{"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/xgen-mm-blip-3-a-family-of-open-large","title":"xGen-MM (BLIP-3): A Family of Open Large Multimodal Models","arxiv_id":"2408.08872","date":"2024-08-16","proceeding":null,"authors":["Le Xue","Manli Shu","Anas Awadalla","Jun Wang","An Yan","Senthil Purushwalkam","Honglu Zhou","Viraj Prabhu","Yutong Dai","Michael S Ryoo","Shrikant Kendre","Jieyu Zhang","Can Qin","Shu Zhang","Chia-Chih Chen","Ning Yu","Juntao Tan","Tulika Manoj Awalgaonkar","Shelby Heinecke","Huan Wang","Yejin Choi","Ludwig Schmidt","Zeyuan Chen","Silvio Savarese","Juan Carlos Niebles","Caiming Xiong","ran Xu"],"abstract":"This report introduces xGen-MM (also known as BLIP-3), a framework for developing Large Multimodal Models (LMMs). The framework comprises meticulously curated datasets, a training recipe, model architectures, and a resulting suite of LMMs. xGen-MM, short for xGen-MultiModal, expands the Salesforce xGen initiative on foundation AI models. Our models undergo rigorous evaluation across a range of tasks, including both single and multi-image benchmarks. Our pre-trained base model exhibits strong in-context learning capabilities and the instruction-tuned model demonstrates competitive performance among open-source LMMs with similar model sizes. In addition, we introduce a safety-tuned model with DPO, aiming to mitigate harmful behaviors such as hallucinations and improve safety. We open-source our models, curated large-scale datasets, and our fine-tuning codebase to facilitate further advancements in LMM research. Associated resources will be available on our project page above.","url_abs":"https://arxiv.org/abs/2408.08872v2","url_pdf":"https://arxiv.org/pdf/2408.08872v2.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":"xgen-mm-blip-3-a-family-of-open-large","repo_url":"https://github.com/zzxslp/som-llava","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"in-context-learning","task_name":"In-Context Learning"}],"methods":[{"method_slug":"base","method_name":"BASE"},{"method_slug":"dpo","method_name":"DPO"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2408.08872","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.08872"}},"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/zzxslp/som-llava","reach":{"status":"ok"}}],"summary":{"ran":4,"ran_fixture":1,"unverified":1},"by_repo_kind":{"listed":{"samples":6,"ran":5,"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":6,"samples":[{"code_sha256_prefix":"cb9ab8a6655701f7","entry":"encode_image_from_file","repo":"zzxslp/som-llava","repo_kind":"listed","path":"SoM/gpt4v.py","file_url":"https://github.com/zzxslp/som-llava/blob/HEAD/SoM/gpt4v.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cb9ab8a6655701f7"}},{"code_sha256_prefix":"71138ba2dfbe50e1","entry":"encode_image_from_pil","repo":"zzxslp/som-llava","repo_kind":"listed","path":"SoM/gpt4v.py","file_url":"https://github.com/zzxslp/som-llava/blob/HEAD/SoM/gpt4v.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"71138ba2dfbe50e1"}},{"code_sha256_prefix":"c53ec291fabfc643","entry":"ms_deform_attn_core_pytorch","repo":"zzxslp/som-llava","repo_kind":"listed","path":"SoM/ops/functions/ms_deform_attn_func.py","file_url":"https://github.com/zzxslp/som-llava/blob/HEAD/SoM/ops/functions/ms_deform_attn_func.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c53ec291fabfc643"}},{"code_sha256_prefix":"de0b3299e81e5722","entry":"prepare_inputs","repo":"zzxslp/som-llava","repo_kind":"listed","path":"SoM/gpt4v.py","file_url":"https://github.com/zzxslp/som-llava/blob/HEAD/SoM/gpt4v.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"de0b3299e81e5722"}},{"code_sha256_prefix":"f64fc4b6daa7513d","entry":"remove_small_regions","repo":"zzxslp/som-llava","repo_kind":"listed","path":"SoM/task_adapter/sam/tasks/inference_sam_m2m_auto.py","file_url":"https://github.com/zzxslp/som-llava/blob/HEAD/SoM/task_adapter/sam/tasks/inference_sam_m2m_auto.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f64fc4b6daa7513d"}},{"code_sha256_prefix":"bf3338796e883021","entry":"highlight","repo":"zzxslp/som-llava","repo_kind":"listed","path":"SoM/demo_gpt4v_som.py","file_url":"https://github.com/zzxslp/som-llava/blob/HEAD/SoM/demo_gpt4v_som.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bf3338796e883021"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}