{"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/adamms-model-merging-for-heterogeneous","title":"AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization","arxiv_id":"2503.23733","date":"2025-03-31","proceeding":"CVPR 2025 1","authors":["Yiyang Du","Xiaochen Wang","Chi Chen","Jiabo Ye","Yiru Wang","Peng Li","Ming Yan","Ji Zhang","Fei Huang","Zhifang Sui","Maosong Sun","Yang Liu"],"abstract":"Recently, model merging methods have demonstrated powerful strengths in combining abilities on various tasks from multiple Large Language Models (LLMs). While previous model merging methods mainly focus on merging homogeneous models with identical architecture, they meet challenges when dealing with Multimodal Large Language Models (MLLMs) with inherent heterogeneous property, including differences in model architecture and the asymmetry in the parameter space. In this work, we propose AdaMMS, a novel model merging method tailored for heterogeneous MLLMs. Our method tackles the challenges in three steps: mapping, merging and searching. Specifically, we first design mapping function between models to apply model merging on MLLMs with different architecture. Then we apply linear interpolation on model weights to actively adapt the asymmetry in the heterogeneous MLLMs. Finally in the hyper-parameter searching step, we propose an unsupervised hyper-parameter selection method for model merging. As the first model merging method capable of merging heterogeneous MLLMs without labeled data, extensive experiments on various model combinations demonstrated that AdaMMS outperforms previous model merging methods on various vision-language benchmarks.","url_abs":"https://arxiv.org/abs/2503.23733v1","url_pdf":"https://arxiv.org/pdf/2503.23733v1.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":"adamms-model-merging-for-heterogeneous","repo_url":"https://github.com/thunlp-mt/adamms","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2503.23733","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.23733"}},"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/thunlp-mt/adamms","reach":null}],"summary":{"ran_draft_wrong":3,"ran_honours":2,"ran_fixture":3},"by_repo_kind":{"official":{"samples":8,"ran":8,"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":8,"samples":[{"code_sha256_prefix":"9a0346fac1c94b40","entry":"disjoint_merge","repo":"thunlp-mt/adamms","repo_kind":"official","path":"merge/ties_merging.py","file_url":"https://github.com/thunlp-mt/adamms/blob/HEAD/merge/ties_merging.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9a0346fac1c94b40"}},{"code_sha256_prefix":"13f5811639b2bd71","entry":"do_merging_strategy","repo":"thunlp-mt/adamms","repo_kind":"official","path":"merge/ties_merging.py","file_url":"https://github.com/thunlp-mt/adamms/blob/HEAD/merge/ties_merging.py","link_basis":"first_harvest_node","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":"13f5811639b2bd71"}},{"code_sha256_prefix":"843a0f021c3f85d2","entry":"resolve_sign","repo":"thunlp-mt/adamms","repo_kind":"official","path":"merge/ties_merging.py","file_url":"https://github.com/thunlp-mt/adamms/blob/HEAD/merge/ties_merging.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"843a0f021c3f85d2"}},{"code_sha256_prefix":"860408c2bd01950e","entry":"resolve_zero_signs","repo":"thunlp-mt/adamms","repo_kind":"official","path":"merge/ties_merging.py","file_url":"https://github.com/thunlp-mt/adamms/blob/HEAD/merge/ties_merging.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"860408c2bd01950e"}},{"code_sha256_prefix":"72391ca34e9a8cfe","entry":"state_dict_to_vector","repo":"thunlp-mt/adamms","repo_kind":"official","path":"merge/ties_merging.py","file_url":"https://github.com/thunlp-mt/adamms/blob/HEAD/merge/ties_merging.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"72391ca34e9a8cfe"}},{"code_sha256_prefix":"9b2cd521bf6db9bf","entry":"ties_merging","repo":"thunlp-mt/adamms","repo_kind":"official","path":"merge/ties_merging.py","file_url":"https://github.com/thunlp-mt/adamms/blob/HEAD/merge/ties_merging.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9b2cd521bf6db9bf"}},{"code_sha256_prefix":"9f4ac26be542f539","entry":"topk_values_mask","repo":"thunlp-mt/adamms","repo_kind":"official","path":"merge/ties_merging.py","file_url":"https://github.com/thunlp-mt/adamms/blob/HEAD/merge/ties_merging.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9f4ac26be542f539"}},{"code_sha256_prefix":"bf6efec91354af72","entry":"vector_to_state_dict","repo":"thunlp-mt/adamms","repo_kind":"official","path":"merge/ties_merging.py","file_url":"https://github.com/thunlp-mt/adamms/blob/HEAD/merge/ties_merging.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bf6efec91354af72"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}