{"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/multi-modal-instruction-tuned-llms-with-fine","title":"Multi-modal Instruction Tuned LLMs with Fine-grained Visual Perception","arxiv_id":"2403.02969","date":"2024-03-05","proceeding":"CVPR 2024 1","authors":["Junwen He","Yifan Wang","Lijun Wang","Huchuan Lu","Jun-Yan He","Jin-Peng Lan","Bin Luo","Xuansong Xie"],"abstract":"Multimodal Large Language Model (MLLMs) leverages Large Language Models as a cognitive framework for diverse visual-language tasks. Recent efforts have been made to equip MLLMs with visual perceiving and grounding capabilities. However, there still remains a gap in providing fine-grained pixel-level perceptions and extending interactions beyond text-specific inputs. In this work, we propose {\\bf{AnyRef}}, a general MLLM model that can generate pixel-wise object perceptions and natural language descriptions from multi-modality references, such as texts, boxes, images, or audio. This innovation empowers users with greater flexibility to engage with the model beyond textual and regional prompts, without modality-specific designs. Through our proposed refocusing mechanism, the generated grounding output is guided to better focus on the referenced object, implicitly incorporating additional pixel-level supervision. This simple modification utilizes attention scores generated during the inference of LLM, eliminating the need for extra computations while exhibiting performance enhancements in both grounding masks and referring expressions. With only publicly available training data, our model achieves state-of-the-art results across multiple benchmarks, including diverse modality referring segmentation and region-level referring expression generation.","url_abs":"https://arxiv.org/abs/2403.02969v2","url_pdf":"https://arxiv.org/pdf/2403.02969v2.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":"multi-modal-instruction-tuned-llms-with-fine","repo_url":"https://github.com/jwh97nn/anyref","is_official":1,"mentioned_in_paper":1,"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":"referring-expression","task_name":"Referring Expression"},{"task_slug":"referring-expression-generation","task_name":"Referring expression generation"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2403.02969","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.02969"}},"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/jwh97nn/anyref","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/jwh97nn/AnyRef","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":3,"ran_fixture":1,"unverified":3},"by_repo_kind":{"official":{"samples":7,"ran":4,"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":"a47ff1b448a12bae","entry":"dice_loss","repo":"jwh97nn/AnyRef","repo_kind":"official","path":"model/anyref.py","file_url":"https://github.com/jwh97nn/AnyRef/blob/HEAD/model/anyref.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":"a47ff1b448a12bae"}},{"code_sha256_prefix":"432c312da80537d6","entry":"get_clip_timepoints","repo":"jwh97nn/AnyRef","repo_kind":"official","path":"model/ImageBind/data.py","file_url":"https://github.com/jwh97nn/AnyRef/blob/HEAD/model/ImageBind/data.py","link_basis":"harvester_set","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":"432c312da80537d6"}},{"code_sha256_prefix":"e1e69d9ba9ffcb24","entry":"load_and_transform_vision_data","repo":"jwh97nn/AnyRef","repo_kind":"official","path":"model/ImageBind/data.py","file_url":"https://github.com/jwh97nn/AnyRef/blob/HEAD/model/ImageBind/data.py","link_basis":"harvester_set","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":"e1e69d9ba9ffcb24"}},{"code_sha256_prefix":"a9292f5d89194794","entry":"sigmoid_ce_loss","repo":"jwh97nn/AnyRef","repo_kind":"official","path":"model/anyref.py","file_url":"https://github.com/jwh97nn/AnyRef/blob/HEAD/model/anyref.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a9292f5d89194794"}},{"code_sha256_prefix":"3f50fb8374909f5f","entry":"build_sam_vit_b","repo":"jwh97nn/AnyRef","repo_kind":"official","path":"model/segment_anything/build_sam.py","file_url":"https://github.com/jwh97nn/AnyRef/blob/HEAD/model/segment_anything/build_sam.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":"3f50fb8374909f5f"}},{"code_sha256_prefix":"bf61a91555ac5280","entry":"build_sam_vit_h","repo":"jwh97nn/AnyRef","repo_kind":"official","path":"model/segment_anything/build_sam.py","file_url":"https://github.com/jwh97nn/AnyRef/blob/HEAD/model/segment_anything/build_sam.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":"bf61a91555ac5280"}},{"code_sha256_prefix":"e2ae4c696b8c968c","entry":"build_sam_vit_l","repo":"jwh97nn/AnyRef","repo_kind":"official","path":"model/segment_anything/build_sam.py","file_url":"https://github.com/jwh97nn/AnyRef/blob/HEAD/model/segment_anything/build_sam.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":"e2ae4c696b8c968c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}