arXiv:2604.24942v1 Announce Type: cross Abstract: Encoding models provide a powerful framework for linking continuous stimulus features to neural activity; however, traditional voxelwise approaches are limited by measurement noise, inter-subject variability, and redundancy arising from spatially correlated voxels encoding overlapping neural signals. Here, we propose an independent component (IC)-based encoding framework that dissociates stimulus-driven and noise-driven […]
Internet of Everything in the 6G Era: Paradigms, Enablers, Potentials and Future Directions
arXiv:2604.25018v1 Announce Type: cross Abstract: The Internet of Everything (IoE) represents an evolution of the Internet of Things (IoT) by integrating people, data, processes, and things into a unified intelligent ecosystem. IoE aims to enhance automation, decision-making, and service efficiency across multiple application domains such as smart cities, healthcare, industry, and next-generation wireless networks. This […]
Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills
arXiv:2604.25109v1 Announce Type: cross Abstract: Agent Skills package SKILL.md files, scripts, reference documents, and repository context into reusable capability units, turning pre-load auditing from single-prompt filtering into cross-file security review. Existing guardrails often flag risk but recover malicious intent inconsistently under semantics-preserving rewrites. This paper formulates pre-load auditing for untrusted Agent Skills as a robust […]
Where Did It Go Wrong? Capability-Oriented Failure Attribution for Vision-and-Language Navigation Agents
arXiv:2604.25161v1 Announce Type: cross Abstract: Embodied agents in safety-critical applications such as Vision-Language Navigation (VLN) rely on multiple interdependent capabilities (e.g., perception, memory, planning, decision), making failures difficult to localize and attribute. Existing testing methods are largely system-level and provide limited insight into which capability deficiencies cause task failures. We propose a capability-oriented testing approach […]
DRAGON: A Benchmark for Evidence-Grounded Visual Reasoning over Diagrams
arXiv:2604.25231v1 Announce Type: cross Abstract: Diagram question answering (DQA) requires models to interpret structured visual representations such as charts, maps, infographics, circuit schematics, and scientific diagrams. Recent vision-language models (VLMs) often achieve high answer accuracy on these tasks, yet correct answers do not guarantee that models ground their reasoning in the diagram regions that support […]
GPT-Image-2 in the Wild: A Twitter Dataset of Self-Reported AI-Generated Images from the First Week of Deployment
arXiv:2604.25370v1 Announce Type: cross Abstract: The release of GPT-image-2 by OpenAI marks a watershed moment in AI-generated imagery: the boundary between photographic reality and synthetic content has never been more difficult to discern. We introduce the GPT-Image-2 Twitter Dataset, the first published dataset of GPT-image-2 generated images, sourced from publicly available Twitter/X posts in the […]
Generative UI as an Accessibility Bridge: Lessons from C2C E-Commerce
arXiv:2604.25455v1 Announce Type: cross Abstract: Web accessibility rests on static standards and developer compliance. That model frays in platforms where content is user-generated: photos arrive blurry or off-frame, descriptions skip size and condition, and page structure shifts from listing to listing. Drawing on six studies conducted between 2022 and 2025 with blind, low-vision, and older […]
MultiHedge: Adaptive Coordination via Retrieval-Augmented Control
arXiv:2604.24905v1 Announce Type: cross Abstract: Decision-making under changing conditions remains a fundamental challenge in many real-world systems. Existing approaches often fail to generalize across shifting regimes and exhibit unstable behavior under uncertainty. This raises the research question: can retrieval-augmented LLM coordination improve the robustness of modular decision pipelines? We propose MultiHedge, a hybrid architecture where […]
Dual-Track CoT: Budget-Aware Stepwise Guidance for Small LMs
arXiv:2604.25039v1 Announce Type: cross Abstract: Large Language Models (LLMs) solve many reasoning tasks via chain-of-thought (CoT) prompting, but smaller models (about 7 to 8B parameters) still struggle with multi-step reasoning under tight compute and token budgets. Existing test time reasoning methods such as self consistency (sampling multiple rationales and voting), Tree-of-Thoughts (search over intermediate thoughts), […]
Scalable Secure Biometric Authentication without Auxiliary Identifiers
arXiv:2604.25071v1 Announce Type: cross Abstract: The prevalence of biometric authentication has been on the rise due to its ease of use and elimination of weak passwords. To date, most biometric authentication systems have been designed for on-device authentication of the device owner (e.g., smartphones and laptops). Recently, biometric authentication systems have started to emerge that […]
M$^3$-VQA: A Benchmark for Multimodal, Multi-Entity, Multi-Hop Visual Question Answering
arXiv:2604.25122v1 Announce Type: cross Abstract: We present M$^3$-VQA, a novel knowledge-based Visual Question Answering (VQA) benchmark, to enhance the evaluation of multimodal large language models (MLLMs) in fine-grained multimodal entity understanding and complex multi-hop reasoning. Unlike existing VQA datasets that focus on coarse-grained categories and simple reasoning over single entities, M$^3$-VQA introduces diverse multi-entity questions […]
Gradient-Direction Sensitivity Reveals Linear-Centroid Coupling Hidden by Optimizer Trajectories
arXiv:2604.25143v1 Announce Type: cross Abstract: We show that replacing the rolling SVD of AdamW updates with a rolling SVD of loss gradients changes the diagnostic by 1-2 orders of magnitude. Performing SVD on the loss gradient instead of the AdamW update increases the measured perturbative coupling between SED directions and Linear Centroid Hypothesis (LCH) features […]