{"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/visual-instruction-tuning-1","title":"Visual Instruction Tuning","arxiv_id":"2304.08485","date":"2023-04-17","proceeding":"NeurIPS 2023 11","authors":["Haotian Liu","Chunyuan Li","Qingyang Wu","Yong Jae Lee"],"abstract":"Instruction tuning large language models (LLMs) using machine-generated instruction-following data has improved zero-shot capabilities on new tasks, but the idea is less explored in the multimodal field. In this paper, we present the first attempt to use language-only GPT-4 to generate multimodal language-image instruction-following data. By instruction tuning on such generated data, we introduce LLaVA: Large Language and Vision Assistant, an end-to-end trained large multimodal model that connects a vision encoder and LLM for general-purpose visual and language understanding.Our early experiments show that LLaVA demonstrates impressive multimodel chat abilities, sometimes exhibiting the behaviors of multimodal GPT-4 on unseen images/instructions, and yields a 85.1% relative score compared with GPT-4 on a synthetic multimodal instruction-following dataset. When fine-tuned on Science QA, the synergy of LLaVA and GPT-4 achieves a new state-of-the-art accuracy of 92.53%. We make GPT-4 generated visual instruction tuning data, our model and code base publicly available.","url_abs":"https://arxiv.org/abs/2304.08485v2","url_pdf":"https://arxiv.org/pdf/2304.08485v2.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":"visual-instruction-tuning-1","repo_url":"https://github.com/haotian-liu/LLaVA","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"visual-instruction-tuning-1","repo_url":"https://github.com/llava-annonymous/llava","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"visual-instruction-tuning-1","repo_url":"https://github.com/computer-vision-in-the-wild/cvinw_readings","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"visual-instruction-tuning-1","repo_url":"https://github.com/LLaVA-VL/LLaVA-NeXT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"visual-instruction-tuning-1","repo_url":"https://github.com/ZhangYiqun018/StickerConv","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"visual-instruction-tuning-1","repo_url":"https://github.com/camenduru/llava-colab","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"visual-instruction-tuning-1","repo_url":"https://github.com/dinhvietcuong1996/icme25-inova","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"visual-instruction-tuning-1","repo_url":"https://github.com/huggingface/transformers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"visual-instruction-tuning-1","repo_url":"https://github.com/qiujihao19/artemis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"visual-instruction-tuning-1","repo_url":"https://github.com/skunkworksai/bakllava","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"visual-instruction-tuning-1","repo_url":"https://github.com/sshh12/multi_token","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"visual-instruction-tuning-1","repo_url":"https://github.com/sunsmarterjie/chatterbox","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"visual-instruction-tuning-1","repo_url":"https://github.com/tabtoyou/kollava","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"1-image-2-2-stitching","task_name":"1 Image, 2*2 Stitching"},{"task_slug":"3d-question-answering-3d-qa","task_name":"3D Question Answering (3D-QA)"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"instruction-following","task_name":"Instruction Following"},{"task_slug":"mmr-total","task_name":"MMR total"},{"task_slug":"referring-expression-comprehension","task_name":"Referring Expression Comprehension"},{"task_slug":"referring-expression-generation","task_name":"Referring expression generation"},{"task_slug":"spatial-reasoning","task_name":"Spatial Reasoning"},{"task_slug":"video-question-answering","task_name":"Video Question Answering"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-reasoning","task_name":"Visual Reasoning"},{"task_slug":"visual-instruction-following","task_name":"visual instruction following"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"base","method_name":"BASE"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-4","method_name":"GPT-4"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[{"slug":"llava-bench-in-the-wild","name":"LLaVA-Bench","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-question-answering-3d-qa-on-scanqa-test-w","task":"3D