{"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":"/code/llavametamodel","entry":"LlavaMetaModel","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":16,"n_papers_ran":0,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":19,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":19,"n_places_pointer_only":7,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":19},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2603.26008","paper":"/paper/arxiv-2603-26008","title":"FairLLaVA: Fairness-Aware Parameter-Efficient Fine-Tuning for Large Vision-Language Assistants","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"bhosalems/FairLLaVA","path":"llava/model/language_model/llava_llama.py","file_url":"https://github.com/bhosalems/FairLLaVA/blob/HEAD/llava/model/language_model/llava_llama.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"f5d8fe80c9e26fd1","mcp_get_code":{"code_sha256":"f5d8fe80c9e26fd1"}},{"arxiv_id":"2603.12930","paper":"/paper/arxiv-2603-12930","title":"Rethinking VLMs for Image Forgery Detection and Localization","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"sha0fengGuo/IFDL-VLM","path":"stage2/llava/model/language_model/llava_llama.py","file_url":"https://github.com/sha0fengGuo/IFDL-VLM/blob/HEAD/stage2/llava/model/language_model/llava_llama.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0476644b7e89c2d5","mcp_get_code":{"code_sha256":"0476644b7e89c2d5"}},{"arxiv_id":"2505.00275","paper":"/paper/adcare-vlm-leveraging-large-vision-language","title":"AdCare-VLM: Leveraging Large Vision Language Model (LVLM) to Monitor Long-Term Medication Adherence and Care","date":"2025-05-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"asad14053/AdCare-VLM","path":"videollava/model/language_model/llava_llama.py","file_url":"https://github.com/asad14053/AdCare-VLM/blob/HEAD/videollava/model/language_model/llava_llama.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e57c28d468e2fe09","mcp_get_code":{"code_sha256":"e57c28d468e2fe09"}},{"arxiv_id":"2504.07962","paper":"/paper/glus-global-local-reasoning-unified-into-a","title":"GLUS: Global-Local Reasoning Unified into A Single Large Language Model for Video Segmentation","date":"2025-04-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"GLUS-video/GLUS","path":"model/GLUS.py","file_url":"https://github.com/GLUS-video/GLUS/blob/HEAD/model/GLUS.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9fb467589b9d20f5","mcp_get_code":{"code_sha256":"9fb467589b9d20f5"}},{"arxiv_id":"2503.24164","paper":null,"title":"arXiv:2503.24164","date":null,"month_inferred_from_arxiv_id":"2025-03","title_source":null,"repo":"vlm-svla/svla","path":"llava/model/language_model/llava_qwen.py","file_url":"https://github.com/vlm-svla/svla/blob/HEAD/llava/model/language_model/llava_qwen.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"018119c8b8cf11bd","mcp_get_code":{"code_sha256":"018119c8b8cf11bd"}},{"arxiv_id":"2503.04006","paper":null,"title":"arXiv:2503.04006","date":null,"month_inferred_from_arxiv_id":"2025-03","title_source":null,"repo":"aminpdik/DSV-LFS","path":"model/DSVLFS.py","file_url":"https://github.com/aminpdik/DSV-LFS/blob/HEAD/model/DSVLFS.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ce5bf617752572ad","mcp_get_code":{"code_sha256":"ce5bf617752572ad"}},{"arxiv_id":"2501.08282","paper":"/paper/llava-st-a-multimodal-large-language-model","title":"LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal Understanding","date":"2025-01-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"appletea233/LLaVA-ST","path":"llava/model/llava_arch.py","file_url":"https://github.com/appletea233/LLaVA-ST/blob/HEAD/llava/model/llava_arch.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"a59d94054d821180","mcp_get_code":{"code_sha256":"a59d94054d821180"}},{"arxiv_id":"2410.06234","paper":"/paper/teochat-a-large-vision-language-assistant-for","title":"TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Data","date":"2024-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ermongroup/teochat","path":"videollava/model/language_model/llava_llama.py","file_url":"https://github.com/ermongroup/teochat/blob/HEAD/videollava/model/language_model/llava_llama.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"10ce3e7babead476","mcp_get_code":{"code_sha256":"10ce3e7babead476"}},{"arxiv_id":"2409.15657","paper":"/paper/mmpt-multimodal-prompt-tuning-for-zero-shot","title":"M$^2$PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning","date":"2024-09-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"william-wang618/m2pt","path":"M2PT/model/llava_archPT.py","file_url":"https://github.com/william-wang618/m2pt/blob/HEAD/M2PT/model/llava_archPT.