molecular design as conditional denoising guided by heterogeneous structural and property signals. By coupling discrete diffusion with reinforcement learning, the model aligns the generation trajectory with non-differentiable objectives while preserving chemical validity and diversity. The non-autoregressive nature of diffusion language model further enables iterative refinement of molecular fragments at inference time. Experiments on structure-conditioned, property-conditioned, and dual-conditioned benchmarks demonstrate consistent improvements over state-of-the-art methods in binding affinity, drug-likeness, and success rate, highlighting the effectiveness of our framework.

---

### On the Complexity of the Discussion-based Semantics in Abstract Argumentation

Authors: Lydia Blümel, Kai Sauerwald, Kenneth Skiba, Matthias Thimm
Published: 2026-04-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.11480v2

We show that deciding whether an argument a is stronger than an argument b with respect to the discussion-based semantics of Amgoud and Ben-Naim is decidable in polynomial time. At its core, this problem is about deciding whether, for two vertices in a graph, the number of walks of each length ending in those vertices is the same. We employ results from automata theory and reduce this problem to the equivalence problem for semiring automata. This offers a new perspective on the computational complexity of ranking semantics, an area in which the complexity of many semantics remains open.

---

### Structural Consequences of Policy-Based Interventions on the Global Supply Chain Network

Authors: Lea Karbevska, Liming Xu, Zehui Dai, Sara AlMahri, Alexandra Brintrup
Published: 2026-04-13
Categories: cs.LG, econ.GN, physics.soc-ph
arXiv: https://arxiv.org/abs/2604.11479v2

As global political tensions rise and the anticipation of additional tariffs from the United States on international trade increases, the issues of economic independence and supply chain resilience become more prominent. The importance of supply chain resilience has been further underscored by disruptions caused by the COVID-19 pandemic and the ongoing war in Ukraine. In light of these challenges, ranging from geopolitical instability to product supply uncertainties, governments are increasingly focused on adopting new trade policies. This study explores the impact of several of these policies on the global electric vehicle (EV) supply chain network, with a particular focus on their effects on country clusters and the broader structure of international trade. Specifically, we analyse three key policies: Country Plus One, Friendshoring, and Reshoring. Our findings show that Friendshoring, contrary to expectations, leads to greater globalisation by increasing the number of supply links across friendly countries, potentially raising transaction costs. The Country Plus One policy similarly enhances network density through redundant links, while the Reshoring policy creates challenges in the EV sector due to the high number of irreplaceable products. Additionally, the effects of these policies vary across industries; for instance, mining goods being less affected in Country Plus One than the Friendshoring policy.

---

### OOM-RL: Out-of-Money Reinforcement Learning Market-Driven Alignment for LLM-Based Multi-Agent Systems

Authors: Kun Liu, Liqun Chen
Published: 2026-04-13
Categories: cs.AI, cs.SE, q-fin.TR
arXiv: https://arxiv.org/abs/2604.11477v1

The alignment of Multi-Agent Systems (MAS) for autonomous software engineering is constrained by evaluator epistemic uncertainty. Current paradigms, such as Reinforcement Learning from Human Feedback (RLHF) and AI Feedback (RLAIF), frequently induce model sycophancy, while execution-based environments suffer from adversarial "Test Evasion" by unconstrained agents. In this paper, we introduce an objective alignment paradigm: \textbf{Out-of-Money Reinforcement Learning (OOM-RL)}. By deploying agents into the non-stationary, high-friction reality of live financial markets, we utilize critical capital depletion as an un-hackable negative gradient. Our longitudinal 20-month empirical study (July 2024 -- February 2026) chronicles the system's evolution from a high-turnover, sycophantic baseline to a robust, liquidity-aware architecture. We demonstrate that the undeniable ontological consequences of financial loss forced the MAS to abandon overfitted hallucinations in favor of the \textbf{Strict Test-Driven Agentic Workflow (STDAW)}, which enforces a Byzantine-inspired uni-directional state lock (RO-Lock) anchored to a deterministically verified $\geq 95\%$ code coverage constraint matrix. Our results show that while early iterations suffered severe execution decay, the final OOM-RL-aligned system achieved a stable equilibrium with an annualized Sharpe ratio of 2.06 in its mature phase. We conclude that substituting subjective human preference with rigorous economic penalties provides a robust methodology for aligning autonomous agents in high-stakes, real-world environments, laying the groundwork for generalized paradigms where computational billing acts as an objective physical constraint

---

### Learning How Much to Think: Difficulty-Aware Dynamic MoEs for Graph Node Classification

Authors: Jiajun Zhou, Yadong Li, Xuanze Chen, Chen Ma, Chuang Zhao, Shanqing Yu, Qi Xuan
Published: 2026-04-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.11473v1

Mixture-of-Experts (MoE) architectures offer a scalable path for Graph Neural Networks (GNNs) in node classification tasks but typically rely on static and rigid routing strategies that enforce a uniform expert budget or coarse-grained expert toggles on all nodes. This limitation overlooks the varying discriminative difficulty of nodes and leads to under-fitting for hard nodes and redundant computation for easy ones. To resolve this issue, we propose D2MoE, a novel framework that shifts the focus from static expert selection to node-wise expert resource allocation. By using predictive entropy as a real-time proxy for difficulty, D2MoE employs a difficulty-driven top-p routing mechanism to adaptively concentrate expert resources on hard nodes while reducing overhead for easy ones, achieving continuous and fine-grained expert budget scaling for node classification. Experiments on 13 benchmarks demonstrate that D2MoE achieves consistent state-of-the-art performance, surpassing leading baselines by up to 7.92% in accuracy on heterophilous graphs. Notably, on large-scale graphs, it reduces memory consumption by up to 73.07% and training time by 46.53% compared to the best-performing Graph MoE, thereby validating its superior efficiency.

---

### Degradation-Aware and Structure-Preserving Diffusion for Real-World Image Super-Resolution

Authors: Yang Ji, Zonghao Chen, Zhihao Xue, Junqin Hu
Published: 2026-04-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.11470v1

Real-world image super-resolution is particularly challenging for diffusion models because real degradations are complex, heterogeneous, and rarely modeled explicitly. We propose a degradation-aware and structure-preserving diffusion framework for real-world SR. Specifically, we introduce Degradation-aware Token Injection, which encodes lightweight degradation statistics from low-resolution inputs and fuses them with semantic conditioning features, enabling explicit degradation-aware restoration. We further propose Spatially Asymmetric Noise Injection, which modulates diffusion noise with local edge strength to better preserve structural regions during training. Both modules are lightweight add-ons to the adopted diffusion SR framework, requiring only minor modifications to the conditioning pipeline. Experiments on DIV2K and RealSR show that our method delivers competitive no-reference perceptual quality and visually more realistic restoration results than recent baselines, while maintaining a favorable perception--distortion trade-off. Ablations confirm the effectiveness of each module and their complementary gains when combined. The code and model are publicly available at https://github.com/jiyang0315/DASP-SR.git.

