{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/deepseek-vl2-mixture-of-experts-vision","title":"DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding","arxiv_id":"2412.10302","date":"2024-12-13","proceeding":null,"authors":["Zhiyu Wu","Xiaokang Chen","Zizheng Pan","Xingchao Liu","Wen Liu","Damai Dai","Huazuo Gao","Yiyang Ma","Chengyue Wu","Bingxuan Wang","Zhenda Xie","Yu Wu","Kai Hu","Jiawei Wang","Yaofeng Sun","Yukun Li","Yishi Piao","Kang Guan","Aixin Liu","Xin Xie","Yuxiang You","Kai Dong","Xingkai Yu","Haowei Zhang","Liang Zhao","Yisong Wang","Chong Ruan"],"abstract":"We present DeepSeek-VL2, an advanced series of large Mixture-of-Experts (MoE) Vision-Language Models that significantly improves upon its predecessor, DeepSeek-VL, through two key major upgrades. For the vision component, we incorporate a dynamic tiling vision encoding strategy designed for processing high-resolution images with different aspect ratios. For the language component, we leverage DeepSeekMoE models with the Multi-head Latent Attention mechanism, which compresses Key-Value cache into latent vectors, to enable efficient inference and high throughput. Trained on an improved vision-language dataset, DeepSeek-VL2 demonstrates superior capabilities across various tasks, including but not limited to visual question answering, optical character recognition, document/table/chart understanding, and visual grounding. Our model series is composed of three variants: DeepSeek-VL2-Tiny, DeepSeek-VL2-Small and DeepSeek-VL2, with 1.0B, 2.8B and 4.5B activated parameters respectively. DeepSeek-VL2 achieves competitive or state-of-the-art performance with similar or fewer activated parameters compared to existing open-source dense and MoE-based models. Codes and pre-trained models are publicly accessible at https://github.com/deepseek-ai/DeepSeek-VL2.","url_abs":"https://arxiv.org/abs/2412.10302v1","url_pdf":"https://arxiv.org/pdf/2412.10302v1.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":"deepseek-vl2-mixture-of-experts-vision","repo_url":"https://github.com/deepseek-ai/deepseek-vl2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"chart-understanding","task_name":"Chart Understanding"},{"task_slug":"mixture-of-experts","task_name":"Mixture-of-Experts"},{"task_slug":"optical-character-recognition","task_name":"Optical Character Recognition"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"referring-expression-comprehension","task_name":"Referring Expression Comprehension"},{"task_slug":"visual-grounding","task_name":"Visual Grounding"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2412.10302","atlas_url":"https://app.syntology.ai/?focus=2412.10302","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.10302"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2412.10302"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2412.10302"},"call":"get_harvested_code_for_paper(arxiv_id=\"2412.10302\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2412.10302"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2412.10302\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2412.10302"},"call":"get_concepts_for_paper(arxiv_id=\"2412.10302\")"}],"by_repo":[{"repo":"deepseek-ai/deepseek-vl2","kind":"official","samples":13,"ran":11,"instrument":3,"unverified":2}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2412.10302.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2412.10302.svg"},"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/deepseek-ai/deepseek-vl2","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":2,"ran":6,"ran_honours":2,"ran_fixture":1,"unverified":2},"n_samples":13,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":2,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":13,"ran":11,"n_ran_checked":8,"n_instrument":3,"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":3,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":3,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":10,"n_ran_without_level_date":1,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-24","last":"2026-09-25","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"96f3e857e91a8cb8","code_sha256_prefix":"96f3e857e91a8cb8","entry":"load_json","repo":"deepseek-ai/deepseek-vl2","repo_kind":"official","path":"deepseek_vl2/utils/io.py","file_url":"https://github.com/deepseek-ai/deepseek-vl2/blob/HEAD/deepseek_vl2/utils/io.