arXiv:2602.00159v2 Announce Type: replace-cross Abstract: The purpose of this paper is to elucidate the theory and mathematical modelling behind the sheaf neural network (SNN) algorithm and then show how SNN can effectively answer to biomedical questions in a concrete case study and outperform the most popular graph neural networks (GNNs) as graph convolutional networks (GCNs), […]
How Uncertainty Estimation Scales with Sampling in Reasoning Models
arXiv:2603.19118v1 Announce Type: new Abstract: Uncertainty estimation is critical for deploying reasoning language models, yet remains poorly understood under extended chain-of-thought reasoning. We study parallel sampling as a fully black-box approach using verbalized confidence and self-consistency. Across three reasoning models and 17 tasks spanning mathematics, STEM, and humanities, we characterize how these signals scale. Both […]
Towards Differentiating Between Failures and Domain Shifts in Industrial Data Streams
arXiv:2603.18032v1 Announce Type: cross Abstract: Anomaly and failure detection methods are crucial in identifying deviations from normal system operational conditions, which allows for actions to be taken in advance, usually preventing more serious damages. Long-lasting deviations indicate failures, while sudden, isolated changes in the data indicate anomalies. However, in many practical applications, changes in the […]
MCP-38: A Comprehensive Threat Taxonomy for Model Context Protocol Systems (v1.0)
arXiv:2603.18063v1 Announce Type: cross Abstract: The Model Context Protocol (MCP) introduces a structurally distinct attack surface that existing threat frameworks, designed for traditional software systems or generic LLM deployments, do not adequately cover. This paper presents MCP-38, a protocol-specific threat taxonomy consisting of 38 threat categories (MCP-01 through MCP-38). The taxonomy was derived through a […]
MineDraft: A Framework for Batch Parallel Speculative Decoding
arXiv:2603.18016v1 Announce Type: cross Abstract: Speculative decoding (SD) accelerates large language model inference by using a smaller draft model to propose draft tokens that are subsequently verified by a larger target model. However, the performance of standard SD is often limited by the strictly sequential execution of these drafting and verification stages. To address this, […]
Engineering Verifiable Modularity in Transformers via Per-Layer Supervision
arXiv:2603.18029v1 Announce Type: cross Abstract: Transformers resist surgical control. Ablating an attention head identified as critical for capitalization produces minimal behavioral change because distributed redundancy compensates for damage. This Hydra effect renders interpretability illusory: we may identify components through correlation, but cannot predict or control their causal role. We demonstrate that architectural interventions can expose […]
Do Vision Language Models Understand Human Engagement in Games?
arXiv:2603.18480v1 Announce Type: cross Abstract: Inferring human engagement from gameplay video is important for game design and player-experience research, yet it remains unclear whether vision–language models (VLMs) can infer such latent psychological states from visual cues alone. Using the GameVibe Few-Shot dataset across nine first-person shooter games, we evaluate three VLMs under six prompting strategies, […]
OS-Themis: A Scalable Critic Framework for Generalist GUI Rewards
arXiv:2603.19191v1 Announce Type: new Abstract: Reinforcement Learning (RL) has the potential to improve the robustness of GUI agents in stochastic environments, yet training is highly sensitive to the quality of the reward function. Existing reward approaches struggle to achieve both scalability and performance. To address this, we propose OS-Themis, a scalable and accurate multi-agent critic […]
Gradient-Informed Temporal Sampling Improves Rollout Accuracy in PDE Surrogate Training
arXiv:2603.18237v1 Announce Type: cross Abstract: Researchers train neural simulators on uniformly sampled numerical simulation data. But under the same budget, does systematically sampled data provide the most effective information? A fundamental yet unformalized problem is how to sample training data for neural simulators so as to maximize rollout accuracy. Existing data sampling methods either tend […]
To See or To Please: Uncovering Visual Sycophancy and Split Beliefs in VLMs
arXiv:2603.18373v1 Announce Type: cross Abstract: When VLMs answer correctly, do they genuinely rely on visual information or exploit language shortcuts? We introduce the Tri-Layer Diagnostic Framework, which disentangles hallucination sources via three metrics: Latent Anomaly Detection (perceptual awareness), Visual Necessity Score (visual dependency, measured via KL divergence), and Competition Score (conflict between visual grounding and […]
Benchmarking PDF Parsers on Table Extraction with LLM-based Semantic Evaluation
arXiv:2603.18652v1 Announce Type: cross Abstract: Reliably extracting tables from PDFs is essential for large-scale scientific data mining and knowledge base construction, yet existing evaluation approaches rely on rule-based metrics that fail to capture semantic equivalence of table content. We present a benchmarking framework based on synthetically generated PDFs with precise LaTeX ground truth, using tables […]
LICA: Layered Image Composition Annotations for Graphic Design Research
arXiv:2603.16098v2 Announce Type: replace-cross Abstract: We introduce LICA (Layered Image Composition Annotations), a large scale dataset of 1,550,244 multi-layer graphic design compositions designed to advance structured understanding and generation of graphic layouts. In addition to rendered PNG images, LICA represents each design as a hierarchical composition of typed components including text, image, vector, and group […]