---

### Beyond Model Design: Data-Centric Training and Self-Ensemble for Gaussian Color Image Denoising

Authors: Gengjia Chang, Xining Ge, Weijun Yuan, Zhan Li, Qiurong Song, Luen Zhu, Shuhong Liu
Published: 2026-04-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.11468v2

This paper presents our solution to the NTIRE 2026 Image Denoising Challenge (Gaussian color image denoising at fixed noise level $σ= 50$). Rather than proposing a new restoration backbone, we revisit the performance boundary of the mature Restormer architecture from two complementary directions: stronger data-centric training and more complete Test-Time capability release. Starting from the public Restormer $σ\!=\!50$ baseline, we expand the standard multi-dataset training recipe with larger and more diverse public image corpora and organize optimization into two stages. At inference, we apply $\times 8$ geometric self-ensemble to further release model capacity. A TLC-style local inference wrapper is retained for implementation consistency; however, systematic ablation reveals its quantitative contribution to be negligible in this setting. On the challenge validation set of 100 images, our final submission achieves 30.762 dB PSNR and 0.861 SSIM, improving over the public Restormer $σ\!=\!50$ pretrained baseline by up to 3.366 dB PSNR. Ablation studies show that the dominant gain originates from the expanded training corpus and the two-stage optimization schedule, and self-ensemble provides marginal but consistent improvement.

---

### From Attribution to Action: A Human-Centered Application of Activation Steering

Authors: Tobias Labarta, Maximilian Dreyer, Katharina Weitz, Wojciech Samek, Sebastian Lapuschkin
Published: 2026-04-13
Categories: cs.AI, cs.HC, cs.LG
arXiv: https://arxiv.org/abs/2604.11467v2

Explainable AI (XAI) methods reveal which features influence model predictions, yet provide limited means for practitioners to act on these explanations. Activation steering of components identified via XAI offers a path toward actionable explanations, although its practical utility remains understudied. We introduce an interactive workflow combining SAE-based attribution with activation steering for instance-level analysis of concept usage in vision models, implemented as a web-based tool. Based on this workflow, we conduct semi-structured expert interviews (N=8) with debugging tasks on CLIP to investigate how practitioners reason about, trust, and apply activation steering. We find that steering enables a shift from inspection to intervention-based hypothesis testing (8/8 participants), with most grounding trust in observed model responses rather than explanation plausibility alone (6/8). Participants adopted systematic debugging strategies dominated by component suppression (7/8) and highlighted risks including ripple effects and limited generalization of instance-level corrections. Overall, activation steering renders interpretability more actionable while raising important considerations for safe and effective use.

---

### SLALOM: Simulation Lifecycle Analysis via Longitudinal Observation Metrics for Social Simulation

Authors: Juhoon Lee, Joseph Seering
Published: 2026-04-13
Categories: cs.MA, cs.AI
arXiv: https://arxiv.org/abs/2604.11466v1

Large Language Model (LLM) agents offer a potentially-transformative path forward for generative social science but face a critical crisis of validity. Current simulation evaluation methodologies suffer from the "stopped clock" problem: they confirm that a simulation reached the correct final outcome while ignoring whether the trajectory leading to it was sociologically plausible. Because the internal reasoning of LLMs is opaque, verifying the "black box" of social mechanisms remains a persistent challenge. In this paper, we introduce SLALOM (Simulation Lifecycle Analysis via Longitudinal Observation Metrics), a framework that shifts validation from outcome verification to process fidelity. Drawing on Pattern-Oriented Modeling (POM), SLALOM treats social phenomena as multivariate time series that must traverse specific SLALOM gates, or intermediate waypoint constraints representing distinct phases. By utilizing Dynamic Time Warping (DTW) to align simulated trajectories with empirical ground truth, SLALOM offers a quantitative metric to assess structural realism, helping to differentiate plausible social dynamics from stochastic noise and contributing to more robust policy simulation standards.

---

### Three Roles, One Model: Role Orchestration at Inference Time to Close the Performance Gap Between Small and Large Agents

Authors: S. Aaron McClendon, Jorge Gallego-Feliciano, Stavros Zervoudakis, Antonios Saravanos
Published: 2026-04-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.11465v2

Large language model (LLM) agents show promise on realistic tool-use tasks, but deploying capable agents on modest hardware remains challenging. We study whether inference-time scaffolding alone, without any additional training compute, can improve the performance of a small model in complex multi-step environments. Operating on a single 24GB GPU, we evaluate Qwen3-8B on the AppWorld benchmark under both full-precision and 4-bit quantized configurations. Without any intervention, the raw model achieves just 5.4% (FP16) and 3.0% (AWQ) task goal completion. Guided by a systematic failure mode analysis, we introduce a three-tier inference scaffolding pipeline that deploys the same frozen model in three distinct roles: (1) a summarization model that preserves critical artifacts (tokens, credentials, API responses) while compressing dialogue history; (2) the main agent model that reasons over the compressed context; and (3) an isolated correction model that reviews and revises the agent's code output without access to conversation history, breaking repetitive failure loops. Applied to the same unmodified model, this scaffolding yields 8.9% (FP16) and 5.9% (AWQ) task goal completion, roughly doubling performance in both settings, with particularly strong gains on difficulty-1 tasks (15.8% to 26.3% FP16; 5.3% to 14.0% AWQ). On full-precision inference, our scaffolded 8B model surpasses DeepSeek-Coder 33B Instruct (7.1%) from the original AppWorld evaluation, demonstrating that structured inference-time interventions can make small models competitive with systems 4 times their size. We formalize the approach as a scaffolded policy over a frozen base model, three invocations of the same weights with different conditioning, drawing connections to test-time compute scaling and action-space shaping in reinforcement learning.

---

### Escaping the Context Bottleneck: Active Context Curation for LLM Agents via Reinforcement Learning

Authors: Xiaozhe Li, Tianyi Lyu, Yizhao Yang, Liang Shan, Siyi Yang, Ligao Zhang, Zhuoyi Huang, Qingwen Liu, Yang Li
Published: 2026-04-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.11462v1

Large Language Models (LLMs) struggle with long-horizon tasks due to the "context bottleneck" and the "lost-in-the-middle" phenomenon, where accumulated noise from verbose environments degrades reasoning over multi-turn interactions. To address this issue, we introduce a symbiotic framework that decouples context management from task execution. Our architecture pairs a lightweight, specialized policy model, ContextCurator, with a powerful frozen foundation model, TaskExecutor. Trained via reinforcement learning, ContextCurator actively reduces information entropy in the working memory. It aggressively prunes environmental noise while preserving reasoning anchors, that is, sparse data points that are critical for future deductions. On WebArena, our framework improves the success rate of Gemini-3.0-flash from 36.4% to 41.2% while reducing token consumption by 8.8% (from 47.4K to 43.3K). On DeepSearch, it achieves a 57.1% success rate, compared with 53.9%, while reducing token consumption by a factor of 8. Remarkably, a 7B ContextCurator matches the context management performance of GPT-4o, providing a scalable and computationally efficient paradigm for autonomous long-horizon agents.