Question Answering (3D-QA)","dataset":"ScanQA Test w/ objects","model":"LL3DA","rank_in_archive_order":18,"of":18,"metrics":{"BLEU-1":"-","BLEU-4":"13.5","CIDEr":"76.8","Exact Match":"-","METEOR":"15.9","ROUGE":"37.3"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-coloninst-v1-seen","task":"Image Classification","dataset":"ColonINST-v1 (Seen)","model":"LLaVA-v1 (w/ LoRA, w/ extra data)","rank_in_archive_order":15,"of":17,"metrics":{"Accuray":"89.61"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-coloninst-v1-seen","task":"Image Classification","dataset":"ColonINST-v1 (Seen)","model":"LLaVA-v1 (w/ LoRA, w/o extra data)","rank_in_archive_order":16,"of":17,"metrics":{"Accuray":"87.86"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-coloninst-v1-unseen","task":"Image Classification","dataset":"ColonINST-v1 (Unseen)","model":"LLaVA-v1\n  (w/ LoRA, w/o extra data)","rank_in_archive_order":15,"of":17,"metrics":{"Accuray":"72.08"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-coloninst-v1-unseen","task":"Image Classification","dataset":"ColonINST-v1 (Unseen)","model":"LLaVA-v1\n  (w/ LoRA, w/ extra data)","rank_in_archive_order":17,"of":17,"metrics":{"Accuray":"42.17"},"uses_additional_data":false},{"leaderboard":"/sota/mmr-total-on-mrr-benchmark","task":"MMR total","dataset":"MRR-Benchmark","model":"LLaVA-NEXT-34B","rank_in_archive_order":4,"of":14,"metrics":{"Total Column Score":"412"},"uses_additional_data":true},{"leaderboard":"/sota/mmr-total-on-mrr-benchmark","task":"MMR total","dataset":"MRR-Benchmark","model":"LLaVA-NEXT-13B","rank_in_archive_order":8,"of":14,"metrics":{"Total Column Score":"335"},"uses_additional_data":true},{"leaderboard":"/sota/mmr-total-on-mrr-benchmark","task":"MMR total","dataset":"MRR-Benchmark","model":"LLaVA-1.5-13B","rank_in_archive_order":11,"of":14,"metrics":{"Total Column Score":"243"},"uses_additional_data":true},{"leaderboard":"/sota/referring-expression-generation-on-coloninst","task":"Referring expression generation","dataset":"ColonINST-v1 (Seen)","model":"LLaVA-v1\n  (w/ LoRA, w/ extra data)","rank_in_archive_order":16,"of":17,"metrics":{"Accuray":"86.87"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-generation-on-coloninst","task":"Referring expression generation","dataset":"ColonINST-v1 (Seen)","model":"LLaVA-v1\n  (w/ LoRA, w/o extra data)","rank_in_archive_order":17,"of":17,"metrics":{"Accuray":"84.55"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-generation-on-coloninst-1","task":"Referring expression generation","dataset":"ColonINST-v1 (Unseen)","model":"LLaVA-v1\n  (w/ LoRA, w/o extra data)","rank_in_archive_order":16,"of":17,"metrics":{"Accuray":"68.11"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-generation-on-coloninst-1","task":"Referring expression generation","dataset":"ColonINST-v1 (Unseen)","model":"LLaVA-v1\n  (w/ LoRA, w/ extra data)","rank_in_archive_order":17,"of":17,"metrics":{"Accuray":"46.85"},"uses_additional_data":false},{"leaderboard":"/sota/spatial-reasoning-on-embspatial-bench","task":"Spatial Reasoning","dataset":"EmbSpatial-Bench","model":"LLaVA-1.6","rank_in_archive_order":4,"of":5,"metrics":{"Generation":"35.19"},"uses_additional_data":false},{"leaderboard":"/sota/video-question-answering-on-mvbench","task":"Video Question Answering","dataset":"MVBench","model":"LLaVa","rank_in_archive_order":17,"of":22,"metrics":{"Avg.":"36.0"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-benchlmm","task":"Visual Question Answering","dataset":"BenchLMM","model":"LLaVA-1.5-7B","rank_in_archive_order":4,"of":10,"metrics":{"GPT-3.5 score":"46.83"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-benchlmm","task":"Visual Question Answering","dataset":"BenchLMM","model":"LLaVA-1-13B","rank_in_archive_order":7,"of":10,"metrics":{"GPT-3.5 