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"filepath:str/0/str","fixture_out_type":"dict","code_page":"/code/load-json","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"96f3e857e91a8cb8"}},{"code_sha256":"ba86a364bce26e9b","code_sha256_prefix":"ba86a364bce26e9b","entry":"compact_text_chunks","repo":"deepseek-ai/deepseek-vl2","repo_kind":"official","path":"deepseek_vl2/serve/app_modules/overwrites.py","file_url":"https://github.com/deepseek-ai/deepseek-vl2/blob/HEAD/deepseek_vl2/serve/app_modules/overwrites.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"self:MockSelf/0/?, prompt:str/0/str, text_chunks:list/1/str","fixture_out_type":"list","level_recorded_at":"2026-09-25T15:42:09.353852+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"ba86a364bce26e9b"}},{"code_sha256":"b675d2f1fa15bd63","code_sha256_prefix":"b675d2f1fa15bd63","entry":"create_siglip_vit","repo":"deepseek-ai/deepseek-vl2","repo_kind":"official","path":"deepseek_vl2/models/siglip_vit.py","file_url":"https://github.com/deepseek-ai/deepseek-vl2/blob/HEAD/deepseek_vl2/models/siglip_vit.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"tensor:Tensor/2/float, mean:float/0/float, std:float/0/float, a:float/0/float, b:float/0/float","fixture_out_type":"VisionTransformer","level_recorded_at":"2026-09-25T15:42:09.353852+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"b675d2f1fa15bd63"}},{"code_sha256":"75628f3739d6fcd3","code_sha256_prefix":"75628f3739d6fcd3","entry":"format_output","repo":"deepseek-ai/deepseek-vl2","repo_kind":"official","path":"deepseek_vl2/serve/app_modules/utils.py","file_url":"https://github.com/deepseek-ai/deepseek-vl2/blob/HEAD/deepseek_vl2/serve/app_modules/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"history:list/1/list, text:str/0/str, x:str/0/str","fixture_out_type":"tuple","level_recorded_at":"2026-09-25T23:22:42.264232+00:00","code_page":"/code/format-output","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"75628f3739d6fcd3"}},{"code_sha256":"56ce205e9245c8c2","code_sha256_prefix":"56ce205e9245c8c2","entry":"load_pil_images","repo":"deepseek-ai/deepseek-vl2","repo_kind":"official","path":"deepseek_vl2/utils/io.py","file_url":"https://github.com/deepseek-ai/deepseek-vl2/blob/HEAD/deepseek_vl2/utils/io.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"list","level_recorded_at":"2026-09-25T23:22:42.264232+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"56ce205e9245c8c2"}},{"code_sha256":"d1fcc287229a99c6","code_sha256_prefix":"d1fcc287229a99c6","entry":"markdown_to_html_with_syntax_highlight","repo":"deepseek-ai/deepseek-vl2","repo_kind":"official","path":"deepseek_vl2/serve/app_modules/utils.py","file_url":"https://github.com/deepseek-ai/deepseek-vl2/blob/HEAD/deepseek_vl2/serve/app_modules/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"md_str:str/0/str","fixture_out_type":"str","level_recorded_at":"2026-09-25T15:42:09.353852+00:00","retrieve_with":{"tool":"get_code","code_sha256":"d1fcc287229a99c6"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"d1fcc287229a99c6"}},{"code_sha256":"6408ebfc6065bf19","code_sha256_prefix":"6408ebfc6065bf19","entry":"select_best_resolution","repo":"deepseek-ai/deepseek-vl2","repo_kind":"official","path":"deepseek_vl2/models/processing_deepseek_vl_v2.py","file_url":"https://github.com/deepseek-ai/deepseek-vl2/blob/HEAD/deepseek_vl2/models/processing_deepseek_vl_v2.