---

### Low-rank Optimization Trajectories Modeling for LLM RLVR Acceleration

Authors: Zhipeng Chen, Tao Qian, Wayne Xin Zhao, Ji-Rong Wen
Published: 2026-04-13
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2604.11446v1

Recently, scaling reinforcement learning with verifiable rewards (RLVR) for large language models (LLMs) has emerged as an effective training paradigm for significantly improving model capabilities, which requires guiding the model to perform extensive exploration and learning, leading to substantial computational overhead and becoming a key challenge. To reduce the number of training steps, Prior work performs linear extrapolation of model parameters. However, the dynamics of model parameter updates during RLVR training remain insufficiently understood. To further investigate the evolution of LLMs during RLVR training, we conduct empirical experiments and find that the rank-1 subspace of the model does not evolve linearly, and its dominance over the original parameters is further amplified during LoRA training. Based on the above insights, we propose the \textbf{N}onlinear \textbf{Ext}rapolation of low-rank trajectories (\textbf{NExt}), a novel framework that models and extrapolates low-rank parameter trajectories in a nonlinear manner. Concretely, we first train the model using LoRA and extract the rank-1 subspace of parameter differences at multiple training steps, which is then used for the subsequent nonlinear extrapolation. Afterward, we utilized the extracted rank-1 subspace to train a predictor, which can model the trajectory of parameter updates during RLVR, and then perform the predict-extend process to extrapolate model parameters, achieving the acceleration of RLVR. To further study and understand NExt, we conduct comprehensive experiments that demonstrate the effectiveness and robustness of the method. Our method reduces computational overhead by approximately 37.5\% while remaining compatible with a wide range of RLVR algorithms and tasks. We release our code in https://github.com/RUCAIBox/NExt.

---

### HuiYanEarth-SAR: A Foundation Model for High-Fidelity and Low-Cost Global Remote Sensing Imagery Generation

Authors: Yongxiang Liu, Jie Zhou, Yafei Song, Tianpeng Liu, Li Liu
Published: 2026-04-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.11444v1

Synthetic Aperture Radar (SAR) imagery generation is essential for deepening the study of scattering mechanisms, establishing trustworthy electromagnetic scene models, and fundamentally alleviating the data scarcity bottleneck that constrains development in this field. However, existing methods find it difficult to simultaneously ensure high fidelity in both global geospatial semantics and microscopic scattering mechanisms, resulting in severe challenges for global generation. To address this, we propose \textbf{HuiYanEarth-SAR}, the first foundational SAR imagery generation model based on AlphaEarth and integrated scattering mechanisms. By injecting geospatial priors to control macroscopic structures and utilizing implicit scattering characteristic modeling to ensure the authenticity of microscopic textures, we achieve the capability of generating high-fidelity SAR images for global locations solely based on geographic coordinates. This study not only constructs an efficient SAR scene simulator but also establishes a bridge connecting geography, scatter mechanism, and artificial intelligence from a methodological standpoint. It advances SAR research by expanding the paradigm from perception and understanding to simulation and creation, providing key technical support for constructing a high-confidence digital twin of the Earth.

---

### Think Before you Write: QA-Guided Reasoning for Character Descriptions in Books

Authors: Argyrios Papoudakis, Mirella Lapata, Frank Keller
Published: 2026-04-13
Categories: cs.CL, cs.AI, cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2604.11435v1

Character description generation is an important capability for narrative-focused applications such as summarization, story analysis, and character-driven simulations. However, generating accurate character descriptions from long-form narratives (e.g., novels) is challenging: models must track evolving attributes (e.g., relationships and events), integrate evidence scattered across the text, and infer implicit details. Despite the success of reasoning-enabled LLMs on many benchmarks, we find that for character description generation their performance improves when built-in reasoning is disabled (i.e., an empty reasoning trace). Motivated by this, we propose a training framework that decouples reasoning from generation. Our approach, which can be applied on top of long-context LLMs or chunk-based methods, consists of a reasoning model that produces a structured QA reasoning trace and a generation model that conditions on this trace to produce the final character description. Experiments on two datasets (BookWorm and CroSS) show that QA-guided reasoning improves faithfulness, informativeness, and grounding over strong long-context baselines.

---

### Hardening x402: PII-Safe Agentic Payments via Pre-Execution Metadata Filtering

Authors: Vladimir Stantchev
Published: 2026-04-13
Categories: cs.CR, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2604.11430v2

AI agents that pay for resources via the x402 protocol embed payment metadata - resource URLs, descriptions, and reason strings - in every HTTP payment request. This metadata is transmitted to the payment server and to the centralised facilitator API before any on-chain settlement occurs; neither party is typically bound by a data processing agreement. We present presidio-hardened-x402, the first open-source middleware that intercepts x402 payment requests before transmission to detect and redact personally identifiable information (PII), enforce declarative spending policies, and block duplicate replay attempts. To evaluate the PII filter, we construct a labeled synthetic corpus of 2,000 x402 metadata triples spanning seven use-case categories, and run a 42-configuration precision/recall sweep across two detection modes (regex, NLP) and five confidence thresholds. The recommended configuration (mode=nlp, min_score=0.4, all entity types) achieves micro-F1 = 0.894 with precision 0.972, at a p99 latency of 5.73ms - well within the 50ms overhead budget. The middleware, corpus, and all experiment code are publicly available at https://github.com/presidio-v/presidio-hardened-x402.

---

### METRO: Towards Strategy Induction from Expert Dialogue Transcripts for Non-collaborative Dialogues

Authors: Haofu Yang, Jiaji Liu, Chen Huang, Faguo Wu, Wenqiang Lei, See-Kiong Ng
Published: 2026-04-13
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2604.11427v3

Developing non-collaborative dialogue agents traditionally requires the manual, unscalable codification of expert strategies. We propose \ours, a method that leverages large language models to autonomously induce both strategy actions and planning logic directly from raw transcripts. METRO formalizes expert knowledge into a Strategy Forest, a hierarchical structure that captures both short-term responses (nodes) and long-term strategic foresight (branches). Experimental results across two benchmarks show that METRO demonstrates promising performance, outperforming existing methods by an average of 9%-10%. Our further analysis not only reveals the success behind METRO (strategic behavioral diversity and foresight), but also demonstrates its robust cross-task transferability. This offers new insights into building non-collaborative agents in a cost-effective and scalable way. Our code is available at https://github.com/Humphrey-0125/METRO.

---

### Bridging What the Model Thinks and How It Speaks: Expressive Speech Generation via Self-Aware Intent-Realization Alignment

Authors: Kuang Wang, Lai Wei, Ping Lin, Qibing Bai, Wenkai Fang, Li Zhou, Feng Jiang, Zhongjie Jiang, Jun Huang, Yannan Wang, Haizhou Li
Published: 2026-04-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.11424v2

Speech Language Models (SLMs) exhibit strong semantic understanding, yet often fail to translate this capacity into expressive acoustic realization, producing speech with flattened prosody and misaligned emotion. We identify this mismatch as the semantic understanding-acoustic realization gap. Existing approaches typically rely on externally specified proxies, such as emotion labels or style prompts, which require annotations and struggle to capture dynamically evolving expressive intent throughout dialogue. To overcome these limitations, we propose SASLM (Self-Aware Speech Language Model), a proxy-free framework that bridges what the model thinks and how it speaks through self-aware intent-realization alignment: (1) Intent-Aware Bridging self-distills expressive intent from the model's own evolving semantic generation states via a Variational Information Bottleneck (VIB), thereby guiding expressive speech realization without external expressive supervision; while (2) Realization-Aware Alignment reflectively aligns generated acoustics with intended expression through self-reward optimization, progressively improving intent-realization consistency during speech generation. Despite using only 3B parameters and 800 hours of expressive speech data, SASLM achieves state-of-the-art performance on EchoMind among open-source systems, surpassing models over 10 times larger and approaching commercial systems.

