{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/qwen2-5-vl-technical-report","title":"Qwen2.5-VL Technical Report","arxiv_id":"2502.13923","date":"2025-02-19","proceeding":null,"authors":["Shuai Bai","Keqin Chen","Xuejing Liu","Jialin Wang","Wenbin Ge","Sibo Song","Kai Dang","Peng Wang","Shijie Wang","Jun Tang","Humen Zhong","Yuanzhi Zhu","Mingkun Yang","Zhaohai Li","Jianqiang Wan","Pengfei Wang","Wei Ding","Zheren Fu","Yiheng Xu","Jiabo Ye","Xi Zhang","Tianbao Xie","Zesen Cheng","Hang Zhang","Zhibo Yang","Haiyang Xu","Junyang Lin"],"abstract":"We introduce Qwen2.5-VL, the latest flagship model of Qwen vision-language series, which demonstrates significant advancements in both foundational capabilities and innovative functionalities. Qwen2.5-VL achieves a major leap forward in understanding and interacting with the world through enhanced visual recognition, precise object localization, robust document parsing, and long-video comprehension. A standout feature of Qwen2.5-VL is its ability to localize objects using bounding boxes or points accurately. It provides robust structured data extraction from invoices, forms, and tables, as well as detailed analysis of charts, diagrams, and layouts. To handle complex inputs, Qwen2.5-VL introduces dynamic resolution processing and absolute time encoding, enabling it to process images of varying sizes and videos of extended durations (up to hours) with second-level event localization. This allows the model to natively perceive spatial scales and temporal dynamics without relying on traditional normalization techniques. By training a native dynamic-resolution Vision Transformer (ViT) from scratch and incorporating Window Attention, we reduce computational overhead while maintaining native resolution. As a result, Qwen2.5-VL excels not only in static image and document understanding but also as an interactive visual agent capable of reasoning, tool usage, and task execution in real-world scenarios such as operating computers and mobile devices. Qwen2.5-VL is available in three sizes, addressing diverse use cases from edge AI to high-performance computing. The flagship Qwen2.5-VL-72B model matches state-of-the-art models like GPT-4o and Claude 3.5 Sonnet, particularly excelling in document and diagram understanding. Additionally, Qwen2.5-VL maintains robust linguistic performance, preserving the core language competencies of the Qwen2.5 LLM.","url_abs":"https://arxiv.org/abs/2502.13923v1","url_pdf":"https://arxiv.org/pdf/2502.13923v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"qwen2-5-vl-technical-report","repo_url":"https://github.com/likaixin2000/screenspot-pro-gui-grounding","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"qwen2-5-vl-technical-report","repo_url":"https://github.com/princeton-nlp/CharXiv","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"qwen2-5-vl-technical-report","repo_url":"https://github.com/qwenlm/qwen2-vl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"qwen2-5-vl-technical-report","repo_url":"https://github.com/qwenlm/qwen2.5-vl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"object-localization","task_name":"Object Localization"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"},{"task_slug":"document-understanding","task_name":"document understanding"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/on-implicitqa","task":"","dataset":"ImplicitQA","model":"Qwen 2.5 VL - 7B","rank_in_archive_order":5,"of":7,"metrics":{"Average Accuracy":"42.8","Macro Average Accuracy":"46.1"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-vqa-on-vlm2-bench","task":"Visual Question Answering (VQA)","dataset":"VLM2-Bench","model":"Qwen2.5-VL-7B","rank_in_archive_order":2,"of":9,"metrics":{"Average Score on VLM2-bench (9 subtasks)":"54.82","GC-mat":"35.91","GC-trk":"43.38","OC-cnt":"41.72","OC-cpr":"71.39","OC-grp":"47.50","PC-VID":"46.50","PC-cnt":"57.98","PC-cpr":"80.00","PC-grp":"69.00"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2502.13923","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.13923"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/qwenlm/qwen2.5-vl","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/princeton-nlp/CharXiv","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/qwenlm/qwen2-vl","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/likaixin2000/screenspot-pro-gui-grounding","reach":null}],"summary":{"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"listed":{"samples":3,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"b6dbf724b472263e","entry":"convert_pil_image_to_base64","repo":"likaixin2000/screenspot-pro-gui-grounding","repo_kind":"listed","path":"models/qwen2_5vl.py","file_url":"https://github.com/likaixin2000/screenspot-pro-gui-grounding/blob/HEAD/models/qwen2_5vl.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b6dbf724b472263e"}},{"code_sha256_prefix":"0f935c4e4dc6c35d","entry":"get_qwen2_5vl_prompt_msg","repo":"likaixin2000/screenspot-pro-gui-grounding","repo_kind":"listed","path":"models/qwen2_5vl.py","file_url":"https://github.com/likaixin2000/screenspot-pro-gui-grounding/blob/HEAD/models/qwen2_5vl.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0f935c4e4dc6c35d"}},{"code_sha256_prefix":"1fd60ce7e7469b1d","entry":"Qwen2_5VLModel","repo":"likaixin2000/screenspot-pro-gui-grounding","repo_kind":"listed","path":"models/qwen2_5vl.py","file_url":"https://github.com/likaixin2000/screenspot-pro-gui-grounding/blob/HEAD/models/qwen2_5vl.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1fd60ce7e7469b1d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}