{"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/2402-03766","title":"MobileVLM V2: Faster and Stronger Baseline for Vision Language Model","arxiv_id":"2402.03766","date":"2024-02-06","proceeding":null,"authors":["Xiangxiang Chu","Limeng Qiao","Xinyu Zhang","Shuang Xu","Fei Wei","Yang Yang","Xiaofei Sun","Yiming Hu","Xinyang Lin","Bo Zhang","Chunhua Shen"],"abstract":"We introduce MobileVLM V2, a family of significantly improved vision language models upon MobileVLM, which proves that a delicate orchestration of novel architectural design, an improved training scheme tailored for mobile VLMs, and rich high-quality dataset curation can substantially benefit VLMs' performance. Specifically, MobileVLM V2 1.7B achieves better or on-par performance on standard VLM benchmarks compared with much larger VLMs at the 3B scale. Notably, our 3B model outperforms a large variety of VLMs at the 7B+ scale. Our models will be released at https://github.com/Meituan-AutoML/MobileVLM .","url_abs":"https://arxiv.org/abs/2402.03766v1","url_pdf":"https://arxiv.org/pdf/2402.03766v1.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":"2402-03766","repo_url":"https://github.com/meituan-automl/mobilevlm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"automl","task_name":"AutoML"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.03766","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03766"}},"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/meituan-automl/mobilevlm","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":4,"ran_violates":1,"ran_honours":1,"unverified":2},"by_repo_kind":{"official":{"samples":8,"ran":6,"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":"592b3c1a88f93d7c","entry":"expand2square","repo":"meituan-automl/mobilevlm","repo_kind":"official","path":"mobilevlm/utils.py","file_url":"https://github.com/meituan-automl/mobilevlm/blob/HEAD/mobilevlm/utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"592b3c1a88f93d7c"}},{"code_sha256_prefix":"42a46570620cd9fa","entry":"get_chunk","repo":"meituan-automl/mobilevlm","repo_kind":"official","path":"mobilevlm/eval/model_vqa_loader.py","file_url":"https://github.com/meituan-automl/mobilevlm/blob/HEAD/mobilevlm/eval/model_vqa_loader.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"42a46570620cd9fa"}},{"code_sha256_prefix":"bae18947b56f2be1","entry":"is_none","repo":"meituan-automl/mobilevlm","repo_kind":"official","path":"mobilevlm/eval/model_vqa_mmbench.py","file_url":"https://github.com/meituan-automl/mobilevlm/blob/HEAD/mobilevlm/eval/model_vqa_mmbench.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bae18947b56f2be1"}},{"code_sha256_prefix":"3aada9ef083faccd","entry":"load_image_from_base64","repo":"meituan-automl/mobilevlm","repo_kind":"official","path":"mobilevlm/utils.py","file_url":"https://github.com/meituan-automl/mobilevlm/blob/HEAD/mobilevlm/utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3aada9ef083faccd"}},{"code_sha256_prefix":"e8f3a2a1be36a4d7","entry":"process_images","repo":"meituan-automl/mobilevlm","repo_kind":"official","path":"mobilevlm/utils.py","file_url":"https://github.com/meituan-automl/mobilevlm/blob/HEAD/mobilevlm/utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e8f3a2a1be36a4d7"}},{"code_sha256_prefix":"076c252c52cbb161","entry":"split_list","repo":"meituan-automl/mobilevlm","repo_kind":"official","path":"mobilevlm/eval/model_vqa_loader.py","file_url":"https://github.com/meituan-automl/mobilevlm/blob/HEAD/mobilevlm/eval/model_vqa_loader.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"076c252c52cbb161"}},{"code_sha256_prefix":"0100980e0d43fee3","entry":"build_vision_projector","repo":"meituan-automl/mobilevlm","repo_kind":"official","path":"mobilevlm/model/vision_projector.py","file_url":"https://github.com/meituan-automl/mobilevlm/blob/HEAD/mobilevlm/model/vision_projector.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0100980e0d43fee3"}},{"code_sha256_prefix":"cd281e119911f887","entry":"build_vision_tower","repo":"meituan-automl/mobilevlm","repo_kind":"official","path":"mobilevlm/model/vision_encoder.py","file_url":"https://github.com/meituan-automl/mobilevlm/blob/HEAD/mobilevlm/model/vision_encoder.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cd281e119911f887"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}