{"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/llavaconfig","entry":"LlavaConfig","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":6,"n_papers_ran":4,"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":9,"n_samples_ran":6,"n_samples_fingerprinted":0,"n_places":9,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":6,"unverified":3},"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":"2603.12930","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":"18fc1382aeed437a","mcp_get_code":{"code_sha256":"18fc1382aeed437a"}},{"arxiv_id":"2503.01773","paper":"/paper/why-is-spatial-reasoning-hard-for-vlms-an","title":"Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas","date":"2025-03-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shiqichen17/adaptvis","path":"model_zoo/llava/modeling_llava_scal.py","file_url":"https://github.com/shiqichen17/adaptvis/blob/HEAD/model_zoo/llava/modeling_llava_scal.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bb877aca152f9d19","mcp_get_code":{"code_sha256":"bb877aca152f9d19"}},{"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":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e9cfb7ae423d3e3a","mcp_get_code":{"code_sha256":"e9cfb7ae423d3e3a"}},{"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":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bbd74464f100863e","mcp_get_code":{"code_sha256":"bbd74464f100863e"}},{"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":"3c8ff5cd40f90abd","mcp_get_code":{"code_sha256":"3c8ff5cd40f90abd"}},{"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":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"dbe52eb96f05b6db","mcp_get_code":{"code_sha256":"dbe52eb96f05b6db"}},{"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":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f01242335a1498b3","mcp_get_code":{"code_sha256":"f01242335a1498b3"}},{"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":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"92cb18f9e27a4e39","mcp_get_code":{"code_sha256":"92cb18f9e27a4e39"}},{"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":"d2904a880e39bfc2","mcp_get_code":{"code_sha256":"d2904a880e39bfc2"}}]}