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"959e688412f8624f","mcp_get_code":{"code_sha256":"959e688412f8624f"}},{"arxiv_id":"2406.19973","paper":"/paper/stllava-med-self-training-large-language-and","title":"STLLaVA-Med: Self-Training Large Language and Vision Assistant for Medical Question-Answering","date":"2024-06-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"heliossun/STLLaVA-Med","path":"llava/model/language_model/llava_llama.py","file_url":"https://github.com/heliossun/STLLaVA-Med/blob/HEAD/llava/model/language_model/llava_llama.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"616ce829130b1d59","mcp_get_code":{"code_sha256":"616ce829130b1d59"}},{"arxiv_id":"2406.08100","paper":"/paper/multimodal-table-understanding","title":"Multimodal Table Understanding","date":"2024-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SpursGoZmy/Table-LLaVA","path":"llava/model/llava_arch.py","file_url":"https://github.com/SpursGoZmy/Table-LLaVA/blob/HEAD/llava/model/llava_arch.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"2f7959e2c2e658be","mcp_get_code":{"code_sha256":"2f7959e2c2e658be"}},{"arxiv_id":"2404.05673","paper":"/paper/cores-orchestrating-the-dance-of-reasoning","title":"CoReS: Orchestrating the Dance of Reasoning and Segmentation","date":"2024-04-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"baoxiaoyi/cores","path":"model/CORES2seg2mask.py","file_url":"https://github.com/baoxiaoyi/cores/blob/HEAD/model/CORES2seg2mask.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9afc541c4acb0992","mcp_get_code":{"code_sha256":"9afc541c4acb0992"}},{"arxiv_id":"2403.04652","paper":"/paper/yi-open-foundation-models-by-01-ai","title":"Yi: Open Foundation Models by 01.AI","date":"2024-03-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"01-ai/yi","path":"VL/llava/model/llava_llama.py","file_url":"https://github.com/01-ai/yi/blob/HEAD/VL/llava/model/llava_llama.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f55142d84e5ac3d0","mcp_get_code":{"code_sha256":"f55142d84e5ac3d0"}},{"arxiv_id":"2402.18695","paper":"/paper/grounding-language-models-for-visual-entity","title":"Grounding Language Models for Visual Entity Recognition","date":"2024-02-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MrZilinXiao/AutoVER","path":"LLaVA/llava/model/language_model/llava_llama.py","file_url":"https://github.com/MrZilinXiao/AutoVER/blob/HEAD/LLaVA/llava/model/language_model/llava_llama.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"ee2ab77aead57d40","mcp_get_code":{"code_sha256":"ee2ab77aead57d40"}},{"arxiv_id":"2304.08485","paper":"/paper/visual-instruction-tuning-1","title":"Visual Instruction Tuning","date":"2023-04-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dinhvietcuong1996/icme25-inova","path":"llava/model/language_model/llava_llama.py","file_url":"https://github.com/dinhvietcuong1996/icme25-inova/blob/HEAD/llava/model/language_model/llava_llama.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"7732a5ae006ababd","mcp_get_code":{"code_sha256":"7732a5ae006ababd"}},{"arxiv_id":"2304.08485","paper":"/paper/visual-instruction-tuning-1","title":"Visual Instruction Tuning","date":"2023-04-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZhangYiqun018/StickerConv","path":"sticker_process/llava/model/language_model/llava_llama.py","file_url":"https://github.com/ZhangYiqun018/StickerConv/blob/HEAD/sticker_process/llava/model/language_model/llava_llama.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"38d280bea74c1e01","mcp_get_code":{"code_sha256":"38d280bea74c1e01"}},{"arxiv_id":"2304.08485","paper":"/paper/visual-instruction-tuning-1","title":"Visual Instruction Tuning","date":"2023-04-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"haotian-liu/LLaVA","path":"llava/model/language_model/llava_llama.py","file_url":"https://github.com/haotian-liu/LLaVA/blob/HEAD/llava/model/language_model/llava_llama.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"0bfdaed6a43a5263","mcp_get_code":{"code_sha256":"0bfdaed6a43a5263"}},{"arxiv_id":"2304.08485","paper":"/paper/visual-instruction-tuning-1","title":"Visual Instruction Tuning","date":"2023-04-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"skunkworksai/bakllava","path":"llava/model/language_model/llava_llama.py","file_url":"https://github.com/skunkworksai/bakllava/blob/HEAD/llava/model/language_model/llava_llama.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5990c8af59a1551f","mcp_get_code":{"code_sha256":"5990c8af59a1551f"}},{"arxiv_id":"2025.emnlp-main.609","paper":null,"title":"arXiv:2025.emnlp-main.609","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"AuroraZengfh/ModalPrompt","path":"llava/model/language_model/ModalPrompt.py","file_url":"https://github.com/AuroraZengfh/ModalPrompt/blob/HEAD/llava/model/language_model/ModalPrompt.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"17905a8fbfcc83cc","mcp_get_code":{"code_sha256":"17905a8fbfcc83cc"}}]}