Found 42,749 document(s)
Page 45 of 2850
-
Monitoring the chain-of-thought (CoT) of language models (LMs) is a key strategy for detecting and preventing misbehaviors for AI safety. As such, it is critical to identify reinforcement learning (RL) practices that lea...
-
Unmanned aerial vehicle (UAV) platforms with integrated sensing and communication (ISAC) are prime candidates for surveillance missions, in which a dual-function drone tracks a mobile target and alerts a ground station w...
-
We present the Observation Assimilation Transformer (OAT), a geometry-aware neural process that corrects and refines a prior numerical weather prediction (NWP) field into a high-resolution posterior field by assimilating...
-
We study discrete-time consensus on the Euclidean unit sphere, where weighted combinations of neighboring states are normalized to unit length. For symmetric weights on connected undirected graphs and ambient dimension $...
-
Machine learning-based fault detectors are often evaluated at the relay locations used for training, although local voltage and current measurements vary across power networks. This work investigates cross-relay generali...
-
Satellite-based continuous-variable quantum key distribution (CV-QKD) is fundamentally constrained by finite communication windows, channel attenuation, and statistical fluctuations arising from a limited number of excha...
-
Beyond the Point Mass: Acceptance-Derived Weights and Distributional Losses for Speculative DecodingIn speculative decoding, a lightweight draft model proposes tokens that the target model verifies in parallel, speeding up generation without changing the target distribution. D-PACE (Wu et al., 2026) trains such drafter...
-
Homotopy type theory (HoTT) provides a natural setting for studying the metatheory of type theory, as it comes with additional extensionality principles compared to ordinary Martin-Löf type theory. In particular, it is e...
-
Agent harnesses are executable code that specifies the prompts, tools, and control flow around a language model. A single global harness can struggle with heterogeneous tasks that require different execution strategies. ...
-
Reasoning about safety is essential for embodied agents powered by large language models (LLMs). We introduce the Contextual Action and Plan Safety benchmark (CAPSafe), designed to evaluate safety reasoning at two levels...
-
LLM agents are commonly trained with RLVR, but the sparse nature of typical RLVR rewards makes credit assignment challenging, especially for long-horizon tasks. We propose Self-Credit, an end-to-end agentic RL method tha...
-
Agentic AI extends large language models (LLMs) from generating responses to planning and executing complex workflows, substantially expanding their utility while exposing applications to unsafe actions, information leak...
-
We present a decentralized multi-view tracking system for scalable camera networks. Single-view detections are projected to bird's-eye-view (BEV) coordinates and fused by independent multi-view trackers, each managing a ...
-
The increasing complexity of Industrial Control Systems (ICS) and their integration with IT infrastructures has significantly expanded the cyber threat landscape. Traditional cybersecurity models, primarily based on the ...
-
When training LLMs to code with reinforcement learning, reward hacking is often detectable but difficult to prevent, since (a) environment hardening is increasingly difficult as training environments grow more complex; a...