arXiv:2604.07530v1 Announce Type: cross Abstract: Scaling laws describe how language model capabilities grow with compute and data, but say nothing about how long a model matters once released. We provide the first large-scale empirical account of how scientists adopt and abandon language models over time. We track 62 LLMs across over 108k citing papers (2018-2025), […]
Learning is Forgetting: LLM Training As Lossy Compression
arXiv:2604.07569v1 Announce Type: cross Abstract: Despite the increasing prevalence of large language models (LLMs), we still have a limited understanding of how their representational spaces are structured. This limits our ability to interpret how and what they learn or relate them to learning in humans. We argue LLMs are best seen as an instance of […]
Sheaf-Laplacian Obstruction and Projection Hardness for Cross-Modal Compatibility on a Modality-Independent Site
arXiv:2604.07632v1 Announce Type: cross Abstract: We develop a unified framework for analyzing cross-modal compatibility in learned representations. The core object is a modality-independent neighborhood site on sample indices, equipped with a cellular sheaf of finite-dimensional real inner-product spaces. For a directed modality pair $(ato b)$, we formalize two complementary incompatibility mechanisms: projection hardness, the minimal […]
AITH: A Post-Quantum Continuous Delegation Protocol for Human-AI Trust Establishment
arXiv:2604.07695v1 Announce Type: cross Abstract: The rapid deployment of AI agents acting autonomously on behalf of human principals has outpaced the development of cryptographic protocols for establishing, bounding, and revoking human-AI trust relationships. Existing frameworks (TLS, OAuth 2.0, Macaroons) assume deterministic software and cannot address probabilistic AI agents operating continuously within variable trust boundaries. We […]
Dual-Loop Control in DCVerse: Advancing Reliable Deployment of AI in Data Centers via Digital Twins
arXiv:2604.07559v1 Announce Type: new Abstract: The growing scale and complexity of modern data centers present major challenges in balancing energy efficiency with outage risk. Although Deep Reinforcement Learning (DRL) shows strong potential for intelligent control, its deployment in mission-critical systems is limited by data scarcity and the lack of real-time pre-evaluation mechanisms. This paper introduces […]
Toward Generalizable Graph Learning for 3D Engineering AI: Explainable Workflows for CAE Mode Shape Classification and CFD Field Prediction
arXiv:2604.07781v1 Announce Type: cross Abstract: Automotive engineering development increasingly relies on heterogeneous 3D data, including finite element (FE) models, body-in-white (BiW) representations, CAD geometry, and CFD meshes. At the same time, engineering teams face growing pressure to shorten development cycles, improve performance and accelerate innovation. Although artificial intelligence (AI) is increasingly explored in this domain, […]
LiloDriver: A Lifelong Learning Framework for Closed-loop Motion Planning in Long-tail Autonomous Driving Scenarios
arXiv:2505.17209v2 Announce Type: replace-cross Abstract: Recent advances in autonomous driving research towards motion planners that are robust, safe, and adaptive. However, existing rule-based and data-driven planners lack adaptability to long-tail scenarios, while knowledge-driven methods offer strong reasoning but face challenges in representation, control, and real-world evaluation. To address these challenges, we present LiloDriver, a lifelong […]
Loop, Think, & Generalize: Implicit Reasoning in Recurrent-Depth Transformers
arXiv:2604.07822v1 Announce Type: cross Abstract: We study implicit reasoning, i.e. the ability to combine knowledge or rules within a single forward pass. While transformer-based large language models store substantial factual knowledge and rules, they often fail to compose this knowledge for implicit multi-hop reasoning, suggesting a lack of compositional generalization over their parametric knowledge. To […]
Predicting Activity Cliffs for Autonomous Medicinal Chemistry
arXiv:2604.07560v1 Announce Type: new Abstract: Activity cliff prediction – identifying positions where small structural changes cause large potency shifts – has been a persistent challenge in computational medicinal chemistry. This work focuses on a parsimonious definition: which small modifications, at which positions, confer the highest probability of an outcome change. Position-level sensitivity is calculated using […]
PyVRP$^+$: LLM-Driven Metacognitive Heuristic Evolution for Hybrid Genetic Search in Vehicle Routing Problems
arXiv:2604.07872v1 Announce Type: cross Abstract: Designing high-performing metaheuristics for NP-hard combinatorial optimization problems, such as the Vehicle Routing Problem (VRP), remains a significant challenge, often requiring extensive domain expertise and manual tuning. Recent advances have demonstrated the potential of large language models (LLMs) to automate this process through evolutionary search. However, existing methods are largely […]
Machine Unlearning in the Era of Quantum Machine Learning: An Empirical Study
arXiv:2512.19253v4 Announce Type: replace-cross Abstract: We present the first empirical study of machine unlearning (MU) in hybrid quantum-classical neural networks. While MU has been extensively explored in classical deep learning, its behavior within variational quantum circuits (VQCs) and quantum-augmented architectures remains largely unexplored. First, we adapt a broad suite of unlearning methods to quantum settings, […]
Sinkhorn doubly stochastic attention rank decay analysis
arXiv:2604.07925v1 Announce Type: cross Abstract: The self-attention mechanism is central to the success of Transformer architectures. However, standard row-stochastic attention has been shown to suffer from significant signal degradation across layers. In particular, it can induce rank collapse, resulting in increasingly uniform token representations, as well as entropy collapse, characterized by highly concentrated attention distributions. […]