{"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/llava-interactive-an-all-in-one-demo-for","title":"LLaVA-Interactive: An All-in-One Demo for Image Chat, Segmentation, Generation and Editing","arxiv_id":"2311.00571","date":"2023-11-01","proceeding":null,"authors":["Wei-Ge Chen","Irina Spiridonova","Jianwei Yang","Jianfeng Gao","Chunyuan Li"],"abstract":"LLaVA-Interactive is a research prototype for multimodal human-AI interaction. The system can have multi-turn dialogues with human users by taking multimodal user inputs and generating multimodal responses. Importantly, LLaVA-Interactive goes beyond language prompt, where visual prompt is enabled to align human intents in the interaction. The development of LLaVA-Interactive is extremely cost-efficient as the system combines three multimodal skills of pre-built AI models without additional model training: visual chat of LLaVA, image segmentation from SEEM, as well as image generation and editing from GLIGEN. A diverse set of application scenarios is presented to demonstrate the promises of LLaVA-Interactive and to inspire future research in multimodal interactive systems.","url_abs":"https://arxiv.org/abs/2311.00571v1","url_pdf":"https://arxiv.org/pdf/2311.00571v1.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":"llava-interactive-an-all-in-one-demo-for","repo_url":"https://github.com/gligen/GLIGEN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"llava-interactive-an-all-in-one-demo-for","repo_url":"https://github.com/ux-decoder/segment-everything-everywhere-all-at-once","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2311.00571","atlas_url":"https://app.syntology.ai/?focus=2311.00571","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.00571"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gligen/GLIGEN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ux-decoder/segment-everything-everywhere-all-at-once","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_fixture":2,"ran_draft_wrong":2,"ran":1,"unverified":2},"by_repo_kind":{"listed":{"samples":6,"ran":4,"repositories":2}},"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":1,"samples":[{"code_sha256_prefix":"b3e1f7172e4955ae","entry":"alpha_generator","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"b3e1f7172e4955ae"}},{"code_sha256_prefix":"a8b7b8f06a868b6f","entry":"alpha_generator","repo":"gligen/GLIGEN","repo_kind":"listed","path":"demo/gligen/task_grounded_generation.py","file_url":"https://github.com/gligen/GLIGEN/blob/HEAD/demo/gligen/task_grounded_generation.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a8b7b8f06a868b6f"}},{"code_sha256_prefix":"5a613694f83a9173","entry":"draw_box","repo":"gligen/GLIGEN","repo_kind":"listed","path":"demo/gligen/task_grounded_generation.py","file_url":"https://github.com/gligen/GLIGEN/blob/HEAD/demo/gligen/task_grounded_generation.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5a613694f83a9173"}},{"code_sha256_prefix":"e49923c3510ee0bc","entry":"project","repo":"gligen/GLIGEN","repo_kind":"listed","path":"gligen_inference.py","file_url":"https://github.com/gligen/GLIGEN/blob/HEAD/gligen_inference.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e49923c3510ee0bc"}},{"code_sha256_prefix":"e4f6733fa1ab1999","entry":"register_norm_module","repo":"ux-decoder/segment-everything-everywhere-all-at-once","repo_kind":"listed","path":"utils/model.py","file_url":"https://github.com/ux-decoder/segment-everything-everywhere-all-at-once/blob/HEAD/utils/model.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":"e4f6733fa1ab1999"}},{"code_sha256_prefix":"a21a61e41d986b6a","entry":"filter_images_with_only_crowd_annotations","repo":"ux-decoder/segment-everything-everywhere-all-at-once","repo_kind":"listed","path":"datasets/build.py","file_url":"https://github.com/ux-decoder/segment-everything-everywhere-all-at-once/blob/HEAD/datasets/build.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":"a21a61e41d986b6a"}},{"code_sha256_prefix":"eb73ad202b73f933","entry":"load_semseg","repo":"ux-decoder/segment-everything-everywhere-all-at-once","repo_kind":"listed","path":"datasets/semseg_loader.py","file_url":"https://github.com/ux-decoder/segment-everything-everywhere-all-at-once/blob/HEAD/datasets/semseg_loader.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":"eb73ad202b73f933"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}