score":"43.50"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2304.08485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.08485"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/huggingface/transformers","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/haotian-liu/LLaVA","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/llava-annonymous/llava","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ZhangYiqun018/StickerConv","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/qiujihao19/artemis","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sshh12/multi_token","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dinhvietcuong1996/icme25-inova","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sunsmarterjie/chatterbox","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/skunkworksai/bakllava","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/computer-vision-in-the-wild/cvinw_readings","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/LLaVA-VL/LLaVA-NeXT","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/camenduru/llava-colab","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tabtoyou/kollava","reach":null}],"summary":{"ran":7,"ran_draft_wrong":4,"ran_fixture":4,"ran_violates":1,"unverified":35},"by_repo_kind":{"official":{"samples":12,"ran":4,"repositories":1},"named_in_paper":{"samples":5,"ran":2,"repositories":1},"listed":{"samples":29,"ran":9,"repositories":7},"community":{"samples":5,"ran":1,"repositories":3}},"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":0,"samples":[{"code_sha256_prefix":"1707c6987676247e","entry":"IdentityMap","repo":"dinhvietcuong1996/icme25-inova","repo_kind":"listed","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","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1707c6987676247e"}},{"code_sha256_prefix":"dbe52eb96f05b6db","entry":"LlavaConfig","repo":"dinhvietcuong1996/icme25-inova","repo_kind":"listed","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","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"dbe52eb96f05b6db"}},{"code_sha256_prefix":"f01242335a1498b3","entry":"LlavaConfig","repo":"haotian-liu/LLaVA","repo_kind":"official","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","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f01242335a1498b3"}},{"code_sha256_prefix":"92cb18f9e27a4e39","entry":"LlavaConfig","repo":"llava-annonymous/llava","repo_kind":"named_in_paper","path":"llava/model/llava.py","file_url":"https://github.com/llava-annonymous/llava/blob/HEAD/llava/model/llava.py","link_basis":"first_harvest_node","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":"92cb18f9e27a4e39"}},{"code_sha256_prefix":"e6460881f1cf311c","entry":"LlavaLlamaModel","repo":"sunsmarterjie/chatterbox","repo_kind":"listed","path":"model/llava/model/llava.py","file_url":"https://github.com/sunsmarterjie/chatterbox/blob/HEAD/model/llava/model/llava.py","link_basis":"first_harvest_node","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":"e6460881f1cf311c"}},{"code_sha256_prefix":"4a7e5ec29fb79acb","entry":"SimpleResBlock","repo":"dinhvietcuong1996/icme25-inova","repo_kind":"listed","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","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4a7e5ec29fb79acb"}},{"code_sha256_prefix":"078a686c14a5d016","entry":"_MLPVectorProjector","repo":"sshh12/multi_token","repo_kind":"listed","path":"multi_token/modalities/projectors.py","file_url":"https://github.com/sshh12/multi_token/blob/HEAD/multi_token/modalities/projectors.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"078a686c14a5d016"}},{"code_sha256_prefix":"ea7ba84c548c5a33","entry":"build_vision_projector","repo":"dinhvietcuong1996/icme25-inova","repo_kind":"listed","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","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ea7ba84c548c5a33"}},{"code_sha256_prefix":"10f2142755f4bbb5","entry":"build_vision_resampler","repo":"dinhvietcuong1996/icme25-inova","repo_kind":"listed","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","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"10f2142755f4bbb5"}},{"code_sha256_prefix":"94fda0761ce0d5b9","entry":"convert_caps","repo":"llava-annonymous/llava","repo_kind":"named_in_paper","path":"llava/eval/eval_science_qa.py","file_url":"https://github.com/llava-annonymous/llava/blob/HEAD/llava/eval/eval_science_qa.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"94fda0761ce0d5b9"}},{"code_sha256_prefix":"2ff0d742a84cb8e2","entry":"get_anyres_image_grid_shape","repo":"haotian-liu/LLaVA","repo_kind":"official","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","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2ff0d742a84cb8e2"}},{"code_sha256_prefix":"a7bee88c1c7fd6a3","entry":"image_parser","repo":"ictnlp/LLaVA-Mini","repo_kind":"community","path":"llavamini/eval/run_llava_mini.py","file_url":"https://github.com/ictnlp/LLaVA-Mini/blob/HEAD/llavamini/eval/run_llava_mini.