---

### Emulating Non-Differentiable Metrics via Knowledge-Guided Learning: Introducing the Minkowski Image Loss

Authors: Filippo Quarenghi, Ryan Cotsakis, Tom Beucler
Published: 2026-04-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2604.11422v1

The ``differentiability gap'' presents a primary bottleneck in Earth system deep learning: since models cannot be trained directly on non-differentiable scientific metrics and must rely on smooth proxies (e.g., MSE), they often fail to capture high-frequency details, yielding ``blurry'' outputs. We develop a framework that bridges this gap using two different methods to deal with non-differentiable functions: the first is to analytically approximate the original non-differentiable function into a differentiable equivalent one; the second is to learn differentiable surrogates for scientific functionals. We formulate the analytical approximation by relaxing discrete topological operations using temperature-controlled sigmoids and continuous logical operators. Conversely, our neural emulator uses Lipschitz-convolutional neural networks to stabilize gradient learning via: (1) spectral normalization to bound the Lipschitz constant; and (2) hard architectural constraints enforcing geometric principles. We demonstrate this framework's utility by developing the Minkowski image loss, a differentiable equivalent for the integral-geometric measures of surface precipitation fields (area, perimeter, connected components). Validated on the EUMETNET OPERA dataset, our constrained neural surrogate achieves high emulation accuracy, completely eliminating the geometric violations observed in unconstrained baselines. However, applying these differentiable surrogates to a deterministic super-resolution task reveals a fundamental trade-off: while strict Lipschitz regularization ensures optimization stability, it inherently over-smooths gradient signals, restricting the recovery of highly localized convective textures. This work highlights the necessity of coupling such topological constraints with stochastic generative architectures to achieve full morphological realism.

---

### Beyond RAG for Cyber Threat Intelligence: A Systematic Evaluation of Graph-Based and Agentic Retrieval

Authors: Dzenan Hamzic, Florian Skopik, Max Landauer, Markus Wurzenberger, Andreas Rauber
Published: 2026-04-13
Categories: cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2604.11419v1

Cyber threat intelligence (CTI) analysts must answer complex questions over large collections of narrative security reports. Retrieval-augmented generation (RAG) systems help language models access external knowledge, but traditional vector retrieval often struggles with queries that require reasoning over relationships between entities such as threat actors, malware, and vulnerabilities. This limitation arises because relevant evidence is often distributed across multiple text fragments and documents. Knowledge graphs address this challenge by enabling structured multi-hop reasoning through explicit representations of entities and relationships. However, multiple retrieval paradigms, including graph-based, agentic, and hybrid approaches, have emerged with different assumptions and failure modes. It remains unclear how these approaches compare in realistic CTI settings and when graph grounding improves performance. We present a systematic evaluation of four RAG architectures for CTI analysis: standard vector retrieval, graph-based retrieval over a CTI knowledge graph, an agentic variant that repairs failed graph queries, and a hybrid approach combining graph queries with text retrieval. We evaluate these systems on 3,300 CTI question-answer pairs spanning factual lookups, multi-hop relational queries, analyst-style synthesis questions, and unanswerable cases. Results show that graph grounding improves performance on structured factual queries. The hybrid graph-text approach improves answer quality by up to 35 percent on multi-hop questions compared to vector RAG, while maintaining more reliable performance than graph-only systems.

---

### Efficient Emotion-Aware Iconic Gesture Prediction for Robot Co-Speech

Authors: Edwin C. Montiel-Vazquez, Christian Arzate Cruz, Stefanos Gkikas, Thomas Kassiotis, Giorgos Giannakakis, Randy Gomez
Published: 2026-04-13
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2604.11417v5

Co-speech gestures increase engagement and improve speech understanding. Most data-driven robot systems generate rhythmic beat-like motion, yet few integrate semantic emphasis. To address this, we propose a lightweight transformer that derives iconic gesture placement and intensity from text and emotion alone, requiring no audio input at inference time. The model outperforms GPT-4o in both semantic gesture placement classification and intensity regression on the BEAT2 dataset, while remaining computationally compact and suitable for real-time deployment on embodied agents.

---

### Exact Certification of Neural Networks and Partition Aggregation Ensembles against Label Poisoning

Authors: Ajinkya Mohgaonkar, Lukas Gosch, Mahalakshmi Sabanayagam, Debarghya Ghoshdastidar, Stephan Günnemann
Published: 2026-04-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.11416v1

Label-flipping attacks, which corrupt training labels to induce misclassifications at inference, remain a major threat to supervised learning models. This drives the need for robustness certificates that provide formal guarantees about a model's robustness under adversarially corrupted labels. Existing certification frameworks rely on ensemble techniques such as smoothing or partition-aggregation, but treat the corresponding base classifiers as black boxes, yielding overly conservative guarantees. We introduce EnsembleCert, the first certification framework for partition-aggregation ensembles that utilizes white-box knowledge of the base classifiers. Concretely, EnsembleCert yields tighter guarantees than black-box approaches by aggregating per-partition white-box certificates to compute ensemble-level guarantees in polynomial time. To extract white-box knowledge from the base classifiers efficiently, we develop ScaLabelCert, a method that leverages the equivalence between sufficiently wide neural networks and kernel methods using the neural tangent kernel. ScaLabelCert yields the first exact, polynomial-time calculable certificate for neural networks against label-flipping attacks. EnsembleCert is either on par, or significantly outperforms the existing partition-based black box certificates. Exemplary, on CIFAR-10, our method can certify upto +26.5% more label flips in median over the test set compared to the existing black-box approach while requiring 100 times fewer partitions, thus, challenging the prevailing notion that heavy partitioning is a necessity for strong certified robustness.

---

### Observe Less, Understand More: Cost-aware Cross-scale Observation for Remote Sensing Understanding

Authors: Zhenghao Xie, Jing Xiao, Zhenqi Wang, Kexin Ma, Liang Liao, Gui-song Xia, Mi Wang
Published: 2026-04-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.11415v2

Remote sensing understanding inherently requires multi-resolution observation, since different targets and application tasks demand different levels of spatial detail. While low-resolution (LR) imagery enables efficient global observation, high-resolution (HR) imagery provides critical local details at a much higher acquisition cost and with limited coverage. This motivates a cross-scale sensing strategy that selectively acquires HR imagery guided by LR-based global perception to improve task performance under constrained cost. Existing HR sampling methods typically make selection decisions from isolated LR patches, thereby ignoring fine-grained intra-patch importance and cross-patch contextual interactions, leading to fragmented feature representation and suboptimal scene reasoning under sparse HR observations. To address this issue, we formulate cross-scale remote sensing understanding as a unified cost-aware problem that couples fine-grained HR sampling with cross-patch representation prediction, enabling more effective task reasoning with fewer HR observations. Furthermore, we present GL-10M, a high- and low-resolution dataset with nearly 100,000 scene pairs and 10 million images for large-scale cross-resolution pretraining. Extensive experiments on recognition and retrieval tasks show that our method consistently achieves a superior performance-cost trade-off. The code is publicly available at https://github.com/xzhacc/CrossSO.

