{"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/lira-inferring-segmentation-in-large-multi","title":"LIRA: Inferring Segmentation in Large Multi-modal Models with Local Interleaved Region Assistance","arxiv_id":"2507.06272","date":"2025-07-08","proceeding":null,"authors":["Zhang Li","Biao Yang","Qiang Liu","Zhiyin Ma","Shuo Zhang","Liang Yin","Linger Deng","Yabo Sun","Yuliang Liu","Xiang Bai"],"abstract":"While large multi-modal models (LMMs) demonstrate promising capabilities in segmentation and comprehension, they still struggle with two limitations: inaccurate segmentation and hallucinated comprehension. These challenges stem primarily from constraints in weak visual comprehension and a lack of fine-grained perception. To alleviate these limitations, we propose LIRA, a framework that capitalizes on the complementary relationship between visual comprehension and segmentation via two key components: (1) Semantic-Enhanced Feature Extractor (SEFE) improves object attribute inference by fusing semantic and pixel-level features, leading to more accurate segmentation; (2) Interleaved Local Visual Coupling (ILVC) autoregressively generates local descriptions after extracting local features based on segmentation masks, offering fine-grained supervision to mitigate hallucinations. Furthermore, we find that the precision of object segmentation is positively correlated with the latent related semantics of the <seg> token. To quantify this relationship and the model's potential semantic inferring ability, we introduce the Attributes Evaluation (AttrEval) dataset. Our experiments show that LIRA achieves state-of-the-art performance in both segmentation and comprehension tasks. Code will be available at https://github.com/echo840/LIRA.","url_abs":"https://arxiv.org/abs/2507.06272v2","url_pdf":"https://arxiv.org/pdf/2507.06272v2.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":[],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2507.06272","atlas_url":"https://app.syntology.ai/?focus=2507.06272","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.06272"}},"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":"deterministic:regex_extraction","url":"https://github.com/echo840/LIRA","reach":{"status":"ok"}}],"summary":{"unverified":6},"by_repo_kind":{"found_in_text":{"samples":6,"ran":0,"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":"dcdc7ef233f3e1e8","entry":"build_model","repo":"echo840/LIRA","repo_kind":"found_in_text","path":"xtuner/apis/model.py","file_url":"https://github.com/echo840/LIRA/blob/HEAD/xtuner/apis/model.py","link_basis":"first_harvest_node","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":"dcdc7ef233f3e1e8"}},{"code_sha256_prefix":"f8035a195671164a","entry":"convert_state_dict_to_hf","repo":"echo840/LIRA","repo_kind":"found_in_text","path":"xtuner/model/llava.py","file_url":"https://github.com/echo840/LIRA/blob/HEAD/xtuner/model/llava.py","link_basis":"harvester_set","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":"f8035a195671164a"}},{"code_sha256_prefix":"269c10dd16c744e8","entry":"create_reference_model","repo":"echo840/LIRA","repo_kind":"found_in_text","path":"xtuner/model/dpo.py","file_url":"https://github.com/echo840/LIRA/blob/HEAD/xtuner/model/dpo.py","link_basis":"first_harvest_node","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":"269c10dd16c744e8"}},{"code_sha256_prefix":"049bf7d70dc3234b","entry":"find_enclosed_values","repo":"echo840/LIRA","repo_kind":"found_in_text","path":"omg_llava/model/lira.py","file_url":"https://github.com/echo840/LIRA/blob/HEAD/omg_llava/model/lira.py","link_basis":"first_harvest_node","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":"049bf7d70dc3234b"}},{"code_sha256_prefix":"41ff9a76f657423e","entry":"get_seg_hidden_states","repo":"echo840/LIRA","repo_kind":"found_in_text","path":"omg_llava/model/lira.py","file_url":"https://github.com/echo840/LIRA/blob/HEAD/omg_llava/model/lira.py","link_basis":"first_harvest_node","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":"41ff9a76f657423e"}},{"code_sha256_prefix":"a5eac67304f51ddd","entry":"prepare_seg_pretrain_data","repo":"echo840/LIRA","repo_kind":"found_in_text","path":"omg_llava/model/lira.py","file_url":"https://github.com/echo840/LIRA/blob/HEAD/omg_llava/model/lira.py","link_basis":"first_harvest_node","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":"a5eac67304f51ddd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}