{"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/mobilevlm-a-vision-language-model-for-better","title":"MobileVLM: A Vision-Language Model for Better Intra- and Inter-UI Understanding","arxiv_id":"2409.14818","date":"2024-09-23","proceeding":null,"authors":["Qinzhuo Wu","Weikai Xu","Wei Liu","Tao Tan","Jianfeng Liu","Ang Li","Jian Luan","Bin Wang","Shuo Shang"],"abstract":"Recently, mobile AI agents based on VLMs have been gaining increasing attention. These works typically utilize VLM as a foundation, fine-tuning it with instruction-based mobile datasets. However, these VLMs are typically pre-trained on general-domain data, which often results in a lack of fundamental capabilities specific to the mobile domain. Therefore, they may struggle to recognize specific UI elements and understand intra-UI fine-grained information. In addition, the current fine-tuning task focuses on interacting with the most relevant element for the given instruction. These fine-tuned VLMs may still ignore the relationships between UI pages, neglect the roles of elements in page transitions and lack inter-UI understanding. To address issues, we propose a VLM called MobileVLM, which includes two additional pre-training stages to enhance both intra- and inter-UI understanding. We defined four UI-based pre-training tasks, enabling the model to better perceive fine-grained elements and capture page transition actions. To address the lack of mobile pre-training data, we built a large Chinese mobile dataset Mobile3M from scratch, which contains 3 million UI pages, and real-world transition actions, forming a directed graph structure. Experimental results show MobileVLM excels on both our test set and public mobile benchmarks, outperforming existing VLMs.","url_abs":"https://arxiv.org/abs/2409.14818v2","url_pdf":"https://arxiv.org/pdf/2409.14818v2.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":"mobilevlm-a-vision-language-model-for-better","repo_url":"https://github.com/xiaomi/mobilevlm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2409.14818","atlas_url":"https://app.syntology.ai/?focus=2409.14818","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.14818"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/xiaomi/mobilevlm","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":12,"ran_draft_wrong":1,"unverified":5},"by_repo_kind":{"official":{"samples":18,"ran":13,"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":18,"samples":[{"code_sha256_prefix":"3aac5dfd1627a360","entry":"calculate_iou","repo":"xiaomi/mobilevlm","repo_kind":"official","path":"test_515/count_aver_iou.py","file_url":"https://github.com/xiaomi/mobilevlm/blob/HEAD/test_515/count_aver_iou.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"3aac5dfd1627a360"}},{"code_sha256_prefix":"e4b5d64062a91b7f","entry":"dict2dict","repo":"xiaomi/mobilevlm","repo_kind":"official","path":"corpus/list_prefix.py","file_url":"https://github.com/xiaomi/mobilevlm/blob/HEAD/corpus/list_prefix.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"e4b5d64062a91b7f"}},{"code_sha256_prefix":"48c980f8b78480c1","entry":"dict2txt","repo":"xiaomi/mobilevlm","repo_kind":"official","path":"corpus/list_prefix.py","file_url":"https://github.com/xiaomi/mobilevlm/blob/HEAD/corpus/list_prefix.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"48c980f8b78480c1"}},{"code_sha256_prefix":"b2e1feaa54352576","entry":"dictcount","repo":"xiaomi/mobilevlm","repo_kind":"official","path":"corpus/list_prefix.py","file_url":"https://github.com/xiaomi/mobilevlm/blob/HEAD/corpus/list_prefix.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"b2e1feaa54352576"}},{"code_sha256_prefix":"e479638f07e3d5f2","entry":"gpt_usage","repo":"xiaomi/mobilevlm","repo_kind":"official","path":"corpus/chatgpt.py","file_url":"https://github.com/xiaomi/mobilevlm/blob/HEAD/corpus/chatgpt.