Stay updated with the latest research and technology news
arXiv:2602.11788v1 Announce Type: new Abstract: This paper establishes a novel upper bound-termed the arithmetic Singleton bound-on the Hamming distance of any simple-root constacyclic code over...
arXiv:2602.11786v1 Announce Type: new Abstract: Traditional benchmarks for large language models (LLMs) primarily assess safety risk through breadth-oriented evaluation across diverse tasks. However, real-world deployment...
arXiv:2602.11785v1 Announce Type: new Abstract: As automated classification systems become increasingly prevalent, concerns have emerged over their potential to reinforce and amplify existing societal biases....
arXiv:2602.11782v1 Announce Type: new Abstract: LLMs can solve complex tasks through reasoning and tool use, but accurately translating these solutions into structured workflows remains challenging....
arXiv:2602.11780v1 Announce Type: new Abstract: In online advertising, advertising text plays a critical role in attracting user engagement and driving advertiser value. Existing industrial systems...
arXiv:2602.11779v1 Announce Type: new Abstract: Temperature is a crucial hyperparameter in large language models (LLMs), controlling the trade-off between exploration and exploitation during text generation....
arXiv:2602.11776v1 Announce Type: new Abstract: In binary classification systems, decision thresholds translate model scores into actions. Choosing suitable thresholds relies on the specific distribution of...
arXiv:2602.11775v1 Announce Type: new Abstract: Explanations are essential for helping users interpret and trust autonomous smart-home decisions, yet evaluating their quality and impact remains methodologically...
arXiv:2602.11773v1 Announce Type: new Abstract: For a directed graph $G$, and a linear order $\ll$ on the vertices of $G$, we define backedge graph $G^\ll$...
arXiv:2602.11772v1 Announce Type: new Abstract: In this paper we study the inverse eigenvector centrality problem on directed graphs: given a prescribed node centrality profile, we...
arXiv:2602.11771v1 Announce Type: new Abstract: Species distribution models (SDMs) commonly produce probabilistic occurrence predictions that must be converted into binary presence-absence maps for ecological inference...
arXiv:2602.11769v1 Announce Type: new Abstract: Recent advances in diffusion-based generative models have established a new paradigm for image and video relighting. However, extending these capabilities...
arXiv:2602.11767v1 Announce Type: new Abstract: Advances in large language models (LLMs) are driving a shift toward using reinforcement learning (RL) to train agents from iterative,...
arXiv:2602.11764v1 Announce Type: new Abstract: Shared, dynamic network infrastructures, such as dual-use LEO satellite constellations, pose critical threats to metadata privacy, particularly for state actors...
arXiv:2602.11759v1 Announce Type: new Abstract: Traffic forecasting based network operation optimization and management offers enormous promise but also presents significant challenges from traffic forecasting perspective....
arXiv:2602.11758v1 Announce Type: new Abstract: Humanoid robots show promise for complex whole-body tasks in unstructured environments. Although Human-Object Interaction (HOI) has advanced, most methods focus...
arXiv:2602.11757v1 Announce Type: new Abstract: Achieving spatial intelligence requires moving beyond visual plausibility to build world simulators grounded in physical laws. While coding LLMs have...
arXiv:2602.11756v1 Announce Type: new Abstract: Data integration is the primary use case for knowledge graphs. However, integrated data are not typically graphs but come in...
arXiv:2602.11754v1 Announce Type: new Abstract: LLM-based multi-agent systems (LLM-MAS), in which autonomous AI agents cooperate to solve tasks, are gaining increasing attention. For such systems...
arXiv:2602.11753v1 Announce Type: new Abstract: Aligning AI systems with human values fundamentally relies on effective human feedback. While significant research has addressed training algorithms, the...
arXiv:2602.11750v1 Announce Type: new Abstract: Benchmarks are paramount for gauging progress in the domain of Mobile GUI Agents. In practical scenarios, users frequently fail to...
arXiv:2602.11749v1 Announce Type: new Abstract: Large Language Model (LLM) agents are increasingly deployed in practice across a wide range of autonomous applications. Yet current safety...
arXiv:2602.11748v1 Announce Type: new Abstract: Achieving effective test-time scaling requires models to engage in In-Context Exploration -- the intrinsic ability to generate, verify, and refine...
arXiv:2602.11746v1 Announce Type: new Abstract: When successful, Open Source Software (OSS) projects create enormous value, but most never reach a sustainable state. Recent work has...