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:2512.10685———ModelSharp———
arXiv:1706.05587———Modeldeeplabv3-mobilevit-xx-small———
arXiv:2506.03524———ModelSeed-Coder-8B-ReasoningModelSeed-Coder-8B-BaseModelSeed-Coder-8B-Instruct———
arXiv:2501.12326———ModelUI-TARS-72B-DPOModelUI-TARS-7B-SFTModelUI-TARS-2B-SFT+2———
arXiv:2509.06493———ModelBFS-Prover-V2-7B———
arXiv:2507.13618———ModelSeed-X-PPO-7B———
arXiv:2501.01320———ModelSeedVR-3BModelSeedVR-7B———
arXiv:2506.05301———ModelSeedVR-3BModelSeedVR-7BModelSeedVR2-7B+1———
arXiv:2505.14683———ModelBAGEL-7B-MoT———
arXiv:2601.15892———ModelStable-DiffCoder-8B-BaseModelStable-DiffCoder-8B-Instruct———
arXiv:2510.13999———Modelcerebras/GLM-4.6-REAP-218B-A32BModelcerebras/GLM-4.6-REAP-268B-A32BModelcerebras/GLM-4.7-REAP-268B-A32B+15———
arXiv:2302.07452———ModelDragon-DocChat-Query-EncoderModelDragon-DocChat-Context-Encoder———
arXiv:2404.07972———ModelUI-TARS 7B———
arXiv:2409.08264———ModelUI-TARS 7B———
arXiv:2401.13919———ModelUI-TARS 7B———
arXiv:2504.01382———ModelUI-TARS 7B———
arXiv:2405.14573———ModelUI-TARS 7B———
arXiv:2410.23218———ModelUI-TARS 7B———
arXiv:2504.07981———ModelUI-TARS 7B———
arXiv:2606.19348———ModelDeepSeek V4 Pro 0423ModelDeepSeek-V4-Flash-DSparkModelDeepSeek V4 Flash 0423+1———
arXiv:2504.00698———Modelc4ai-command-a-03-2025Modelc4ai-command-r7b-12-2024———
arXiv:2510.18234———ModelDeepSeek-OCR-2ModelDeepSeek-OCR———
arXiv:2412.19437———ModelDeepSeek V3 0324ModelDeepSeek V3———
arXiv:2501.12948———Modeldeepseek-r1-distill-qwen-14bModelDeepSeek-R1-Distill-Qwen-7BModelDeepSeek-R1-Distill-Qwen-1.5B+3———
arXiv:2601.20552———ModelDeepSeek-OCR-2———

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.