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"image_size:tuple/1/int, candidate_resolutions:list/1/tuple","fixture_out_type":"tuple","level_recorded_at":"2026-09-25T23:53:12.863503+00:00","code_page":"/code/select-best-resolution","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"6408ebfc6065bf19"}},{"code_sha256":"f7fc8e891d83a3e1","code_sha256_prefix":"f7fc8e891d83a3e1","entry":"strip_stop_words","repo":"deepseek-ai/deepseek-vl2","repo_kind":"official","path":"deepseek_vl2/serve/app_modules/utils.py","file_url":"https://github.com/deepseek-ai/deepseek-vl2/blob/HEAD/deepseek_vl2/serve/app_modules/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"x:str/0/str, stop_words:list/1/str","fixture_out_type":"str","level_recorded_at":"2026-09-25T23:53:12.863503+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"f7fc8e891d83a3e1"}},{"code_sha256":"de3c1ddb7a5bbb47","code_sha256_prefix":"de3c1ddb7a5bbb47","entry":"yarn_find_correction_dim","repo":"deepseek-ai/deepseek-vl2","repo_kind":"official","path":"deepseek_vl2/models/modeling_deepseek.py","file_url":"https://github.com/deepseek-ai/deepseek-vl2/blob/HEAD/deepseek_vl2/models/modeling_deepseek.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"num_rotations:int/0/int, dim:int/0/int, base:int/0/int, max_position_embeddings:int/0/int","fixture_out_type":"float","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","retrieve_with":{"tool":"get_code","code_sha256":"de3c1ddb7a5bbb47"},"code_page":null,"census":null,"licence":"MIT","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from Miraclecsc/Discrete-Latent-Reasoning, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"de3c1ddb7a5bbb47"}},{"code_sha256":"ed5f1f4e8c0439b2","code_sha256_prefix":"ed5f1f4e8c0439b2","entry":"yarn_find_correction_range","repo":"deepseek-ai/deepseek-vl2","repo_kind":"official","path":"deepseek_vl2/models/modeling_deepseek.py","file_url":"https://github.com/deepseek-ai/deepseek-vl2/blob/HEAD/deepseek_vl2/models/modeling_deepseek.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"low_rot:float/0/float, high_rot:float/0/float, dim:int/0/int, base:int/0/int, max_position_embeddings:int/0/int","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from Miraclecsc/Discrete-Latent-Reasoning, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"ed5f1f4e8c0439b2"}},{"code_sha256":"8dfdb3a53834d90f","code_sha256_prefix":"8dfdb3a53834d90f","entry":"yarn_get_mscale","repo":"deepseek-ai/deepseek-vl2","repo_kind":"official","path":"deepseek_vl2/models/modeling_deepseek.py","file_url":"https://github.com/deepseek-ai/deepseek-vl2/blob/HEAD/deepseek_vl2/models/modeling_deepseek.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"scale:float/0/float, mscale:float/0/float","fixture_out_type":"float","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","retrieve_with":{"tool":"get_code","code_sha256":"8dfdb3a53834d90f"},"code_page":"/code/yarn-get-mscale","census":null,"licence":"MIT","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from Miraclecsc/Discrete-Latent-Reasoning, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"8dfdb3a53834d90f"}},{"code_sha256":"132894d1028abd5a","code_sha256_prefix":"132894d1028abd5a","entry":"get_conv_template","repo":"deepseek-ai/deepseek-vl2","repo_kind":"official","path":"deepseek_vl2/models/conversation.py","file_url":"https://github.com/deepseek-ai/deepseek-vl2/blob/HEAD/deepseek_vl2/models/conversation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/get-conv-template","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"132894d1028abd5a"}},{"code_sha256":"8a1727ee6e04ec45","code_sha256_prefix":"8a1727ee6e04ec45","entry":"load_pretrained_model","repo":"deepseek-ai/deepseek-vl2","repo_kind":"official","path":"deepseek_vl2/utils/io.py","file_url":"https://github.com/deepseek-ai/deepseek-vl2/blob/HEAD/deepseek_vl2/utils/io.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/load-pretrained-model","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"8a1727ee6e04ec45"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"5214003bb6e74712be73189e21c2767d8def48f861a8a7c122f5e378425d3132","record_changed_at":"2026-10-04","record_changed_at_basis":"changed"}