{"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/mantis-interleaved-multi-image-instruction","title":"MANTIS: Interleaved Multi-Image Instruction Tuning","arxiv_id":"2405.01483","date":"2024-05-02","proceeding":null,"authors":["Dongfu Jiang","Xuan He","Huaye Zeng","Cong Wei","Max Ku","Qian Liu","Wenhu Chen"],"abstract":"Large multimodal models (LMMs) have shown great results in single-image vision language tasks. However, their abilities to solve multi-image visual language tasks is yet to be improved. The existing LMMs like OpenFlamingo, Emu2, and Idefics gain their multi-image ability through pre-training on hundreds of millions of noisy interleaved image-text data from the web, which is neither efficient nor effective. In this paper, we aim to build strong multi-image LMMs via instruction tuning with academic-level resources. Therefore, we meticulously construct Mantis-Instruct containing 721K multi-image instruction data to train a family of Mantis models. The instruction tuning empowers Mantis with different multi-image skills like co-reference, comparison, reasoning, and temporal understanding. We evaluate Mantis on 8 multi-image benchmarks and 6 single-image benchmarks. Mantis-Idefics2 can achieve SoTA results on all the multi-image benchmarks and beat the strongest multi-image baseline, Idefics2-8B by an average of 13 absolute points. Notably, Idefics2-8B was pre-trained on 140M interleaved multi-image data, which is 200x larger than Mantis-Instruct. We observe that Mantis performs equivalently well on the held-in and held-out benchmarks, which shows its generalization ability. We further evaluate Mantis on single-image benchmarks and demonstrate that Mantis also maintains a strong single-image performance on par with CogVLM and Emu2. Our results show that multi-image abilities are not necessarily gained through massive pre-training, instead, they can be gained by low-cost instruction tuning. The training and evaluation of Mantis has paved the road for future work to improve LMMs' multi-image abilities.","url_abs":"https://arxiv.org/abs/2405.01483v3","url_pdf":"https://arxiv.org/pdf/2405.01483v3.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":"mantis-interleaved-multi-image-instruction","repo_url":"https://github.com/TIGER-AI-Lab/Mantis","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2405.01483","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.01483"}},"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/TIGER-AI-Lab/Mantis","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":3,"unverified":2},"by_repo_kind":{"official":{"samples":5,"ran":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":0,"samples":[{"code_sha256_prefix":"bdf3deef8bbd025f","entry":"get_prompt_uids","repo":"TIGER-AI-Lab/Mantis","repo_kind":"official","path":"mantis/easy_openai/openai_utils.py","file_url":"https://github.com/TIGER-AI-Lab/Mantis/blob/HEAD/mantis/easy_openai/openai_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bdf3deef8bbd025f"}},{"code_sha256_prefix":"29a942c0eb6bb78d","entry":"load_graph","repo":"TIGER-AI-Lab/Mantis","repo_kind":"official","path":"mantis/benchmark/mementos_eval_utils.py","file_url":"https://github.com/TIGER-AI-Lab/Mantis/blob/HEAD/mantis/benchmark/mementos_eval_utils.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":"29a942c0eb6bb78d"}},{"code_sha256_prefix":"3b97d96aa93fe3ee","entry":"local_image_to_data_url","repo":"TIGER-AI-Lab/Mantis","repo_kind":"official","path":"mantis/easy_openai/openai_utils.py","file_url":"https://github.com/TIGER-AI-Lab/Mantis/blob/HEAD/mantis/easy_openai/openai_utils.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":"3b97d96aa93fe3ee"}},{"code_sha256_prefix":"09e8ea99a1c791f2","entry":"eval_mementos_subset","repo":"TIGER-AI-Lab/Mantis","repo_kind":"official","path":"mantis/benchmark/mementos_eval_utils.py","file_url":"https://github.com/TIGER-AI-Lab/Mantis/blob/HEAD/mantis/benchmark/mementos_eval_utils.py","link_basis":"first_harvest_node","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":"09e8ea99a1c791f2"}},{"code_sha256_prefix":"08f6992e74a8110d","entry":"save_eval_results","repo":"TIGER-AI-Lab/Mantis","repo_kind":"official","path":"mantis/benchmark/eval_on_mementos.py","file_url":"https://github.com/TIGER-AI-Lab/Mantis/blob/HEAD/mantis/benchmark/eval_on_mementos.py","link_basis":"first_harvest_node","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":"08f6992e74a8110d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}