{"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/llavallamaforcausallm","entry":"LlavaLlamaForCausalLM","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":15,"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":21,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":21,"n_places_pointer_only":6,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":21},"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":"6ea78811a0c7e746","mcp_get_code":{"code_sha256":"6ea78811a0c7e746"}},{"arxiv_id":"2603.20193","paper":"/paper/arxiv-2603-20193","title":"From Masks to Pixels and Meaning: A New Taxonomy, Benchmark, and Metrics for VLM Image Tampering","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"VILA-Lab/PIXAR","path":"model/PIXAR.py","file_url":"https://github.com/VILA-Lab/PIXAR/blob/HEAD/model/PIXAR.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3d4a28c629a82a93","mcp_get_code":{"code_sha256":"3d4a28c629a82a93"}},{"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":"c5c93160b1124542","mcp_get_code":{"code_sha256":"c5c93160b1124542"}},{"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":"8bf0e6b04d962b11","mcp_get_code":{"code_sha256":"8bf0e6b04d962b11"}},{"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":"b77d0b4e10b306e7","mcp_get_code":{"code_sha256":"b77d0b4e10b306e7"}},{"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":"f60b6c476c6273c2","mcp_get_code":{"code_sha256":"f60b6c476c6273c2"}},{"arxiv_id":"2406.20095","paper":"/paper/llara-supercharging-robot-learning-data-for","title":"LLaRA: Supercharging Robot Learning Data for Vision-Language Policy","date":"2024-06-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lostxine/llara","path":"train-llava/llava/model/language_model/llava_llama.py","file_url":"https://github.com/lostxine/llara/blob/HEAD/train-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":"e8b1d3f3b543afbc","mcp_get_code":{"code_sha256":"e8b1d3f3b543afbc"}},{"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":"846e78137649eefe","mcp_get_code":{"code_sha256":"846e78137649eefe"}},{"arxiv_id":"2406.10701","paper":"/paper/mind-multimodal-shopping-intention","title":"MIND: Multimodal Shopping Intention Distillation from Large Vision-language Models for E-commerce Purchase Understanding","date":"2024-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HKUST-KnowComp/MIND_Distillation","path":"MIND/llava/model/language_model/llava_llama.py","file_url":"https://github.com/HKUST-KnowComp/MIND_Distillation/blob/HEAD/MIND/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":"400e8396e3333966","mcp_get_code":{"code_sha256":"400e8396e3333966"}},{"arxiv_id":"2405.14974","paper":"/paper/lova3-learning-to-visual-question-answering","title":"LOVA3: Learning to Visual Question Answering, Asking and Assessment","date":"2024-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"showlab/lova3","path":"llava/model/language_model/llava_llama.py","file_url":"https://github.com/showlab/lova3/blob/HEAD/llava/model/language_model/llava_llama.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3ac2a257afa09f0c","mcp_get_code":{"code_sha256":"3ac2a257afa09f0c"}},{"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":"d0c3203cb9c25202","mcp_get_code":{"code_sha256":"d0c3203cb9c25202"}},{"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":"3ce5244608be8933","mcp_get_code":{"code_sha256":"3ce5244608be8933"}},{"arxiv_id":"2309.17102","paper":"/paper/guiding-instruction-based-image-editing-via","title":"Guiding Instruction-based Image Editing via Multimodal Large Language Models","date":"2023-09-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"apple/ml-mgie","path":"mgie_llava.py","file_url":"https://github.com/apple/ml-mgie/blob/HEAD/mgie_llava.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"22e57ed82fd754ec","mcp_get_code":{"code_sha256":"22e57ed82fd754ec"}},{"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":"1717d5d0a430f17f","mcp_get_code":{"code_sha256":"1717d5d0a430f17f"}},{"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":"44969b8364ff17f1","mcp_get_code":{"code_sha256":"44969b8364ff17f1"}},{"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":"4363aef6226bb213","mcp_get_code":{"code_sha256":"4363aef6226bb213"}},{"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":"llava-annonymous/llava","path":"llava/model/llava.py","file_url":"https://github.com/llava-annonymous/llava/blob/HEAD/llava/model/llava.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":"7adeedb5a7dcbd7a","mcp_get_code":{"code_sha256":"7adeedb5a7dcbd7a"}},{"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":"e589073e81d58266","mcp_get_code":{"code_sha256":"e589073e81d58266"}},{"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":"sunsmarterjie/chatterbox","path":"model/llava/model/llava.py","file_url":"https://github.com/sunsmarterjie/chatterbox/blob/HEAD/model/llava/model/llava.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":"d138a906d3799efb","mcp_get_code":{"code_sha256":"d138a906d3799efb"}},{"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":"tabtoyou/kollava","path":"llava/model/language_model/llava_llama.py","file_url":"https://github.com/tabtoyou/kollava/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":"d70c330590b6be51","mcp_get_code":{"code_sha256":"d70c330590b6be51"}},{"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":"e748e63d3c0105ba","mcp_get_code":{"code_sha256":"e748e63d3c0105ba"}}]}