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a7bee88c1c7fd6a3"}},{"code_sha256_prefix":"08787a49ef19e0aa","entry":"should_only_save_mm_adapter","repo":"LLaVA-VL/LLaVA-NeXT","repo_kind":"listed","path":"llava/train/llava_trainer.py","file_url":"https://github.com/LLaVA-VL/LLaVA-NeXT/blob/HEAD/llava/train/llava_trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"08787a49ef19e0aa"}},{"code_sha256_prefix":"10893c4608c08075","entry":"split_to_even_chunks","repo":"haotian-liu/LLaVA","repo_kind":"official","path":"llava/train/llava_trainer.py","file_url":"https://github.com/haotian-liu/LLaVA/blob/HEAD/llava/train/llava_trainer.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"10893c4608c08075"}},{"code_sha256_prefix":"55c32993da87759b","entry":"unpad_image","repo":"haotian-liu/LLaVA","repo_kind":"official","path":"llava/model/llava_arch.py","file_url":"https://github.com/haotian-liu/LLaVA/blob/HEAD/llava/model/llava_arch.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"55c32993da87759b"}},{"code_sha256_prefix":"7606525af238fb64","entry":"unpad_image","repo":"LLaVA-VL/LLaVA-NeXT","repo_kind":"listed","path":"llava/model/llava_arch.py","file_url":"https://github.com/LLaVA-VL/LLaVA-NeXT/blob/HEAD/llava/model/llava_arch.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7606525af238fb64"}},{"code_sha256_prefix":"98e6fcd805f498d1","entry":"CLIPVisionTower","repo":"dinhvietcuong1996/icme25-inova","repo_kind":"listed","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","link_basis":"first_harvest_node","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":"98e6fcd805f498d1"}},{"code_sha256_prefix":"d7be74cc1bd52de7","entry":"CLIPVisionTowerS2","repo":"dinhvietcuong1996/icme25-inova","repo_kind":"listed","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","link_basis":"first_harvest_node","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":"d7be74cc1bd52de7"}},{"code_sha256_prefix":"5d1c9ab7042cee8d","entry":"CLIPVisionTowerS2","repo":"haotian-liu/LLaVA","repo_kind":"official","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","link_basis":"first_harvest_node","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":"5d1c9ab7042cee8d"}},{"code_sha256_prefix":"d2904a880e39bfc2","entry":"LlavaConfig","repo":"sunsmarterjie/chatterbox","repo_kind":"listed","path":"model/llava/model/llava.py","file_url":"https://github.com/sunsmarterjie/chatterbox/blob/HEAD/model/llava/model/llava.py","link_basis":"first_harvest_node","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":"d2904a880e39bfc2"}},{"code_sha256_prefix":"1717d5d0a430f17f","entry":"LlavaLlamaForCausalLM","repo":"dinhvietcuong1996/icme25-inova","repo_kind":"listed","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","link_basis":"first_harvest_node","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":"1717d5d0a430f17f"}},{"code_sha256_prefix":"44969b8364ff17f1","entry":"LlavaLlamaForCausalLM","repo":"ZhangYiqun018/StickerConv","repo_kind":"listed","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","link_basis":"first_harvest_node","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":"44969b8364ff17f1"}},{"code_sha256_prefix":"4363aef6226bb213","entry":"LlavaLlamaForCausalLM","repo":"haotian-liu/LLaVA","repo_kind":"official","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","link_basis":"first_harvest_node","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":"4363aef6226bb213"}},{"code_sha256_prefix":"7adeedb5a7dcbd7a","entry":"LlavaLlamaForCausalLM","repo":"llava-annonymous/llava","repo_kind":"named_in_paper","path":"llava/model/llava.py","file_url":"https://github.com/llava-annonymous/llava/blob/HEAD/llava/model/llava.py","link_basis":"first_harvest_node","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":"7adeedb5a7dcbd7a"}},{"code_sha256_prefix":"e589073e81d58266","entry":"LlavaLlamaForCausalLM","repo":"skunkworksai/bakllava","repo_kind":"listed","path":"llava/model/language_model/llava_llama.py","file_url":"https://github.com/skunkworksai/bakllava/blob/HEAD/llava/model/language_model/llava_llama.py","link_basis":"first_harvest_node","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":"e589