arXiv:2604.24040v2 Announce Type: replace-cross Abstract: Transformer-based table retrieval systems flatten structured tables into token sequences, making retrieval sensitive to the choice of serialization even when table semantics remain unchanged. We show that semantically equivalent serializations, such as $textttcsv$, $texttttsv$, $texttthtml$, $textttmarkdown$, and $textttddl$, can produce substantially different embeddings and retrieval results across multiple benchmarks and […]
Prefill-Time Intervention for Mitigating Hallucination in Large Vision-Language Models
arXiv:2604.25642v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have achieved remarkable progress in visual-textual understanding, yet their reliability is critically undermined by hallucinations, i.e., the generation of factually incorrect or inconsistent responses. While recent studies using steering vectors demonstrated promise in reducing hallucinations, a notable challenge remains: they inadvertently amplify the severity of residual […]
Learning Structure, Energy, and Dynamics: A Survey of Artificial Intelligence for Protein Dynamics
arXiv:2604.25244v1 Announce Type: new Abstract: Protein dynamics underlie many biological functions, yet remain difficult to characterize due to the high computational cost of molecular dynamics simulations and the scarcity of dynamic structural data. This survey reviews recent advances in artificial intelligence for protein dynamics from three perspectives: learning from structural ensembles and trajectories, learning from […]
Threat-Oriented Digital Twinning for Security Evaluation of Autonomous Platforms
arXiv:2604.25757v1 Announce Type: cross Abstract: Open, unclassified research on secure autonomy is constrained by limited access to operational platforms, contested communications infrastructure, and representative adversarial test conditions. This paper presents a threat-oriented digital twinning methodology for cybersecurity evaluation of learning-enabled autonomous platforms. The approach is instantiated as an open-source, modular twin of a representative autonomy […]
Rethinking Layer Redundancy in Large Language Models: Calibration Objectives and Search for Depth Pruning
arXiv:2604.24938v1 Announce Type: cross Abstract: Depth pruning improves the inference efficiency of large language models by removing Transformer blocks. Prior work has focused on importance criteria and search algorithms, often treating layer redundancy as an inherent structural property of pretrained networks. In contrast, we adopt a emphfunctional perspective, where redundancy is jointly influenced by the […]
AutoResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery
arXiv:2604.25256v1 Announce Type: new Abstract: Autonomous scientific research is significantly advanced thanks to the development of AI agents. One key step in this process is finding the right scientific literature, whether to explore existing knowledge for a research problem, or to acquire evidence for verifying assumptions and supporting claims. To assess AI agents’ capability in […]
Towards Agentic Investigation of Security Alerts
arXiv:2604.25846v1 Announce Type: cross Abstract: Security analysts are overwhelmed by the volume of alerts and the low context provided by many detection systems. Early-stage investigations typically require manual correlation across multiple log sources, a task that is usually time-consuming. In this paper, we present an experimental, agentic workflow that leverages large language models (LLMs) augmented […]
Plausible but Wrong: A case study on Agentic Failures in Astrophysical Workflows
arXiv:2604.25345v1 Announce Type: new Abstract: Agentic AI systems are increasingly being integrated into scientific workflows, yet their behavior under realistic conditions remains insufficiently understood. We evaluate CMBAgent across two workflow paradigms and eighteen astrophysical tasks. In the One-Shot setting, access to domain-specific context yields an approximately ~6x performance improvement (0.85 vs. ~0 without context), with […]
No Pedestrian Left Behind: Real-Time Detection and Tracking of Vulnerable Road Users for Adaptive Traffic Signal Control
arXiv:2604.25887v1 Announce Type: cross Abstract: Current pedestrian crossing signals operate on fixed timing without adjustment to pedestrian behavior, which can leave vulnerable road users (VRUs) such as the elderly, disabled, or distracted pedestrians stranded when the light changes. We introduce No Pedestrian Left Behind (NPLB), a real-time adaptive traffic signal system that monitors VRUs in […]
Multi-action Tangled Program Graphs for Multi-task Reinforcement Learning with Continuous Control
arXiv:2604.25369v1 Announce Type: new Abstract: Over the past few decades, machine learning has been widely used to learn complex tasks. Reinforcement Learning (RL), inspired by human behavior, is a great example, as it involves developing specific behaviours for specific tasks. To further challenge algorithms, Multi-Task RL (MTRL) environments have been introduced, requiring a single model […]
BayesL: a Logical Framework for the Verification of Bayesian Networks
arXiv:2506.23773v2 Announce Type: replace Abstract: Modern explainable AI still struggles with a fundamental gap: although Bayesian networks (BNs) provide transparent probabilistic structure, there is no unified way to formally express, query, and verify what these models imply. Analysts often rely on ad hoc queries, manual interventions, or informal reasoning to explore causal relations and hypothetical […]
PhyloSDF: Phylogenetically-Conditioned Neural Generation of 3D Skull Morphology via Residual Flow Matching
arXiv:2604.25371v1 Announce Type: new Abstract: Generating novel, biologically plausible three-dimensional morphological structures is a fundamental challenge in computational evolutionary biology, hampered by extreme data scarcity and the requirement that generated shapes respect phylogenetic relationships among species. In this work, we present PhyloSDF, a phylogenetically-conditioned neural generative model for 3D biological morphology that integrates two innovations: […]