---

### Observe Less, Understand More: Cost-aware Cross-scale Observation for Remote Sensing Understanding

Authors: Zhenghao Xie, Jing Xiao, Zhenqi Wang, Kexin Ma, Liang Liao, Gui-Song Xia, Mi Wang
Published: 2026-04-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.11415v1

Remote sensing understanding inherently requires multi-resolution observation, since different targets and application tasks demand different levels of spatial detail. While low-resolution (LR) imagery enables efficient global observation, high-resolution (HR) imagery provides critical local details at much higher acquisition cost and limited coverage. This motivates a cross-scale sensing strategy that selectively acquires HR imagery from LR-based global perception to improve task performance under constrained cost. Existing methods for HR sampling methods typically make selection decisions from isolated LR patches, which ignore fine-grained intra-patch importance and cross-patch contextual interactions, leading to fragmented feature representation and suboptimal scene reasoning under sparse HR observations. To address this issue, we formulate cross-scale remote sensing understanding as a unified cost-aware problem that couples fine-grained HR sampling with cross-patch representation prediction, enabling more effective task reasoning with fewer HR observations. Furthermore, we present GL-10M, a large-scale benchmark of 10 million spatially aligned multi-resolution images, enabling systematic evaluation of budget-constrained cross-scale reasoning in remote sensing. Extensive experiments on recognition and retrieval tasks show that our method consistently achieves a superior performance-cost trade-off.

---

### Online Reasoning Video Object Segmentation

Authors: Jinyuan Liu, Yang Wang, Zeyu Zhao, Weixin Li, Song Wang, Ruize Han
Published: 2026-04-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.11411v1

Reasoning video object segmentation predicts pixel-level masks in videos from natural-language queries that may involve implicit and temporally grounded references. However, existing methods are developed and evaluated in an offline regime, where the entire video is available at inference time and future frames can be exploited for retrospective disambiguation, deviating from real-world deployments that require strictly causal, frame-by-frame decisions. We study Online Reasoning Video Object Segmentation (ORVOS), where models must incrementally interpret queries using only past and current frames without revisiting previous predictions, while handling referent shifts as events unfold. To support evaluation, we introduce ORVOSB, a benchmark with frame-level causal annotations and referent-shift labels, comprising 210 videos, 12,907 annotated frames, and 512 queries across five reasoning categories. We further propose a baseline with continually-updated segmentation prompts and a structured temporal token reservoir for long-horizon reasoning under bounded computation. Experiments show that existing methods struggle under strict causality and referent shifts, while our baseline establishes a strong foundation for future research.

---

### Active Bayesian Inference for Robust Control under Sensor False Data Injection Attacks

Authors: Axel Andersson, György Dán
Published: 2026-04-13
Categories: cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2604.11410v1

We present a framework for bridging the gap between sensor attack detection and recovery in cyber-physical systems. The proposed framework models modern-day, complex perception pipelines as bipartite graphs, which combined with anomaly detector alerts defines a Bayesian network for inferring compromised sensors. An active probing strategy exploits system nonlinearities to maximize distinguishability between attack hypotheses, while compromised sensors are selectively disabled to maintain reliable state estimation. We propose a threshold-based probing strategy and show its effectiveness via a simplified partially observable Markov decision process (POMDP) formulation. Experiments on an inverted pendulum under single and multi-sensor attacks show that our method significantly outperforms outlier-robust and prediction-based baselines, especially under prolonged attacks.

---

### Retrieval as Generation: A Unified Framework with Self-Triggered Information Planning

Authors: Bo Li, Mingda Wang, Gexiang Fang, Shikun Zhang, Wei Ye
Published: 2026-04-13
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2604.11407v2

We revisit retrieval-augmented generation (RAG) by embedding retrieval control directly into generation. Instead of treating retrieval as an external intervention, we express retrieval decisions within token-level decoding, enabling end-to-end coordination without additional controllers or classifiers. Under the paradigm of Retrieval as Generation, we propose \textbf{GRIP} (\textbf{G}eneration-guided \textbf{R}etrieval with \textbf{I}nformation \textbf{P}lanning), a unified framework in which the model regulates retrieval behavior through control-token emission. Central to GRIP is \textit{Self-Triggered Information Planning}, which allows the model to decide when to retrieve, how to reformulate queries, and when to terminate, all within a single autoregressive trajectory. This design tightly couples retrieval and reasoning and supports dynamic multi-step inference with on-the-fly evidence integration. To supervise these behaviors, we construct a structured training set covering answerable, partially answerable, and multi-hop queries, each aligned with specific token patterns. Experiments on five QA benchmarks show that GRIP surpasses strong RAG baselines and is competitive with GPT-4o while using substantially fewer parameters.

---

### GlobalCY I: A JAX Framework for Globally Defined and Symmetry-Aware Neural Kähler Potentials

Authors: Abdul Rahman
Published: 2026-04-13
Categories: hep-th, cs.LG, math.AG
arXiv: https://arxiv.org/abs/2604.11404v1

We present \emph{GlobalCY}, a JAX-based framework for globally defined and symmetry-aware neural Kähler-potential models on projective hypersurface Calabi--Yau geometries. The central problem is that local-input neural Kähler-potential models can train successfully while still failing the geometry-sensitive diagnostics that matter in hard quartic regimes, especially near singular and near-singular members of the Cefalú family. To study this, we compare three model families -- a local-input baseline, a globally defined invariant model, and a symmetry-aware global model -- on the hard Cefalú cases $λ=0.75$ and $λ=1.0$ using a fixed multi-seed protocol and a geometry-aware diagnostic suite. In this benchmark, the globally defined invariant model is the strongest overall family, outperforming the local baseline on the two clearest geometric comparison metrics, negative-eigenvalue frequency and projective-invariance drift, in both cases. The gains are strongest at $λ=0.75$, while $λ=1.0$ remains more difficult. The current symmetry-aware model improves projective-invariance drift relative to the local baseline, but does not yet surpass the plain global invariant model. These results show that global invariant structure is a meaningful architectural constraint for learned Kähler-potential modeling in hard quartic Calabi--Yau settings.

---

### One Scale at a Time: Scale-Autoregressive Modeling for Fluid Flow Distributions

Authors: Mario Lino, Nils Thuerey
Published: 2026-04-13
Categories: cs.CE, cs.AI, physics.flu-dyn
arXiv: https://arxiv.org/abs/2604.11403v1

Analyzing unsteady fluid flows often requires access to the full distribution of possible temporal states, yet conventional PDE solvers are computationally prohibitive and learned time-stepping surrogates quickly accumulate error over long rollouts. Generative models avoid compounding error by sampling states independently, but diffusion and flow-matching methods, while accurate, are limited by the cost of many evaluations over the entire mesh. We introduce scale-autoregressive modeling (SAR) for sampling flows on unstructured meshes hierarchically from coarse to fine: it first generates a low-resolution field, then refines it by progressively sampling higher resolutions conditioned on coarser predictions. This coarse-to-fine factorization improves efficiency by concentrating computation at coarser scales, where uncertainty is greatest, while requiring fewer steps at finer scales. Across unsteady-flow benchmarks of varying complexity, SAR attains substantially lower distributional error and higher per-sample accuracy than state-of-the-art diffusion models based on multi-scale GNNs, while matching or surpassing a flow-matching Transolver (a linear-time transformer) yet running 2-7x faster than this depending on the task. Overall, SAR provides a practical tool for fast and accurate estimation of statistical flow quantities (e.g., turbulent kinetic energy and two-point correlations) in real-world settings.

