Stay updated with the latest research and technology news
arXiv:2602.11881v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) have proven effective for extracting monosemantic features from large language models (LLMs), yet these features are typically...
arXiv:2602.11882v1 Announce Type: new Abstract: Efficient spatial reasoning requires world models that remain reliable under tight precision budgets. We study whether low-bit planning behavior is...
arXiv:2602.11885v1 Announce Type: new Abstract: Diffusion-based policies show limited generalization in semantic manipulation, posing a key obstacle to the deployment of real-world robots. This limitation...
arXiv:2602.11886v1 Announce Type: new Abstract: Corporate financial reports are a valuable source of structured knowledge for Knowledge Graph construction, but the lack of annotated ground...
arXiv:2602.11887v1 Announce Type: new Abstract: Verifying that a compiled binary originates from its claimed source code is a fundamental security requirement, called source code provenance....
arXiv:2602.11890v1 Announce Type: new Abstract: Modeling vessel activity at sea is critical for a wide range of applications, including route planning, transportation logistics, maritime safety,...
arXiv:2602.11893v1 Announce Type: new Abstract: We introduce a universal diffusion-based downscaling framework that lifts deterministic low-resolution weather forecasts into probabilistic high-resolution predictions without any model-specific...
arXiv:2602.11896v1 Announce Type: new Abstract: The concept of metamerism originates from colorimetry, where it describes a sensation of visual similarity between two colored lights despite...
arXiv:2602.11897v1 Announce Type: new Abstract: Contemporary AI-driven cybersecurity systems are predominantly architected as model-centric detection and automation pipelines optimized for task-level performance metrics such as...
arXiv:2602.11898v1 Announce Type: new Abstract: Benchmarks underpin how progress in large language models (LLMs) is measured and trusted. Yet our analyses reveal that apparent convergence...
arXiv:2602.11899v1 Announce Type: new Abstract: This paper investigates gradient-based adaptive prediction and control for nonlinear stochastic dynamical systems under a weak convexity condition on the...
arXiv:2602.11901v1 Announce Type: new Abstract: In this letter, we develop a unified Cram\'{e}r-Rao bound (CRB) framework to characterize the fundamental performance limits of transmission activity...
arXiv:2602.11902v1 Announce Type: new Abstract: Direct Preference Optimization (DPO) has become the de facto standard for offline preference alignment of large language models, but its...
arXiv:2602.11904v1 Announce Type: new Abstract: Software languages evolve over time for reasons such as feature additions. When grammars evolve, textual instances that originally conformed to...
arXiv:2602.11907v1 Announce Type: new Abstract: Presheaves and nominal sets provide alternative abstract models of sets of syntactic objects with free and bound variables, such as...
arXiv:2602.11908v1 Announce Type: new Abstract: LLMs are widely used, yet they remain prone to factual errors that erode user trust and limit adoption in high-risk...
arXiv:2602.11909v1 Announce Type: new Abstract: The maturation of Large Audio Language Models (LALMs) has raised growing expectations for them to comprehend complex audio much like...
arXiv:2602.11910v1 Announce Type: new Abstract: Audio diffusion models can synthesize high-fidelity music from text, yet their internal mechanisms for representing high-level concepts remain poorly understood....
arXiv:2602.11911v1 Announce Type: new Abstract: Large language models (LLMs) have shown remarkable capabilities in automated code generation. While effective for mainstream languages, they may underperform...
arXiv:2602.11914v1 Announce Type: new Abstract: Shortlisting is a common and effective method for pre-selecting participants in competitive settings. To ensure fairness, a cut-off score is...
arXiv:2602.11917v1 Announce Type: new Abstract: Extracting signals through alpha factor mining is a fundamental challenge in quantitative finance. Existing automated methods primarily follow two paradigms:...
arXiv:2602.11918v1 Announce Type: new Abstract: LLMs have demonstrated significant potential in quantitative finance by processing vast unstructured data to emulate human-like analytical workflows. However, current...
arXiv:2602.11919v1 Announce Type: new Abstract: Most existing hand motion generation benchmarks for hand-object interaction (HOI) focus on static objects, leaving dynamic scenarios with moving targets...
arXiv:2602.11920v1 Announce Type: new Abstract: We introduce the problem of learning conditional averages in the PAC framework. The learner receives a sample labeled by an...