Stay updated with the latest research and technology news
arXiv:2602.00513v2 Announce Type: replace Abstract: Cyber threat intelligence (CTI) analysts routinely convert noisy, unstructured security artifacts into standardized, automation-ready representations. Although large language models (LLMs)...
arXiv:2602.01143v2 Announce Type: replace Abstract: This paper is concerned with the approximation of continuously differentiable functions with high-dimensional input by a composition of two functions:...
arXiv:2602.01501v3 Announce Type: replace Abstract: Reliable localization is crucial for navigation in forests, where GPS is often degraded and LiDAR measurements are repetitive, occluded, and...
arXiv:2602.01511v2 Announce Type: replace Abstract: Standard reward models typically predict scalar scores that fail to capture the multifaceted nature of response quality in non-verifiable domains,...
arXiv:2602.02095v2 Announce Type: replace Abstract: We review some recent advances in the field of element-based algebraic stabilization for continuous finite element discretizations of nonlinear hyperbolic...
arXiv:2602.02201v3 Announce Type: replace Abstract: Drug discovery motivates accurate molecular property prediction when labeled data are limited and candidate spaces are vast. This article presents...
arXiv:2602.02613v3 Announce Type: replace Abstract: The rapid emergence of autonomous large language model agents has given rise to persistent, large-scale agent ecosystems whose collective behavior...
arXiv:2602.03368v2 Announce Type: replace Abstract: While retrieval augmented generation (RAG) has been swiftly adopted in industrial applications based on large language models (LLMs), there is...
arXiv:2602.03507v2 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has markedly improved the performance of Large Language Models (LLMs) on tasks requiring multi-step...
arXiv:2602.03563v2 Announce Type: replace Abstract: Despite its success in self-supervised learning, contrastive learning is less studied in the supervised setting. In this work, we first...
arXiv:2602.03828v2 Announce Type: replace Abstract: High-quality scientific illustrations are crucial for effectively communicating complex scientific and technical concepts, yet their manual creation remains a well-recognized...
arXiv:2602.04003v2 Announce Type: replace Abstract: Most adversarial threats in artificial intelligence target the computational behavior of models rather than the humans who rely on them....
arXiv:2602.04509v2 Announce Type: replace Abstract: Fine-tuning Multimodal Large Language Models (MLLMs) on task-specific data is an effective way to improve performance on downstream applications. However,...
arXiv:2602.04809v2 Announce Type: replace Abstract: Recent years have seen an explosion of interest in autonomous cyber defence agents trained to defend computer networks using deep...
arXiv:2602.04852v2 Announce Type: replace Abstract: Linear attention offers a computationally efficient yet expressive alternative to softmax attention. However, recent empirical results indicate that the hidden...
arXiv:2602.05014v3 Announce Type: replace Abstract: With the rapid advancement of tool-use capabilities in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) is shifting from static, one-shot...
arXiv:2602.05148v2 Announce Type: replace Abstract: Parameter-Efficient Fine-Tuning (PEFT) has emerged as a practical paradigm for adapting large language models (LLMs) without updating all parameters. Most...
arXiv:2602.05447v2 Announce Type: replace Abstract: Large Language Model agents increasingly operate external systems through programmatic interfaces, yet practitioners lack empirical guidance on how to structure...
arXiv:2602.05548v2 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR), particularly GRPO, has become the standard for eliciting LLM reasoning. However, its efficiency in...
arXiv:2602.05578v2 Announce Type: replace Abstract: Open-vocabulary semantic segmentation (OVSS) extends traditional closed-set segmentation by enabling pixel-wise annotation for both seen and unseen categories using arbitrary...
arXiv:2602.05774v3 Announce Type: replace Abstract: This note investigates core properties of martingales, emphasizing the measure-theoretic formulation of conditional expectation, the martingale transform, and the upcrossing...
arXiv:2602.06511v2 Announce Type: replace Abstract: Large language model (LLM)-based multi-agent systems (MAS) show strong promise for complex reasoning, planning, and tool-augmented tasks, but designing effective...
arXiv:2602.06643v2 Announce Type: replace Abstract: Current approaches for humanoid whole-body manipulation, primarily relying on teleoperation or visual sim-to-real reinforcement learning, are hindered by hardware logistics...
arXiv:2602.07011v2 Announce Type: replace Abstract: As industrial manufacturing scales, automating fine-grained product image analysis has become critical for quality control. However, existing approaches are hindered...