---

### SCD4VPR: Multi-modal Scene Change Detection for Long-term Visual Place Recognition Database Update

Authors: Diwei Sheng, Vijayraj Gohil, Satyam Gaba, Zihan Liu, Giles Hamilton-Fletcher, John-Ross Rizzo, Yongqing Liang, Chen Feng
Published: 2026-04-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.11402v2

Long-term autonomy in mobile robotics requires maps that remain accurate as environments change over time. Visual Place Recognition (VPR), a core localization capability, degrades sharply as the temporal gap between query and database images grows, particularly across seasonal transitions. Scene Change Detection (SCD) offers a principled mechanism for database maintenance, but existing methods rely on binary, uni-modal visual features that cannot distinguish structural changes from viewpoint-induced differences - a distinction essential for correct update decisions. We propose SCD4VPR, a scene change detection that jointly reasons about what has changed and distinguishes genuine change from viewpoint-induced difference in a unified vision-language framework. SCD4VPR fuses VLM-generated semantic descriptions with visual features via cross-modal attention and refines predictions with geometric-semantic matching, producing multi-class change masks that separately identify object changes, appearance changes, and viewpoint-induced changes. We introduce NYC-CD, the first real-world street-view SCD benchmark with pixel-level multi-class annotations across 8,122 image pairs. Experiments across four SCD benchmarks show that SCD4VPR consistently improves three architecturally distinct backbones. In a controlled VPR database maintenance experiment on NYU-VPR spanning summer through late winter, we confirm that retrieval performance deteriorates substantially when the database is left unchanged, and show that SCD4VPR-guided updates recover most of this loss (+30.1 R@1 at the largest time gap) while keeping the database far more compact than naive append.

---

### GS4City: Hierarchical Semantic Gaussian Splatting via City-Model Priors

Authors: Qilin Zhang, Jinyu Zhu, Olaf Wysocki, Benjamin Busam, Boris Jutzi
Published: 2026-04-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.11401v1

Recent semantic 3D Gaussian Splatting (3DGS) methods primarily rely on 2D foundation models, often yielding ambiguous boundaries and limited support for structured urban semantics. While city models such as CityGML encode hierarchically organized semantics together with building geometry, these labels cannot be directly mapped to Gaussian primitives. We present GS4City, a hierarchical semantic Gaussian Splatting method that incorporates city-model priors for urban scene understanding. GS4City derives reliable image-aligned masks from Level of Detail (LoD) 3 CityGML models via two-pass raycasting, explicitly using parent-child relations to validate and recover fine-grained facade elements. It then fuses these geometry-grounded masks with foundation-model predictions to establish scene-consistent instance correspondences, and learns a compact identity encoding for each Gaussian under joint 2D identity supervision and 3D spatial regularization. Experiments on the TUM2TWIN and Gold Coast datasets show that GS4City effectively incorporates structured building semantics into Gaussian scene representations, outperforming existing 2D-driven semantic 3DGS baselines, including LangSplat and Gaga, by up to 15.8 IoU points in coarse building segmentation and 14.2 mIoU points in fine-grained semantic segmentation. By bridging structured city models and photorealistic Gaussian scene representations, GS4City enables semantically queryable and structure-aware urban reconstruction. Code is available at https://github.com/Jinyzzz/GS4City.

---

### EagleVision: A Multi-Task Benchmark for Cross-Domain Perception in High-Speed Autonomous Racing

Authors: Zakhar Yagudin, Murad Mebrahtu, Ren Jin, Jiaqi Huang, Yujia Yue, Dzmitry Tsetserukou, Jorge Dias, Majid Khonji
Published: 2026-04-13
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2604.11400v1

High-speed autonomous racing presents extreme perception challenges, including large relative velocities and substantial domain shifts from conventional urban-driving datasets. Existing benchmarks do not adequately capture these high-dynamic conditions. We introduce EagleVision, a unified LiDAR-based multi-task benchmark for 3D detection and trajectory prediction in high-speed racing, providing newly annotated 3D bounding boxes for the Indy Autonomous Challenge dataset (14,893 frames) and the A2RL Real competition dataset (1,163 frames), together with 12,000 simulator-generated annotated frames, all standardized under a common evaluation protocol. Using a dataset-centric transfer framework, we quantify cross-domain generalization across urban, simulator, and real racing domains. Urban pretraining improves detection over scratch training (NDS 0.72 vs. 0.69), while intermediate pretraining on real racing data achieves the best transfer to A2RL (NDS 0.726), outperforming simulator-only adaptation. For trajectory prediction, Indy-trained models surpass in-domain A2RL training on A2RL test sequences (FDE 0.947 vs. 1.250), highlighting the role of motion-distribution coverage in cross-domain forecasting. EagleVision enables systematic study of perception generalization under extreme high-speed dynamics. The dataset and benchmark are publicly available at https://avlab.io/EagleVision

---

### Lost in Adaptation: Layer-Selective Recovery of Temporal Reasoning in Video-Language Models

Authors: Zihang Fu, Haonan Wang, Jian Kang, Kenji Kawaguchi, Jiaying Wu
Published: 2026-04-13
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2604.11399v2

Multimodal adaptation can erode temporal reasoning (TR) in video-language models (VLMs), leaving models able to perceive salient events yet unable to infer their temporal and causal structure. We introduce MERIT, a gradient-free framework that repairs this capability through layer-selective model merging. MERIT assigns each self-attention layer a VLM-dominant or LLM-dominant interpolation and uses the Covariance Matrix Adaptation Evolution Strategy (CMA-ES) to search the resulting combinatorial space under an objective that rewards TR gains while penalizing temporal perception (TP) degradation. Across three VLM families and five video benchmarks, MERIT consistently improves TR while preserving TP; recipes selected on a compact diagnostic set transfer to four unseen benchmarks, with relative gains of up to 27.8%. Interventional masking and frame-level attribution further show that the selected layers are functionally important for reasoning and that MERIT shifts decisions toward temporally distributed, causally relevant evidence. These results establish layer-selective merging as a practical post-hoc mechanism for repairing video temporal reasoning degraded during multimodal adaptation, without learning new parameters.

---

### Reasoning Resides in Layers: Restoring Temporal Reasoning in Video-Language Models with Layer-Selective Merging

Authors: Zihang Fu, Haonan Wang, Jian Kang, Kenji Kawaguchi, Jiaying Wu
Published: 2026-04-13
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2604.11399v1

Multimodal adaptation equips large language models (LLMs) with perceptual capabilities, but often weakens the reasoning ability inherited from language-only pretraining. This trade-off is especially pronounced in video-language models (VLMs), where visual alignment can impair temporal reasoning (TR) over sequential events. We propose MERIT, a training-free, task-driven model merging framework for restoring TR in VLMs. MERIT searches over layer-wise self-attention merging recipes between a VLM and its paired text-only backbone using an objective that improves TR while penalizing degradation in temporal perception (TP). Across three representative VLMs and multiple challenging video benchmarks, MERIT consistently improves TR, preserves or improves TP, and generalizes beyond the search set to four distinct benchmarks. It also outperforms uniform full-model merging and random layer selection, showing that effective recovery depends on selecting the right layers. Interventional masking and frame-level attribution further show that the selected layers are disproportionately important for reasoning and shift model decisions toward temporally and causally relevant evidence. These results show that targeted, perception-aware model merging can effectively restore TR in VLMs without retraining.

---

### Video-based Heart Rate Estimation with Angle-guided ROI Optimization and Graph Signal Denoising

Authors: Gan Pei, Junhao Ning, Boqiu Shen, Yan Zhu, Menghan Hu
Published: 2026-04-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.11395v1

Remote photoplethysmography (rPPG) enables non-contact heart rate measurement from facial videos, but its performance is significantly degraded by facial motions such as speaking and head shaking. To address this issue, we propose two plug-and-play modules. The Angle-guided ROI Adaptive Optimization module quantifies ROI-Camera angles to refine motion-affected signals and capture global motion, while the Multi-region Joint Graph Signal Denoising module jointly models intra- and inter-regional ROI signals using graph signal processing to suppress motion artifacts. The modules are compatible with reflection model-based rPPG methods and validated on three public datasets. Results show that jointly use markedly reduces MAE, with an average decrease of 20.38\% over the baseline, while ablation studies confirm the effectiveness of each module. The work demonstrates the potential of angle-guided optimization and graph-based denoising to enhance rPPG performance in motion scenarios.

