arXiv:2506.07985v2 Announce Type: replace-cross Abstract: Interpreting individual neurons or directions in activation space is an important topic in mechanistic interpretability. Numerous automated interpretability methods have been proposed to generate such explanations, but it remains unclear how reliable these explanations are,…
arXiv:2512.03102v1 Announce Type: new Abstract: In emergency response and other high-stakes societal applications, early-stage state estimates critically shape downstream outcomes. Yet, these initial state estimates-often based on limited or biased information-can be severely misaligned with reality, constraining subsequent actions and…
arXiv:2512.03107v1 Announce Type: new Abstract: Large language models (LLMs) produce fluent but unsupported answers – hallucinations – limiting safe deployment in high-stakes domains. We propose ECLIPSE, a framework that treats hallucination as a mismatch between a model’s semantic entropy and…
arXiv:2512.03339v1 Announce Type: cross Abstract: Ejection fraction (EF) is a crucial metric for assessing cardiac function and diagnosing conditions such as heart failure. Traditionally, EF estimation requires manual tracing and domain expertise, making the process time-consuming and subject to interobserver…
arXiv:2512.03109v1 Announce Type: new Abstract: Agentic AI systems execute a sequence of actions, such as reasoning steps or tool calls, in response to a user prompt. To evaluate the success of their trajectories, researchers have developed verifiers, such as LLM…
arXiv:2512.03494v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly prevalent in the field of long-context modeling, however, their inference computational costs have become a critical bottleneck hindering the advancement of tasks such as agents and multimodal applications. This…
arXiv:2512.03112v1 Announce Type: new Abstract: Shapley values, a gold standard for feature attribution in Explainable AI, face two primary challenges. First, the canonical Shapley framework assumes that the worth function is additive, yet real-world payoff constructions–driven by non-Gaussian distributions, heavy…
arXiv:2512.03719v1 Announce Type: cross Abstract: Over-the-Air Federated Learning (AirFL) is an emerging paradigm that tightly integrates wireless signal processing and distributed machine learning to enable scalable AI at the network edge. By leveraging the superposition property of wireless signals, AirFL…
arXiv:2512.03114v1 Announce Type: new Abstract: The rapid growth of solar photovoltaic (PV) systems necessitates advanced methods for performance monitoring and anomaly detection to ensure optimal operation. In this study, we propose a novel approach leveraging Temporal Graph Neural Network (Temporal…
arXiv:2512.03817v1 Announce Type: cross Abstract: Egyptian hieroglyphs, the ancient Egyptian writing system, are composed entirely of drawings. Translating these glyphs into English poses various challenges, including the fact that a single glyph can have multiple meanings. Deep learning translation applications…
