Skip to content
AI Atlas
Research

Papers

Publications linked to models, labs and benchmarks. Authors, venues and abstracts come from arXiv and publisher pages; model links come from model cards citing the paper.

1,245 papers

Papers
TitleAuthorsOrganizationPublishedIntroduces Models (and artifacts) whose model card or documentation cites this paper — inbound described_by relations.DatasetsBenchmarksCode
arXiv:2401.06066ModelDeepSeek-Coder-V2-Lite-Instruct
arXiv:2405.04434ModelDeepSeek-V2-Lite
arXiv:2304.01373Modelpythia-12bModelpythia-14m-dedupedModelpythia-2.8b+10
arXiv:2101.00027Modelstablelm-3b-4e1tModelpythia-12bModelpythia-14m-deduped+15
arXiv:2201.07311Modelpythia-12bModelpythia-14m-dedupedModelpythia-2.8b+11
arXiv:2104.09864Modelstablelm-3b-4e1tModelgpt-j-6bModelgpt-neox-20b
arXiv:2503.09543Modelpythia-160m-seed2Modelpythia-160m-seed1Modelpythia-160m-seed3
arXiv:2603.11510Modeltiny-aya-globalModeltiny-aya-base
arXiv:2408.14960Modelaya-expanse-32bModelaya-expanse-8b
arXiv:2407.02552Modelaya-expanse-32bModelaya-expanse-8b
arXiv:2406.18682Modelaya-expanse-32bModelaya-expanse-8b
arXiv:2410.10801Modelaya-expanse-32bModelaya-expanse-8b
arXiv:2412.04261Modelaya-vision-8bModelaya-expanse-32bModelaya-expanse-8b
arXiv:2405.15032Modelaya-23-8B
arXiv:1910.09700Modelalias-gpt2-small-x21ModelctrlModelflan-t5-base+1
arXiv:2402.07827Modelaya-101
arXiv:2306.09683Modelowlv2-base-patch16-ensemble
arXiv:2607.02770Modelgemma-4-12B-itModelgemma-4-E2B-itModelgemma-4-E4B-it+3
arXiv:2305.13035Modelsiglip-so400m-patch14-384
arXiv:2209.06794Modelsiglip-so400m-patch14-384Modelsiglip2-base-patch16-224Modelsiglip-base-patch16-224+1
arXiv:2502.02737Modelstack-edu-classifier-pythonModelSmolLM2-1.7B-InstructModelSmolLM2-360M-Instruct+4
arXiv:2504.05299ModelSmolVLM-InstructModelSmolVLM2-256M-Video-InstructModelSmolVLM-500M-Instruct+3
arXiv:1406.2661Modelelectra-base-discriminator
arXiv:2010.11929Modelvit-base-patch16-224-in21kModelvit-base-patch16-224
arXiv:2006.03677Modelvit-base-patch16-224-in21kModelvit-base-patch16-224

Author lists and categories are copied from the paper's own metadata (arXiv, publisher). Linked models, datasets, benchmarks and code come from stated relations only; a dash means no source stated one.