{"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/groma-localized-visual-tokenization-for","title":"Groma: Localized Visual Tokenization for Grounding Multimodal Large Language Models","arxiv_id":"2404.13013","date":"2024-04-19","proceeding":null,"authors":["Chuofan Ma","Yi Jiang","Jiannan Wu","Zehuan Yuan","Xiaojuan Qi"],"abstract":"We introduce Groma, a Multimodal Large Language Model (MLLM) with grounded and fine-grained visual perception ability. Beyond holistic image understanding, Groma is adept at region-level tasks such as region captioning and visual grounding. Such capabilities are built upon a localized visual tokenization mechanism, where an image input is decomposed into regions of interest and subsequently encoded into region tokens. By integrating region tokens into user instructions and model responses, we seamlessly enable Groma to understand user-specified region inputs and ground its textual output to images. Besides, to enhance the grounded chat ability of Groma, we curate a visually grounded instruction dataset by leveraging the powerful GPT-4V and visual prompting techniques. Compared with MLLMs that rely on the language model or external module for localization, Groma consistently demonstrates superior performances in standard referring and grounding benchmarks, highlighting the advantages of embedding localization into image tokenization. Project page: https://groma-mllm.github.io/.","url_abs":"https://arxiv.org/abs/2404.13013v1","url_pdf":"https://arxiv.org/pdf/2404.13013v1.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":"groma-localized-visual-tokenization-for","repo_url":"https://github.com/FoundationVision/Groma","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"multimodal-large-language-model","task_name":"Multimodal Large Language Model"},{"task_slug":"natural-language-visual-grounding","task_name":"Natural Language Visual Grounding"},{"task_slug":"visual-grounding","task_name":"Visual Grounding"},{"task_slug":"visual-prompting","task_name":"Visual Prompting"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/natural-language-visual-grounding-on","task":"Natural Language Visual Grounding","dataset":"ScreenSpot","model":"Groma","rank_in_archive_order":17,"of":18,"metrics":{"Accuracy (%)":"5.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.13013","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.13013"}},"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/FoundationVision/Groma","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":4,"ran_violates":1,"unverified":4},"by_repo_kind":{"official":{"samples":9,"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":0,"samples":[{"code_sha256_prefix":"af6df62850536230","entry":"align_tensor","repo":"FoundationVision/Groma","repo_kind":"official","path":"groma/model/roi_align.py","file_url":"https://github.com/FoundationVision/Groma/blob/HEAD/groma/model/roi_align.py","link_basis":"plan_row","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":"af6df62850536230"}},{"code_sha256_prefix":"77950a821bd7955f","entry":"coordinate_to_encoding","repo":"FoundationVision/Groma","repo_kind":"official","path":"groma/model/roi_align.py","file_url":"https://github.com/FoundationVision/Groma/blob/HEAD/groma/model/roi_align.py","link_basis":"plan_row","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":"77950a821bd7955f"}},{"code_sha256_prefix":"2a8d2d5ef535755e","entry":"custom_collate_fn","repo":"FoundationVision/Groma","repo_kind":"official","path":"groma/eval/model_refcocog.py","file_url":"https://github.com/FoundationVision/Groma/blob/HEAD/groma/eval/model_refcocog.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":"2a8d2d5ef535755e"}},{"code_sha256_prefix":"763f6fe20bd52fbb","entry":"parse_score","repo":"FoundationVision/Groma","repo_kind":"official","path":"groma/eval/eval_gpt_review_visual.py","file_url":"https://github.com/FoundationVision/Groma/blob/HEAD/groma/eval/eval_gpt_review_visual.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"763f6fe20bd52fbb"}},{"code_sha256_prefix":"79307b0c7bfc9b57","entry":"str2spi","repo":"FoundationVision/Groma","repo_kind":"official","path":"groma/model/roi_align.py","file_url":"https://github.com/FoundationVision/Groma/blob/HEAD/groma/model/roi_align.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":"79307b0c7bfc9b57"}},{"code_sha256_prefix":"55b3991e52737846","entry":"get_eval","repo":"FoundationVision/Groma","repo_kind":"official","path":"groma/eval/eval_gpt_review_visual.py","file_url":"https://github.com/FoundationVision/Groma/blob/HEAD/groma/eval/eval_gpt_review_visual.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":"55b3991e52737846"}},{"code_sha256_prefix":"f78ec6fd3d821f61","entry":"load_model","repo":"FoundationVision/Groma","repo_kind":"official","path":"groma/serve/model_worker.py","file_url":"https://github.com/FoundationVision/Groma/blob/HEAD/groma/serve/model_worker.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":"f78ec6fd3d821f61"}},{"code_sha256_prefix":"37899f22fb191b37","entry":"pretty_print_semaphore","repo":"FoundationVision/Groma","repo_kind":"official","path":"groma/utils.py","file_url":"https://github.com/FoundationVision/Groma/blob/HEAD/groma/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":"37899f22fb191b37"}},{"code_sha256_prefix":"f9939a84b9a65279","entry":"violates_moderation","repo":"FoundationVision/Groma","repo_kind":"official","path":"groma/utils.py","file_url":"https://github.com/FoundationVision/Groma/blob/HEAD/groma/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":"f9939a84b9a65279"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}