{"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/llava-uhd-v2-an-mllm-integrating-high","title":"LLaVA-UHD v2: an MLLM Integrating High-Resolution Feature Pyramid via Hierarchical Window Transformer","arxiv_id":"2412.13871","date":"2024-12-18","proceeding":null,"authors":["YiPeng Zhang","Yifan Liu","Zonghao Guo","Yidan Zhang","Xuesong Yang","Chi Chen","Jun Song","Bo Zheng","Yuan YAO","Zhiyuan Liu","Tat-Seng Chua","Maosong Sun"],"abstract":"In multimodal large language models (MLLMs), vision transformers (ViTs) are widely employed for visual encoding. However, their performance in solving universal MLLM tasks is not satisfactory. We attribute it to a lack of information from diverse visual levels, impeding alignment with the various semantic granularity required for language generation. To address this issue, we present LLaVA-UHD v2, an advanced MLLM centered around a Hierarchical window transformer that enables capturing diverse visual granularity by constructing and integrating a high-resolution feature pyramid. As a vision-language projector, Hiwin transformer comprises two primary modules: (i) an inverse feature pyramid, constructed by a ViT-derived feature up-sampling process utilizing high-frequency details from an image pyramid, and (ii) hierarchical window attention, focusing on a set of key sampling features within cross-scale windows to condense multi-level feature maps. Extensive experiments demonstrate that LLaVA-UHD v2 achieves superior performance over existing MLLMs on popular benchmarks. Notably, our design brings an average boost of 3.7% across 14 benchmarks compared with the baseline method, 9.3% on DocVQA for instance. We make all the data, model checkpoint, and code publicly available to facilitate future research.","url_abs":"https://arxiv.org/abs/2412.13871v1","url_pdf":"https://arxiv.org/pdf/2412.13871v1.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":"llava-uhd-v2-an-mllm-integrating-high","repo_url":"https://github.com/thunlp/llava-uhd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2412.13871","atlas_url":"https://app.syntology.ai/?focus=2412.13871","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.13871"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/thunlp/llava-uhd","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":5,"ran_fixture":2,"unverified":4},"by_repo_kind":{"official":{"samples":11,"ran":7,"repositories":1}},"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":"a76fe5da7ade58fb","entry":"extract_answer","repo":"thunlp/llava-uhd","repo_kind":"official","path":"VLMEvalKit/vlmeval/vlm/llava_qwen2_uhd_v3.py","file_url":"https://github.com/thunlp/llava-uhd/blob/HEAD/VLMEvalKit/vlmeval/vlm/llava_qwen2_uhd_v3.py","link_basis":"harvester_set","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":"a76fe5da7ade58fb"}},{"code_sha256_prefix":"46ca4942d73607af","entry":"extract_choice","repo":"thunlp/llava-uhd","repo_kind":"official","path":"VLMEvalKit/vlmeval/vlm/llava_qwen2_uhd_v3.py","file_url":"https://github.com/thunlp/llava-uhd/blob/HEAD/VLMEvalKit/vlmeval/vlm/llava_qwen2_uhd_v3.py","link_basis":"harvester_set","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":"46ca4942d73607af"}},{"code_sha256_prefix":"b0a851cae92754ff","entry":"extract_patches","repo":"thunlp/llava-uhd","repo_kind":"official","path":"llava/mm_utils.py","file_url":"https://github.com/thunlp/llava-uhd/blob/HEAD/llava/mm_utils.py","link_basis":"harvester_set","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":"b0a851cae92754ff"}},{"code_sha256_prefix":"fb3f8b5f16ed11cb","entry":"extract_yes_no","repo":"thunlp/llava-uhd","repo_kind":"official","path":"VLMEvalKit/vlmeval/vlm/llava_qwen2_uhd_v3.py","file_url":"https://github.com/thunlp/llava-uhd/blob/HEAD/VLMEvalKit/vlmeval/vlm/llava_qwen2_uhd_v3.py","link_basis":"harvester_set","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":"fb3f8b5f16ed11cb"}},{"code_sha256_prefix":"77e8a3ac46f3afec","entry":"get_2d_sincos_pos_embed","repo":"thunlp/llava-uhd","repo_kind":"official","path":"llava/model/multimodal_projector/uhd_v1_resampler.py","file_url":"https://github.com/thunlp/llava-uhd/blob/HEAD/llava/model/multimodal_projector/uhd_v1_resampler.py","link_basis":"harvester_set","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":"77e8a3ac46f3afec"}},{"code_sha256_prefix":"17e90d5853a48fa7","entry":"get_abs_pos","repo":"thunlp/llava-uhd","repo_kind":"official","path":"llava/model/multimodal_projector/uhd_v1_resampler.py","file_url":"https://github.com/thunlp/llava-uhd/blob/HEAD/llava/model/multimodal_projector/uhd_v1_resampler.py","link_basis":"harvester_set","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":"17e90d5853a48fa7"}},{"code_sha256_prefix":"7606525af238fb64","entry":"unpad_image","repo":"thunlp/llava-uhd","repo_kind":"official","path":"llava/model/llava_arch.py","file_url":"https://github.com/thunlp/llava-uhd/blob/HEAD/llava/model/llava_arch.py","link_basis":"harvester_set","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":"3c8823948724e269","entry":"auto_pad_images","repo":"thunlp/llava-uhd","repo_kind":"official","path":"llava/mm_utils.py","file_url":"https://github.com/thunlp/llava-uhd/blob/HEAD/llava/mm_utils.py","link_basis":"harvester_set","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":"3c8823948724e269"}},{"code_sha256_prefix":"2884deadbb637c3e","entry":"get_2d_sincos_pos_embed_from_grid","repo":"thunlp/llava-uhd","repo_kind":"official","path":"llava/model/multimodal_projector/uhd_v1_resampler.py","file_url":"https://github.com/thunlp/llava-uhd/blob/HEAD/llava/model/multimodal_projector/uhd_v1_resampler.py","link_basis":"harvester_set","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":"2884deadbb637c3e"}},{"code_sha256_prefix":"c80358dff96c25ce","entry":"resize_and_center_crop","repo":"thunlp/llava-uhd","repo_kind":"official","path":"llava/mm_utils.py","file_url":"https://github.com/thunlp/llava-uhd/blob/HEAD/llava/mm_utils.py","link_basis":"harvester_set","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":"c80358dff96c25ce"}},{"code_sha256_prefix":"b20705b0dfd77ffc","entry":"safe_load_tokenizer","repo":"thunlp/llava-uhd","repo_kind":"official","path":"llava/conversation.py","file_url":"https://github.com/thunlp/llava-uhd/blob/HEAD/llava/conversation.py","link_basis":"harvester_set","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":"b20705b0dfd77ffc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}