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"e479638f07e3d5f2"}},{"code_sha256_prefix":"e0f0dbdcd40e0123","entry":"load_dict","repo":"xiaomi/mobilevlm","repo_kind":"official","path":"corpus/bm25.py","file_url":"https://github.com/xiaomi/mobilevlm/blob/HEAD/corpus/bm25.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"e0f0dbdcd40e0123"}},{"code_sha256_prefix":"1c84aeb1de479bcc","entry":"load_json","repo":"xiaomi/mobilevlm","repo_kind":"official","path":"corpus/bm25.py","file_url":"https://github.com/xiaomi/mobilevlm/blob/HEAD/corpus/bm25.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"1c84aeb1de479bcc"}},{"code_sha256_prefix":"1aa5d2a1084ca8a3","entry":"load_txt","repo":"xiaomi/mobilevlm","repo_kind":"official","path":"corpus/bm25.py","file_url":"https://github.com/xiaomi/mobilevlm/blob/HEAD/corpus/bm25.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"1aa5d2a1084ca8a3"}},{"code_sha256_prefix":"829b3a29017bf6be","entry":"local_image_to_data_url","repo":"xiaomi/mobilevlm","repo_kind":"official","path":"test_515/gpt.py","file_url":"https://github.com/xiaomi/mobilevlm/blob/HEAD/test_515/gpt.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"829b3a29017bf6be"}},{"code_sha256_prefix":"8b733c9fc590e4c1","entry":"preprocess","repo":"xiaomi/mobilevlm","repo_kind":"official","path":"finetune.py","file_url":"https://github.com/xiaomi/mobilevlm/blob/HEAD/finetune.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8b733c9fc590e4c1"}},{"code_sha256_prefix":"d4b2c3b54965a829","entry":"process_html","repo":"xiaomi/mobilevlm","repo_kind":"official","path":"test_515/build_test_inout_put.py","file_url":"https://github.com/xiaomi/mobilevlm/blob/HEAD/test_515/build_test_inout_put.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"d4b2c3b54965a829"}},{"code_sha256_prefix":"707a0ecb9f3c6f2d","entry":"read_json_file","repo":"xiaomi/mobilevlm","repo_kind":"official","path":"corpus/xml_test_22.py","file_url":"https://github.com/xiaomi/mobilevlm/blob/HEAD/corpus/xml_test_22.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"707a0ecb9f3c6f2d"}},{"code_sha256_prefix":"a8686802123b33d2","entry":"scale_coordinates","repo":"xiaomi/mobilevlm","repo_kind":"official","path":"test_515/count_aver_iou.py","file_url":"https://github.com/xiaomi/mobilevlm/blob/HEAD/test_515/count_aver_iou.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"a8686802123b33d2"}},{"code_sha256_prefix":"2f9f1293699146bc","entry":"any_tree_to_html","repo":"xiaomi/mobilevlm","repo_kind":"official","path":"xml_to_html.py","file_url":"https://github.com/xiaomi/mobilevlm/blob/HEAD/xml_to_html.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"2f9f1293699146bc"}},{"code_sha256_prefix":"ff85b6fede884ce7","entry":"chatgpt","repo":"xiaomi/mobilevlm","repo_kind":"official","path":"corpus/chatgpt.py","file_url":"https://github.com/xiaomi/mobilevlm/blob/HEAD/corpus/chatgpt.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"ff85b6fede884ce7"}},{"code_sha256_prefix":"7261ce7a4e26085e","entry":"extract_coordinates","repo":"xiaomi/mobilevlm","repo_kind":"official","path":"test_515/count_aver_iou.py","file_url":"https://github.com/xiaomi/mobilevlm/blob/HEAD/test_515/count_aver_iou.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"7261ce7a4e26085e"}},{"code_sha256_prefix":"b6659c22b1479358","entry":"gpt_4v_actionspace","repo":"xiaomi/mobilevlm","repo_kind":"official","path":"test_515/gpt.py","file_url":"https://github.com/xiaomi/mobilevlm/blob/HEAD/test_515/gpt.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"b6659c22b1479358"}},{"code_sha256_prefix":"e513b28efe0be636","entry":"gpt_4v_ref","repo":"xiaomi/mobilevlm","repo_kind":"official","path":"test_515/gpt.py","file_url":"https://github.com/xiaomi/mobilevlm/blob/HEAD/test_515/gpt.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"e513b28efe0be636"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}