---

### Beyond Reconstruction: Reconstruction-to-Vector Diffusion for Hyperspectral Anomaly Detection

Authors: Jijun Xiang, Tao Wang, Jiayi Wang, Pengxiang Wang, Cheng Chen, Nian Wang
Published: 2026-04-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.11390v2

While Hyperspectral Anomaly Detection (HAD) excels at identifying sparse targets in complex scenes, existing models remain trapped in a scalar "reconstruction-as-endpoint" paradigm. This reliance on ambiguous scalar residuals consistently triggers sub-pixel anomaly vanishing during spatial downsampling, alongside severe confirmation bias when unpurified anomalies corrupt training weights. In this paper, we propose Reconstruction-to-Vector Diffusion (R2VD), which fundamentally redefines reconstruction as a manifold purification origin to establish a novel residual-guided generative dynamics paradigm. Our framework introduces a four-stage pipeline: (1) a Physical Prior Extraction (PPE) stage that mitigates early confirmation bias via dual-stream statistical guidance; (2) a Guided Manifold Purification (GMP) stage utilizing an OmniContext Autoencoder (OCA) to extract purified residual maps while preserving fragile sub-pixel topologies; (3) a Residual Score Modeling (RSM) stage where a Diffusion Transformer (DiT), guarded by a Physical Spectral Firewall (PSF), effectively isolates cross-spectral leakage; and (4) a Vector Dynamics Inference (VDI) stage that robustly decouples targets from backgrounds by evaluating high-dimensional vector interference patterns instead of conventional scalar errors. Comprehensive evaluations on eight datasets confirm that R2VD establishes a new state-of-the-art, delivering exceptional target detectability and background suppression. The code is available at https://github.com/Bondojijun/R2VD.

---

### ConvFormer3D-TAP: Phase/Uncertainty-Aware Front-End Fusion for Cine CMR View Classification Pipelines

Authors: Nafiseh Ghaffar Nia, Vinesh Appadurai, Suchithra V., Chinmay Rane, Daniel Pittman, James Carr, Adrienne Kline
Published: 2026-04-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.11389v1

Reliable recognition of standard cine cardiac MRI views is essential because each view determines which cardiac anatomy is visualized and which quantitative analyses can be performed. Incorrect view identification, whether by a human reader or an automated deep learning system, can propagate errors into segmentation, volumetric assessment, strain analysis, and valve evaluation. However, accurate view classification remains challenging under routine clinical variability in scanner vendor, acquisition protocol, motion artifacts, and plane prescription. We present ConvFormer3D-TAP, a cine-specific spatiotemporal architecture that integrates 3D convolutional tokenization with multiscale self-attention. The model is trained using masked spatiotemporal reconstruction and uncertainty-weighted multi-clip fusion to enhance robustness across cardiac phases and ambiguous temporal segments. The design captures complementary cues: local anatomical structure through convolutional priors and long-range cardiac-cycle dynamics through hierarchical attention. On a cohort of 150,974 clinically acquired cine sequences spanning six standard cine cardiac MRI views, ConvFormer3D-TAP achieved 96% validation accuracy with per-class F1-scores >= 0.94 and strong calibration (ECE = 0.025; Brier = 0.040). Error analysis shows that residual confusions are concentrated in anatomically adjacent long-axis and LVOT/AV view pairs, consistent with intrinsic prescription overlap. These results support ConvFormer3D-TAP as a scalable front-end for view routing, filtering and quality control in end-to-end cMRI workflows.

---

### ComSim: Building Scalable Real-World Robot Data Generation via Compositional Simulation

Authors: Yiran Qin, Jiahua Ma, Li Kang, Wenzhan Li, Yihang Jiao, Xin Wen, Xiufeng Song, Heng Zhou, Jiwen Yu, Zhenfei Yin, Xihui Liu, Philip Torr et al.
Published: 2026-04-13
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2604.11386v1

Recent advancements in foundational models, such as large language models and world models, have greatly enhanced the capabilities of robotics, enabling robots to autonomously perform complex tasks. However, acquiring large-scale, high-quality training data for robotics remains a challenge, as it often requires substantial manual effort and is limited in its coverage of diverse real-world environments. To address this, we propose a novel hybrid approach called Compositional Simulation, which combines classical simulation and neural simulation to generate accurate action-video pairs while maintaining real-world consistency. Our approach utilizes a closed-loop real-sim-real data augmentation pipeline, leveraging a small amount of real-world data to generate diverse, large-scale training datasets that cover a broader spectrum of real-world scenarios. We train a neural simulator to transform classical simulation videos into real-world representations, improving the accuracy of policy models trained in real-world environments. Through extensive experiments, we demonstrate that our method significantly reduces the sim2real domain gap, resulting in higher success rates in real-world policy model training. Our approach offers a scalable solution for generating robust training data and bridging the gap between simulated and real-world robotics.

---

### From Agent Loops to Structured Graphs:A Scheduler-Theoretic Framework for LLM Agent Execution

Authors: Hu Wei
Published: 2026-04-13
Categories: cs.AI, eess.SY
arXiv: https://arxiv.org/abs/2604.11378v1

The dominant paradigm for building LLM based agents is the Agent Loop, an iterative cycle where a single language model decides what to do next by reading an ever growing context window. This paradigm has three structural weaknesses: implicit dependencies between steps, unbounded recovery loops, and mutable execution history that complicates debugging. We characterize the Agent Loop as a single ready unit scheduler: at any moment, at most one executable unit is active, and the choice of which unit to activate comes from opaque LLM inference rather than an inspectable policy. This perspective places Agent Loops and graph based execution engines on a single semantic continuum. We propose SGH, Structured Graph Harness, which lifts control flow from implicit context into an explicit static DAG. SGH makes three commitments: execution plans are immutable within a plan version, planning execution and recovery are separated into three layers, and recovery follows a strict escalation protocol. These choices trade some expressiveness for controllability, verifiability, and implementability. Our contributions are fourfold: a scheduler unified framework that applies classical scheduling theory to LLM agent execution and identifies challenges introduced by non deterministic LLM nodes; a trade off analysis of controllability, expressiveness, and implementability across 70 surveyed systems; a formal specification including a node state machine with termination and soundness guarantees; and an attributable experimental framework with a seven group design for future validation. This is a position paper and design proposal. We provide a theoretical framework, design analysis, and experimental protocol, not a production implementation or empirical results.

