{"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/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"}},"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/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":1,"unverified":1},"by_repo_kind":{"official":{"samples":8,"ran":7,"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":"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"269bb26a4378dd51"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"592b3c1a88f93d7c"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"42a46570620cd9fa"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bae18947b56f2be1"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"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","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c3ee9d07c900dd55"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"076c252c52cbb161"}},{"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":"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":"d6153bc4456b4b0c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}