073e81d58266"}},{"code_sha256_prefix":"d138a906d3799efb","entry":"LlavaLlamaForCausalLM","repo":"sunsmarterjie/chatterbox","repo_kind":"listed","path":"model/llava/model/llava.py","file_url":"https://github.com/sunsmarterjie/chatterbox/blob/HEAD/model/llava/model/llava.py","link_basis":"first_harvest_node","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":"d138a906d3799efb"}},{"code_sha256_prefix":"d70c330590b6be51","entry":"LlavaLlamaForCausalLM","repo":"tabtoyou/kollava","repo_kind":"listed","path":"llava/model/language_model/llava_llama.py","file_url":"https://github.com/tabtoyou/kollava/blob/HEAD/llava/model/language_model/llava_llama.py","link_basis":"first_harvest_node","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":"d70c330590b6be51"}},{"code_sha256_prefix":"a39a4ca102cca6cc","entry":"LlavaLlamaModel","repo":"dinhvietcuong1996/icme25-inova","repo_kind":"listed","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","link_basis":"first_harvest_node","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":"a39a4ca102cca6cc"}},{"code_sha256_prefix":"7fc60199325c39f5","entry":"LlavaLlamaModel","repo":"ZhangYiqun018/StickerConv","repo_kind":"listed","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","link_basis":"first_harvest_node","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":"7fc60199325c39f5"}},{"code_sha256_prefix":"9707b7b56a48db85","entry":"LlavaLlamaModel","repo":"haotian-liu/LLaVA","repo_kind":"official","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","link_basis":"first_harvest_node","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":"9707b7b56a48db85"}},{"code_sha256_prefix":"e992c05c75e7c542","entry":"LlavaLlamaModel","repo":"llava-annonymous/llava","repo_kind":"named_in_paper","path":"llava/model/llava.py","file_url":"https://github.com/llava-annonymous/llava/blob/HEAD/llava/model/llava.py","link_basis":"first_harvest_node","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":"e992c05c75e7c542"}},{"code_sha256_prefix":"d9cce1fb106ab082","entry":"LlavaLlamaModel","repo":"skunkworksai/bakllava","repo_kind":"listed","path":"llava/model/language_model/llava_llama.py","file_url":"https://github.com/skunkworksai/bakllava/blob/HEAD/llava/model/language_model/llava_llama.py","link_basis":"first_harvest_node","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":"d9cce1fb106ab082"}},{"code_sha256_prefix":"39343c26374462af","entry":"LlavaMetaForCausalLM","repo":"LLaVA-VL/LLaVA-NeXT","repo_kind":"listed","path":"llava/model/llava_arch.py","file_url":"https://github.com/LLaVA-VL/LLaVA-NeXT/blob/HEAD/llava/model/llava_arch.py","link_basis":"first_harvest_node","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":"39343c26374462af"}},{"code_sha256_prefix":"31bedbeb8856618e","entry":"LlavaMetaForCausalLM","repo":"dinhvietcuong1996/icme25-inova","repo_kind":"listed","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","link_basis":"first_harvest_node","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":"31bedbeb8856618e"}},{"code_sha256_prefix":"abf7b5851a13bc76","entry":"LlavaMetaForCausalLM","repo":"ZhangYiqun018/StickerConv","repo_kind":"listed","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","link_basis":"first_harvest_node","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":"abf7b5851a13bc76"}},{"code_sha256_prefix":"8e3647258cae7507","entry":"LlavaMetaForCausalLM","repo":"haotian-liu/LLaVA","repo_kind":"official","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","link_basis":"first_harvest_node","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":"8e3647258cae7507"}},{"code_sha256_prefix":"2efb2d959762f4ed","entry":"LlavaMetaForCausalLM","repo":"tabtoyou/kollava","repo_kind":"listed","path":"llava/model/language_model/llava_llama.py","file_url":"https://github.com/tabtoyou/kollava/blob/HEAD/llava/model/language_model/llava_llama.py","link_basis":"first_harvest_node","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":"2efb2d959762f4ed"}},{"code_sha256_prefix":"7732a5ae006ababd","entry":"LlavaMetaModel","repo":"dinhvietcuong1996/icme25-inova","repo_kind":"listed","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","link_basis":"first_harvest_node","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":"7732a5ae006ababd"}},{"code_sha256_prefix":"38d280bea74c1e01","entry":"LlavaMetaModel","repo":"ZhangYiqun018/StickerConv","repo_kind":"listed","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","link_basis":"first_harvest_node","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":"38d280bea74c1e01"}},{"code_sha256_prefix":"0bfdaed6a43a5263","entry":"LlavaMetaModel","repo":"haotian-liu/LLaVA","repo_kind":"official","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","link_basis":"first_harvest_node","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":"0bfdaed6a43a5263"}},{"code_sha256_prefix":"5990c8af59a1551f","entry":"LlavaMetaModel","repo":"skunkworksai/bakllava","repo_kind":"listed","path":"llava/model/language_model/llava_llama.py","file_url":"https://github.com/skunkworksai/bakllava/blob/HEAD/llava/model/language_model/llava_llama.py","link_basis":"first_harvest_node","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":"5990c8af59a1551f"}},{"code_sha256_prefix":"875ebbe8f3a0c711","entry":"build_vision_tower","repo":"dinhvietcuong1996/icme25-inova","repo_kind":"listed","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","link_basis":"first_harvest_node","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":"875ebbe8f3a0c711"}},{"code_sha256_prefix":"014050859277825c","entry":"build_vision_tower","repo":"ZhangYiqun018/StickerConv","repo_kind":"listed","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","link_basis":"first_harvest_node","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":"014050859277825c"}},{"code_sha256_prefix":"3ee345b55cc88a11","entry":"build_vision_tower","repo":"haotian-liu/LLaVA","repo_kind":"official","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","link_basis":"first_harvest_node","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":"3ee345b55cc88a11"}},{"code_sha256_prefix":"150a20daa039f495","entry":"convert_caps","repo":"LLaVA-VL/LLaVA-Plus-Codebase","repo_kind":"community","path":"llava/eval/eval_science_qa.py","file_url":"https://github.com/LLaVA-VL/LLaVA-Plus-Codebase/blob/HEAD/llava/eval/eval_science_qa.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":"OPAQUE_PARAMS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"150a20daa039f495"}},{"code_sha256_prefix":"bb35e3ac741bb2c9","entry":"get_mm_adapter_state_maybe_zero_3","repo":"haotian-liu/LLaVA","repo_kind":"official","path":"llava/train/llava_trainer.py","file_url":"https://github.com/haotian-liu/LLaVA/blob/HEAD/llava/train/llava_trainer.py","link_basis":"first_harvest_node","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":"bb35e3ac741bb2c9"}},{"code_sha256_prefix":"63959934f6d1fa06","entry":"get_pred_idx","repo":"LLaVA-VL/LLaVA-Plus-Codebase","repo_kind":"community","path":"llava/eval/eval_science_qa.py","file_url":"https://github.com/LLaVA-VL/LLaVA-Plus-Codebase/blob/HEAD/llava/eval/eval_science_qa.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"63959934f6d1fa06"}},{"code_sha256_prefix":"268b6194c5c23103","entry":"get_pred_idx","repo":"llava-annonymous/llava","repo_kind":"named_in_paper","path":"llava/eval/eval_science_qa.py","file_url":"https://github.com/llava-annonymous/llava/blob/HEAD/llava/eval/eval_science_qa.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"268b6194c5c23103"}},{"code_sha256_prefix":"735025744c1ab0cf","entry":"maybe_zero_3","repo":"haotian-liu/LLaVA","repo_kind":"official","path":"llava/train/llava_trainer.py","file_url":"https://github.com/haotian-liu/LLaVA/blob/HEAD/llava/train/llava_trainer.py","link_basis":"first_harvest_node","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":"735025744c1ab0cf"}},{"code_sha256_prefix":"e2e5c3a95a6aebb4","entry":"save_image_to_local","repo":"PKU-YuanGroup/MoE-LLaVA","repo_kind":"community","path":"moellava/serve/gradio_web_server.py","file_url":"https://github.com/PKU-YuanGroup/MoE-LLaVA/blob/HEAD/moellava/serve/gradio_web_server.py","link_basis":"first_harvest_node","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":"e2e5c3a95a6aebb4"}},{"code_sha256_prefix":"22930d58d32e2d08","entry":"save_video_to_local","repo":"PKU-YuanGroup/MoE-LLaVA","repo_kind":"community","path":"moellava/serve/gradio_web_server.py","file_url":"https://github.com/PKU-YuanGroup/MoE-LLaVA/blob/HEAD/moellava/serve/gradio_web_server.py","link_basis":"first_harvest_node","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":"22930d58d32e2d08"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}