---

### From Redaction to Restoration: Deep Learning for Medical Image Anonymization and Reconstruction

Authors: Adrienne Kline, Abhijit Gaonkar, Daniel Pittman, Chris Kuehn, Nils Forkert
Published: 2026-04-13
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2604.11376v1

Removing patient-specific information from medical images is crucial to enable sharing and open science without compromising patient identities. However, many methods currently used for deidentification have negative effects on downstream image analysis tasks because of removal of relevant but non-identifiable information. This work presents an end-to-end deep learning framework for transforming raw clinical image volumes into de-identified, analysis-ready datasets without compromising downstream utility. The methodology developed and tested in this work first detects and redacts regions likely to contain protected health information (PHI), such as burned-in text and metadata, and then uses a generative deep learning model to inpaint the redacted areas with anatomically and imaging plausible content. The proposed pipeline leverages a lightweight hybrid architecture, combining CRNN-based redaction with a latent-diffusion inpainting restoration module (Stable Diffusion 2). We evaluate the approach using both privacy-oriented metrics, which quantify residual PHI and success of redaction, and image-quality and task-based metrics, which assess the fidelity of restored volumes for representative deep learning applications. Our results suggest that the proposed method yields de-identified medical images that are visually coherent, maintaining fidelity for downstream models, while substantially reducing the risk of patient re-identification. By automating anonymization and image reconstruction within a single workflow, and dissemination of large-scale medical imaging collections, thereby lowering a key barrier to data sharing and multi-institutional collaboration in medical imaging AI.

---

### What Do Vision-Language Models Encode for Personalized Image Aesthetics Assessment?

Authors: Koki Ryu, Hitomi Yanaka
Published: 2026-04-13
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2604.11374v1

Personalized image aesthetics assessment (PIAA) is an important research problem with practical real-world applications. While methods based on vision-language models (VLMs) are promising candidates for PIAA, it remains unclear whether they internally encode rich, multi-level aesthetic attributes required for effective personalization. In this paper, we first analyze the internal representations of VLMs to examine the presence and distribution of such aesthetic attributes, and then leverage them for lightweight, individual-level personalization without model fine-tuning. Our analysis reveals that VLMs encode diverse aesthetic attributes that propagate into the language decoder layers. Building on these representations, we demonstrate that simple linear models can perform PIAA effectively. We further analyze how aesthetic information is transferred across layers in different VLM architectures and across image domains. Our findings provide insights into how VLMs can be utilized for modeling subjective, individual aesthetic preferences. Our code is available at https://github.com/ynklab/vlm-latent-piaa.

---

### Minimal Embodiment Enables Efficient Learning of Number Concepts in Robot

Authors: Zhegong Shangguan, Alessandro Di Nuovo, Angelo Cangelosi
Published: 2026-04-13
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2604.11373v1

Robots are increasingly entering human-interactive scenarios that require understanding of quantity. How intelligent systems acquire abstract numerical concepts from sensorimotor experience remains a fundamental challenge in cognitive science and artificial intelligence. Here we investigate embodied numerical learning using a neural network model trained to perform sequential counting through naturalistic robotic interaction with a Franka Panda manipulator. We demonstrate that embodied models achieve 96.8\% counting accuracy with only 10\% of training data, compared to 60.6\% for vision-only baselines. This advantage persists when visual-motor correspondences are randomized, indicating that embodiment functions as a structural prior that regularizes learning rather than as an information source. The model spontaneously develops biologically plausible representations: number-selective units with logarithmic tuning, mental number line organization, Weber-law scaling, and rotational dynamics encoding numerical magnitude ($r = 0.97$, slope $= 30.6°$/count). The learning trajectory parallels children's developmental progression from subset-knowers to cardinal-principle knowers. These findings demonstrate that minimal embodiment can ground abstract concepts, improve data efficiency, and yield interpretable representations aligned with biological cognition, which may contribute to embodied mathematics tutoring and safety-critical industrial applications.

---

### Learning from Contrasts: Synthesizing Reasoning Paths from Diverse Search Trajectories

Authors: Peiyang Liu, Zhirui Chen, Xi Wang, Di Liang, Youru Li, Zhi Cai, Wei Ye
Published: 2026-04-13
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2604.11365v1

Monte Carlo Tree Search (MCTS) has been widely used for automated reasoning data exploration, but current supervision extraction methods remain inefficient. Standard approaches retain only the single highest-reward trajectory, discarding the comparative signals present in the many explored paths. Here we introduce \textbf{Contrastive Reasoning Path Synthesis (CRPS)}, a framework that transforms supervision extraction from a filtering process into a synthesis procedure. CRPS uses a structured reflective process to analyze the differences between high- and low-quality search trajectories, extracting explicit information about strategic pivots and local failure modes. These insights guide the synthesis of reasoning chains that incorporate success patterns while avoiding identified pitfalls. We show empirically that models fine-tuned on just 60K CRPS-synthesized examples match or exceed the performance of baselines trained on 590K examples derived from standard rejection sampling, a 20$\times$ reduction in dataset size. Furthermore, CRPS improves generalization on out-of-domain benchmarks, demonstrating that learning from the contrast between success and failure produces more transferable reasoning capabilities than learning from success alone.

---

### The Missing Knowledge Layer in Cognitive Architectures for AI Agents

Authors: Michaël Roynard
Published: 2026-04-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.11364v2

The two most influential cognitive architecture frameworks for AI agents, CoALA (21) and JEPA (12), both lack an explicit Knowledge layer with its own persistence semantics. This gap produces a category error: systems apply cognitive decay to factual claims, or treat facts and experiences with identical update mechanics. We survey persistence semantics across existing memory systems and identify eight convergence points, from Karpathy's LLM Knowledge Base (10) to the BEAM benchmark's near-zero contradiction-resolution scores (22), all pointing to related architectural gaps. We propose a four-layer decom position (Knowledge, Memory, Wisdom, Intelligence) where each layer has fundamentally different persistence semantics: indefinite supersession, Ebbinghaus decay, evidence-gated revision, and ephemeral inference respectively. Companion implementations in Python and Rust demonstrate the architectural separation is feasible. We borrow terminology from cognitive science as a useful analogy (the Knowledge/Memory distinction echoes Tulving's trichotomy), but our layers are engineering constructs justified by persistence-semantics requirements, not by neural architecture. We argue that these distinctions demand distinct persistence semantics in engineering implementations, and that no current framework or system provides this.

---

### CoRe-ECG: Advancing Self-Supervised Representation Learning for 12-Lead ECG via Contrastive and Reconstructive Synergy

Authors: Zehao Qin, Xiaojian Lin, Ping Zhang, Hongliang Wu, Xinkang Wang, Guangling Liu, Bo Chen, Wenming Yang, Guijin Wang
Published: 2026-04-13
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2604.11359v1

Accurate interpretation of electrocardiogram (ECG) remains challenging due to the scarcity of labeled data and the high cost of expert annotation. Self-supervised learning (SSL) offers a promising solution by enabling models to learn expressive representations from unlabeled signals. Existing ECG SSL methods typically rely on either contrastive learning or reconstructive learning. However, each approach in isolation provides limited supervisory signals and suffers from additional limitations, including non-physiological distortions introduced by naive augmentations and trivial correlations across multiple leads that models may exploit as shortcuts. In this work, we propose CoRe-ECG, a unified contrastive and reconstructive pretraining paradigm that establishes a synergistic interaction between global semantic modeling and local structural learning. CoRe-ECG aligns global representations during reconstruction, enabling instance-level discriminative signals to guide local waveform recovery. To further enhance pretraining, we introduce Frequency Dynamic Augmentation (FDA) to adaptively perturb ECG signals based on their frequency-domain importance, and Spatio-Temporal Dual Masking (STDM) to break linear dependencies across leads, increasing the difficulty of reconstructive tasks. Our method achieves state-of-the-art performance across multiple downstream ECG datasets. Ablation studies further demonstrate the necessity and complementarity of each component. This approach provides a robust and physiologically meaningful representation learning framework for ECG analysis.

---