{"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/skywork-r1v3-technical-report","title":"Skywork-R1V3 Technical Report","arxiv_id":"2507.06167","date":"2025-07-08","proceeding":null,"authors":["Wei Shen","Jiangbo Pei","Yi Peng","Xuchen Song","Yang Liu","Jian Peng","Haofeng Sun","Yunzhuo Hao","Peiyu Wang","Yahui Zhou"],"abstract":"We introduce Skywork-R1V3, an advanced, open-source vision-language model (VLM) that pioneers a new approach to visual reasoning. Its key innovation lies in effectively transferring reasoning skills from text-only Large Language Models (LLMs) to visual tasks. The strong performance of Skywork-R1V3 primarily stems from our elaborate post-training RL framework, which effectively activates and enhances the model's reasoning ability, without the need for additional continue pre-training. Through this framework, we further uncover the fundamental role of the connector module in achieving robust cross-modal alignment for multimodal reasoning models. In addition, we introduce a unique indicator of reasoning capability, the entropy of critical reasoning tokens, which has proven highly effective for checkpoint selection during RL training. Skywork-R1V3 achieves state-of-the-art results on MMMU, significantly improving from 64.3% to 76.0%. This performance matches entry-level human capabilities. Remarkably, our RL-powered post-training approach enables even the 38B parameter model to rival top closed-source VLMs. The implementation successfully transfers mathematical reasoning to other subject-related reasoning tasks. We also include an analysis of curriculum learning and reinforcement finetuning strategies, along with a broader discussion on multimodal reasoning. Skywork-R1V3 represents a significant leap in multimodal reasoning, showcasing RL as a powerful engine for advancing open-source VLM capabilities.","url_abs":"https://arxiv.org/abs/2507.06167v1","url_pdf":"https://arxiv.org/pdf/2507.06167v1.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":"skywork-r1v3-technical-report","repo_url":"https://github.com/SkyworkAI/Skywork-R1V","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"skywork-r1v3-technical-report","repo_url":"https://github.com/seephys/seephys-project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"mathematical-reasoning","task_name":"Mathematical Reasoning"},{"task_slug":"multimodal-reasoning","task_name":"Multimodal Reasoning"},{"task_slug":"visual-reasoning","task_name":"Visual Reasoning"},{"task_slug":"cross-modal-alignment","task_name":"cross-modal alignment"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2507.06167","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.06167"}},"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/SkyworkAI/Skywork-R1V","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/seephys/seephys-project","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":3,"unverified":9},"by_repo_kind":{"listed":{"samples":9,"ran":0,"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":12,"samples":[{"code_sha256_prefix":"0a19144295a700b0","entry":"call_gpt","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"0a19144295a700b0"}},{"code_sha256_prefix":"946612831b2fdd2e","entry":"create_test_prompt","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"946612831b2fdd2e"}},{"code_sha256_prefix":"f2e0d1d5712940ed","entry":"fast_extract_answer","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"f2e0d1d5712940ed"}},{"code_sha256_prefix":"df88cee14b28de2a","entry":"build_extract_prompt","repo":"seephys/seephys-project","repo_kind":"listed","path":"vlmeval/dataset/utils/seephys.py","file_url":"https://github.com/seephys/seephys-project/blob/HEAD/vlmeval/dataset/utils/seephys.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"df88cee14b28de2a"}},{"code_sha256_prefix":"c96f86fc774ee85d","entry":"chat_mt","repo":"seephys/seephys-project","repo_kind":"listed","path":"vlmeval/inference_mt.py","file_url":"https://github.com/seephys/seephys-project/blob/HEAD/vlmeval/inference_mt.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c96f86fc774ee85d"}},{"code_sha256_prefix":"949f0167dd9b6572","entry":"completed","repo":"seephys/seephys-project","repo_kind":"listed","path":"vlmeval/tools.py","file_url":"https://github.com/seephys/seephys-project/blob/HEAD/vlmeval/tools.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"949f0167dd9b6572"}},{"code_sha256_prefix":"006f9965fbe1db5c","entry":"extract_by_rule","repo":"seephys/seephys-project","repo_kind":"listed","path":"vlmeval/dataset/utils/seephys.py","file_url":"https://github.com/seephys/seephys-project/blob/HEAD/vlmeval/dataset/utils/seephys.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"006f9965fbe1db5c"}},{"code_sha256_prefix":"6517db7a566fb96d","entry":"get_gpu_num","repo":"seephys/seephys-project","repo_kind":"listed","path":"vlmeval/api/hf_chat_model.py","file_url":"https://github.com/seephys/seephys-project/blob/HEAD/vlmeval/api/hf_chat_model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6517db7a566fb96d"}},{"code_sha256_prefix":"a37f5e20fcdfc1ff","entry":"last_boxed_only_string","repo":"seephys/seephys-project","repo_kind":"listed","path":"vlmeval/api/bluelm_api.py","file_url":"https://github.com/seephys/seephys-project/blob/HEAD/vlmeval/api/bluelm_api.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a37f5e20fcdfc1ff"}},{"code_sha256_prefix":"82238737d11621e0","entry":"list_to_dict","repo":"seephys/seephys-project","repo_kind":"listed","path":"vlmeval/dataset/utils/seephys.py","file_url":"https://github.com/seephys/seephys-project/blob/HEAD/vlmeval/dataset/utils/seephys.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"82238737d11621e0"}},{"code_sha256_prefix":"e531d45668a6c715","entry":"remove_boxed","repo":"seephys/seephys-project","repo_kind":"listed","path":"vlmeval/api/bluelm_api.py","file_url":"https://github.com/seephys/seephys-project/blob/HEAD/vlmeval/api/bluelm_api.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e531d45668a6c715"}},{"code_sha256_prefix":"2b4a4657b9b1fc73","entry":"split_think","repo":"seephys/seephys-project","repo_kind":"listed","path":"vlmeval/api/bluelm_api.py","file_url":"https://github.com/seephys/seephys-project/blob/HEAD/vlmeval/api/bluelm_api.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2b4a4657b9b1fc73"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}