{"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/mini-gemini-mining-the-potential-of-multi","title":"Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models","arxiv_id":"2403.18814","date":"2024-03-27","proceeding":null,"authors":["Yanwei Li","Yuechen Zhang","Chengyao Wang","Zhisheng Zhong","Yixin Chen","Ruihang Chu","Shaoteng Liu","Jiaya Jia"],"abstract":"In this work, we introduce Mini-Gemini, a simple and effective framework enhancing multi-modality Vision Language Models (VLMs). Despite the advancements in VLMs facilitating basic visual dialog and reasoning, a performance gap persists compared to advanced models like GPT-4 and Gemini. We try to narrow the gap by mining the potential of VLMs for better performance and any-to-any workflow from three aspects, i.e., high-resolution visual tokens, high-quality data, and VLM-guided generation. To enhance visual tokens, we propose to utilize an additional visual encoder for high-resolution refinement without increasing the visual token count. We further construct a high-quality dataset that promotes precise image comprehension and reasoning-based generation, expanding the operational scope of current VLMs. In general, Mini-Gemini further mines the potential of VLMs and empowers current frameworks with image understanding, reasoning, and generation simultaneously. Mini-Gemini supports a series of dense and MoE Large Language Models (LLMs) from 2B to 34B. It is demonstrated to achieve leading performance in several zero-shot benchmarks and even surpasses the developed private models. Code and models are available at https://github.com/dvlab-research/MiniGemini.","url_abs":"https://arxiv.org/abs/2403.18814v1","url_pdf":"https://arxiv.org/pdf/2403.18814v1.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":"mini-gemini-mining-the-potential-of-multi","repo_url":"https://github.com/dvlab-research/minigemini","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"mini-gemini-mining-the-potential-of-multi","repo_url":"https://github.com/dvlab-research/MGM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-comprehension","task_name":"Image Comprehension"},{"task_slug":"referring-expression-comprehension","task_name":"Referring Expression Comprehension"},{"task_slug":"referring-expression-generation","task_name":"Referring expression generation"},{"task_slug":"visual-dialogue","task_name":"Visual Dialog"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"}],"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":"gpt-4","method_name":"GPT-4"},{"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":"moe","method_name":"MoE"},{"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"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-coloninst-v1-seen","task":"Image Classification","dataset":"ColonINST-v1 (Seen)","model":"MGM-2B (w/o LoRA, w/ extra data)","rank_in_archive_order":7,"of":17,"metrics":{"Accuray":"93.24"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-coloninst-v1-seen","task":"Image Classification","dataset":"ColonINST-v1 (Seen)","model":"MGM-2B (w/o LoRA, w/o extra data)","rank_in_archive_order":10,"of":17,"metrics":{"Accuray":"92.97"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-coloninst-v1-unseen","task":"Image Classification","dataset":"ColonINST-v1 (Unseen)","model":"MGM-2B\n  (w/o LoRA, w/o extra data)","rank_in_archive_order":7,"of":17,"metrics":{"Accuray":"78.99"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-coloninst-v1-unseen","task":"Image Classification","dataset":"ColonINST-v1 (Unseen)","model":"MGM-2B\n  (w/o LoRA, w/ extra data)","rank_in_archive_order":9,"of":17,"metrics":{"Accuray":"78.69"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-generation-on-coloninst","task":"Referring expression generation","dataset":"ColonINST-v1 (Seen)","model":"MGM-2B\n  (w/o LoRA, w/ extra data)","rank_in_archive_order":4,"of":17,"metrics":{"Accuray":"98.75"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-generation-on-coloninst","task":"Referring expression generation","dataset":"ColonINST-v1 (Seen)","model":"MGM-2B\n  (w/o LoRA, w/o extra data)","rank_in_archive_order":6,"of":17,"metrics":{"Accuray":"98.17"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-generation-on-coloninst-1","task":"Referring expression generation","dataset":"ColonINST-v1 (Unseen)","model":"MGM-2B\n  (w/o LoRA, w/ extra data)","rank_in_archive_order":6,"of":17,"metrics":{"Accuray":"74.30"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-generation-on-coloninst-1","task":"Referring expression generation","dataset":"ColonINST-v1 (Unseen)","model":"MGM-2B\n  (w/o LoRA, w/o extra data)","rank_in_archive_order":14,"of":17,"metrics":{"Accuray":"69.81"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-mm-vet","task":"Visual Question Answering","dataset":"MM-Vet","model":"Mini-Gemini-HD-BS","rank_in_archive_order":35,"of":231,"metrics":{"GPT-4 score":"60.8"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-mm-vet","task":"Visual Question Answering","dataset":"MM-Vet","model":"Mini-Gemini-HD","rank_in_archive_order":40,"of":231,"metrics":{"GPT-4 score":"59.3"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-mm-vet","task":"Visual Question Answering","dataset":"MM-Vet","model":"Mini-Gemini","rank_in_archive_order":50,"of":231,"metrics":{"GPT-4 score":"53.0"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2403.18814","atlas_url":"https://app.syntology.ai/?focus=2403.18814","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.18814"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2403.18814"},"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":"2403.18814"},"call":"get_harvested_code_for_paper(arxiv_id=\"2403.18814\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2403.18814"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2403.18814\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2403.18814"},"call":"get_concepts_for_paper(arxiv_id=\"2403.18814\")"}],"by_repo":[{"repo":"dvlab-research/minigemini","kind":"official","samples":8,"ran":8,"instrument":3,"unverified":0},{"repo":"dvlab-research/MGM","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"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/2403.18814.