arXiv. org e-Print archive arXiv is a free distribution service and an open-access archive for nearly 2 4 million scholarly articles in the fields of physics, mathematics, computer science, quantitative biology, quantitative finance, statistics, electrical engineering and systems science, and economics Materials on this site are not peer-reviewed by arXiv
Log in to arXiv | arXiv e-print repository If you've never logged in to arXiv org Register for the first time Registration is required to submit or update papers, but is not necessary to view them
About arXiv - arXiv info Read more arXiv offers researchers a broad range of services: article submission, compilation, production, retrieval, search and discovery, web distribution for human readers, and API access for machines, together with content curation and preservation
Artificial Intelligence - arXiv. org Artificial Intelligence Authors and titles for recent submissions Fri, 8 May 2026 Thu, 7 May 2026 Wed, 6 May 2026 Tue, 5 May 2026 Mon, 4 May 2026 See today's new changes
[2511. 21631] Qwen3-VL Technical Report - arXiv. org We introduce Qwen3-VL, the most capable vision-language model in the Qwen series to date, achieving superior performance across a broad range of multimodal benchmarks It natively supports interleaved contexts of up to 256K tokens, seamlessly integrating text, images, and video The model family includes both dense (2B 4B 8B 32B) and mixture-of-experts (30B-A3B 235B-A22B) variants to
[2603. 15031] Attention Residuals - arXiv. org Residual connections with PreNorm are standard in modern LLMs, yet they accumulate all layer outputs with fixed unit weights This uniform aggregation causes uncontrolled hidden-state growth with depth, progressively diluting each layer's contribution We propose Attention Residuals (AttnRes), which replaces this fixed accumulation with softmax attention over preceding layer outputs, allowing
Computer Science - arXiv. org Multi-depot vehicle routing problems (MDVRPs) are prevalent in a variety of practical applications However, they are computationally challenging to solve due to their inherent complexity This paper proposes an effective hybrid algorithm for a class of MDVRPs The algorithm integrates a learning-driven, diversity-controlled route-exchange crossover and a multi-depot-supported feasible-and
Machine Learning - arXiv. org Machine Learning Authors and titles for recent submissions Fri, 8 May 2026 Thu, 7 May 2026 Wed, 6 May 2026 Tue, 5 May 2026 Mon, 4 May 2026 See today's new changes
[2602. 15763] GLM-5: from Vibe Coding to Agentic Engineering - arXiv. org We present GLM-5, a next-generation foundation model designed to transition the paradigm of vibe coding to agentic engineering Building upon the agentic, reasoning, and coding (ARC) capabilities of its predecessor, GLM-5 adopts DSA to significantly reduce training and inference costs while maintaining long-context fidelity To advance model alignment and autonomy, we implement a new
Mathematics - arXiv. org In this paper, we expand the theory of depth-unbiased source localization to unbiased parameter estimation and signal reconstruction of an arbitrary number of non-zero parameters to be recovered The topic touches on the concept of exact reconstructibility, most commonly known in compressed sensing and multisource estimation in various imaging problems The theoretical results derive upper