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quantitative finance, statistics, electrical engineering and systems science, and economics Materials on this site are not peer-reviewed by arXiv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
Computer Science - arXiv. org Computer Science (since January 1993) For a specific paper, enter the identifier into the top right search box Browse: new (most recent mailing, with abstracts) recent (last 5 mailings) current month's listings
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
Submission Overview - arXiv info Home Policies Submission Guidelines While submission to arXiv is free for authors, we do ask authors to carefully prepare their work according to these guidelines This will improve discoverability of the work and reduce the likelihood of delays before announcement Submissions to arXiv should be topical and refereeable scientific contributions that follow accepted standards of scholarly
Artificial Intelligence - arXiv. org Artificial Intelligence Authors and titles for recent submissions Wed, 3 Jun 2026 Tue, 2 Jun 2026 Mon, 1 Jun 2026 Fri, 29 May 2026 Thu, 28 May 2026 See today's new changes
High Energy Physics - Theory - arXiv. org High Energy Physics - Theory New submissions Cross-lists Replacements See recent articles Showing new listings for Tuesday, 26 May 2026
Algebraic Geometry - arXiv. org Towards the Relative Langlands Duality for Orthosymplectic Pairs Dor Mezer Subjects: Representation Theory (math RT); Algebraic Geometry (math AG) [13] arXiv:2606 03048 (cross-list from math OC) [pdf, html, other]
LLaMA: Open and Efficient Foundation Language Models We introduce LLaMA, a collection of foundation language models ranging from 7B to 65B parameters We train our models on trillions of tokens, and show that it is possible to train state-of-the-art models using publicly available datasets exclusively, without resorting to proprietary and inaccessible datasets In particular, LLaMA-13B outperforms GPT-3 (175B) on most benchmarks, and LLaMA-65B
[2501. 12948] DeepSeek-R1: Incentivizing Reasoning Capability in LLMs . . . General reasoning represents a long-standing and formidable challenge in artificial intelligence Recent breakthroughs, exemplified by large language models (LLMs) and chain-of-thought prompting, have achieved considerable success on foundational reasoning tasks However, this success is heavily contingent upon extensive human-annotated demonstrations, and models' capabilities are still