{"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/llavametaforcausallm","entry":"LlavaMetaForCausalLM","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":20,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":20,"n_places_pointer_only":6,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":20},"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":"d7d5e9bc6f9033f1","mcp_get_code":{"code_sha256":"d7d5e9bc6f9033f1"}},{"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":"8bf697b4b6b3997f","mcp_get_code":{"code_sha256":"8bf697b4b6b3997f"}},{"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":"ec9a2680c81d44c8","mcp_get_code":{"code_sha256":"ec9a2680c81d44c8"}},{"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":"236fb9c779e786df","mcp_get_code":{"code_sha256":"236fb9c779e786df"}},{"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":"65e399d0eab7c33e","mcp_get_code":{"code_sha256":"65e399d0eab7c33e"}},{"arxiv_id":"2503.08481","paper":"/paper/physvlm-enabling-visual-language-models-to","title":"PhysVLM: Enabling Visual Language Models to Understand Robotic Physical Reachability","date":"2025-03-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"unira-zwj/PhysVLM","path":"physvlm-main/physvlm/model/physvlm_arch.py","file_url":"https://github.com/unira-zwj/PhysVLM/blob/HEAD/physvlm-main/physvlm/model/physvlm_arch.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2471ebd61b1a1407","mcp_get_code":{"code_sha256":"2471ebd61b1a1407"}},{"arxiv_id":"2501.06598","paper":"/paper/chartcoder-advancing-multimodal-large","title":"ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation","date":"2025-01-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thunlp/ChartCoder","path":"llava/model/llava_arch.py","file_url":"https://github.com/thunlp/ChartCoder/blob/HEAD/llava/model/llava_arch.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9fa96b93f7babf84","mcp_get_code":{"code_sha256":"9fa96b93f7babf84"}},{"arxiv_id":"2410.13085","paper":"/paper/mmed-rag-versatile-multimodal-rag-system-for","title":"MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models","date":"2024-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"richard-peng-xia/mmed-rag","path":"train/dpo/llava/model/llava_arch.py","file_url":"https://github.com/richard-peng-xia/mmed-rag/blob/HEAD/train/dpo/llava/model/llava_arch.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b9978345e2dba578","mcp_get_code":{"code_sha256":"b9978345e2dba578"}},{"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":"6106e117d2c9317b","mcp_get_code":{"code_sha256":"6106e117d2c9317b"}},{"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":"9392f432fde94da9","mcp_get_code":{"code_sha256":"9392f432fde94da9"}},{"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":"24aa7ddc724a2e74","mcp_get_code":{"code_sha256":"24aa7ddc724a2e74"}},{"arxiv_id":"2404.05052","paper":"/paper/facial-affective-behavior-analysis-with","title":"Facial Affective Behavior Analysis with Instruction Tuning","date":"2024-04-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JackYFL/EmoLA","path":"emollava/model/emollava_arch.py","file_url":"https://github.com/JackYFL/EmoLA/blob/HEAD/emollava/model/emollava_arch.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e5f1f03f03a9563a","mcp_get_code":{"code_sha256":"e5f1f03f03a9563a"}},{"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":"cb4478f3b5e0497f","mcp_get_code":{"code_sha256":"cb4478f3b5e0497f"}},{"arxiv_id":"2311.10122","paper":"/paper/video-llava-learning-united-visual-1","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","date":"2023-11-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PKU-YuanGroup/LLMBind","path":"model/llava/model/llava_arch.py","file_url":"https://github.com/PKU-YuanGroup/LLMBind/blob/HEAD/model/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":"3d9df14425d0ebcf","mcp_get_code":{"code_sha256":"3d9df14425d0ebcf"}},{"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-VL/LLaVA-NeXT","path":"llava/model/llava_arch.py","file_url":"https://github.com/LLaVA-VL/LLaVA-NeXT/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":"39343c26374462af","mcp_get_code":{"code_sha256":"39343c26374462af"}},{"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":"31bedbeb8856618e","mcp_get_code":{"code_sha256":"31bedbeb8856618e"}},{"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":"abf7b5851a13bc76","mcp_get_code":{"code_sha256":"abf7b5851a13bc76"}},{"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":"8e3647258cae7507","mcp_get_code":{"code_sha256":"8e3647258cae7507"}},{"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":"2efb2d959762f4ed","mcp_get_code":{"code_sha256":"2efb2d959762f4ed"}},{"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":"a353ac5254bcb7b3","mcp_get_code":{"code_sha256":"a353ac5254bcb7b3"}}]}