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/2403.18814.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/dvlab-research/MGM","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dvlab-research/minigemini","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":2,"ran_draft_wrong":3,"ran_violates":1,"ran_honours":2},"n_samples":8,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":0,"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":8,"ran":8,"n_ran_checked":5,"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":1,"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":1,"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":6,"n_ran_without_level_date":2,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-22","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":"269bb26a4378dd51","code_sha256_prefix":"269bb26a4378dd51","entry":"create_one_query","repo":"dvlab-research/minigemini","repo_kind":"official","path":"mgm/eval/model_math_vista.py","file_url":"https://github.com/dvlab-research/minigemini/blob/HEAD/mgm/eval/model_math_vista.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"problem:dict/0/?, shot_num:int/0/int, shot_type:str/0/str, use_caption:bool/0/bool","fixture_out_type":"str","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/create-one-query","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"269bb26a4378dd51"}},{"code_sha256":"592b3c1a88f93d7c","code_sha256_prefix":"592b3c1a88f93d7c","entry":"expand2square","repo":"dvlab-research/minigemini","repo_kind":"official","path":"mgm/mm_utils.py","file_url":"https://github.com/dvlab-research/minigemini/blob/HEAD/mgm/mm_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,"signature":"pil_img:Image/0/?, background_color:tuple/1/int","fixture_out_type":"Image","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/expand2square","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"592b3c1a88f93d7c"}},{"code_sha256":"42a46570620cd9fa","code_sha256_prefix":"42a46570620cd9fa","entry":"get_chunk","repo":"dvlab-research/minigemini","repo_kind":"official","path":"mgm/eval/model_math_vista.py","file_url":"https://github.com/dvlab-research/minigemini/blob/HEAD/mgm/eval/model_math_vista.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"signature":"lst:list/1/int, n:int/0/int, k:int/0/int","fixture_out_type":"list","retrieve_with":{"tool":"get_code","code_sha256":"42a46570620cd9fa"},"code_page":"/code/get-chunk","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"42a46570620cd9fa"}},{"code_sha256":"bae18947b56f2be1","code_sha256_prefix":"bae18947b56f2be1","entry":"is_none","repo":"dvlab-research/minigemini","repo_kind":"official","path":"mgm/eval/model_vqa_mmbench.py","file_url":"https://github.com/dvlab-research/minigemini/blob/HEAD/mgm/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,"signature":"value:NoneType/0/?","fixture_out_type":"bool","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/is-none","census":null,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from ASTRAL-Group/ASTRA, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"bae18947b56f2be1"}},{"code_sha256":"9b3c1cb391672ccb","code_sha256_prefix":"9b3c1cb391672ccb","entry":"load_image","repo":"dvlab-research/minigemini","repo_kind":"official","path":"predict.py","file_url":"https://github.com/dvlab-research/minigemini/blob/HEAD/predict.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"image_file:str/0/str","fixture_out_type":"Image","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/load-image","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"code_sha256":"c3ee9d07c900dd55","code_sha256_prefix":"c3ee9d07c900dd55","entry":"load_image_from_base64","repo":"dvlab-research/minigemini","repo_kind":"official","path":"mgm/mm_utils.py","file_url":"https://github.com/dvlab-research/minigemini/blob/HEAD/mgm/mm_utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"image:str/0/str","fixture_out_type":"PngImageFile","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/load-image-from-base64","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"c3ee9d07c900dd55"}},{"code_sha256":"d6153bc4456b4b0c","code_sha256_prefix":"d6153bc4456b4b0c","entry":"process_images","repo":"dvlab-research/minigemini","repo_kind":"official","path":"mgm/mm_utils.py","file_url":"https://github.com/dvlab-research/minigemini/blob/HEAD/mgm/mm_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"images:list/1/Image, image_processor:callable/0/?, model_cfg:MockModelConfig/0/?","fixture_out_type":"Tensor","level_recorded_at":"2026-09-25T22:21:49.183891+00:00","code_page":"/code/process-images","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"d6153bc4456b4b0c"}},{"code_sha256":"076c252c52cbb161","code_sha256_prefix":"076c252c52cbb161","entry":"split_list","repo":"dvlab-research/minigemini","repo_kind":"official","path":"mgm/eval/model_math_vista.py","file_url":"https://github.com/dvlab-research/minigemini/blob/HEAD/mgm/eval/model_math_vista.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"signature":"lst:list/1/int, n:int/0/int","fixture_out_type":"list","retrieve_with":{"tool":"get_code","code_sha256":"076c252c52cbb161"},"code_page":"/code/split-list","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"076c252c52cbb161"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"65c2cacb2f77afb21bfecc62eaeaac5ae4327ac42ba7c3150b5da7634cfcde30","record_changed_at":"2026-10-04","record_changed_at_basis":"changed"}