{"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/adaretake-adaptive-redundancy-reduction-to","title":"AdaReTaKe: Adaptive Redundancy Reduction to Perceive Longer for Video-language Understanding","arxiv_id":"2503.12559","date":"2025-03-16","proceeding":null,"authors":["Xiao Wang","Qingyi Si","Jianlong Wu","Shiyu Zhu","Li Cao","Liqiang Nie"],"abstract":"Multimodal Large Language Models (MLLMs) have revolutionized video understanding, yet are still limited by context length when processing long videos. Recent methods compress videos by leveraging visual redundancy uniformly, yielding promising results. Nevertheless, our quantitative analysis shows that redundancy varies significantly across time and model layers, necessitating a more flexible compression strategy. We propose AdaReTaKe, a training-free method that flexibly reduces visual redundancy by allocating compression ratios among time and layers with theoretical guarantees. Integrated into state-of-the-art MLLMs, AdaReTaKe improves processing capacity from 256 to 2048 frames while preserving critical information. Experiments on VideoMME, MLVU, LongVideoBench, and LVBench datasets demonstrate that AdaReTaKe outperforms existing methods by 2.3% and 2.8% for 7B and 72B models, respectively, with even greater improvements of 5.9% and 6.0% on the longest LVBench. Our code is available at https://github.com/SCZwangxiao/video-FlexReduc.git.","url_abs":"https://arxiv.org/abs/2503.12559v2","url_pdf":"https://arxiv.org/pdf/2503.12559v2.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":"adaretake-adaptive-redundancy-reduction-to","repo_url":"https://github.com/sczwangxiao/video-flexreduc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"video-understanding","task_name":"Video Understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2503.12559","atlas_url":"https://app.syntology.ai/?focus=2503.12559","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.12559"}},"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/sczwangxiao/video-flexreduc","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1,"ran":15,"ran_draft_wrong":1,"unverified":6},"by_repo_kind":{"official":{"samples":23,"ran":17,"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":"3c76e52815c5401d","entry":"repeat_kv","repo":"sczwangxiao/video-flexreduc","repo_kind":"official","path":"retake/longvideo_cache.py","file_url":"https://github.com/sczwangxiao/video-flexreduc/blob/HEAD/retake/longvideo_cache.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3c76e52815c5401d"}},{"code_sha256_prefix":"81664204c8525de9","entry":"evaluate_mlvu_generation","repo":"sczwangxiao/video-flexreduc","repo_kind":"official","path":"retake/dataset_utils.py","file_url":"https://github.com/sczwangxiao/video-flexreduc/blob/HEAD/retake/dataset_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"81664204c8525de9"}},{"code_sha256_prefix":"e1e87b90e35fb630","entry":"gather_results","repo":"sczwangxiao/video-flexreduc","repo_kind":"official","path":"retake/infer_eval.py","file_url":"https://github.com/sczwangxiao/video-flexreduc/blob/HEAD/retake/infer_eval.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e1e87b90e35fb630"}},{"code_sha256_prefix":"d37f4e5bd2ad847b","entry":"load_yaml","repo":"sczwangxiao/video-flexreduc","repo_kind":"official","path":"retake/infer_eval.py","file_url":"https://github.com/sczwangxiao/video-flexreduc/blob/HEAD/retake/infer_eval.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d37f4e5bd2ad847b"}},{"code_sha256_prefix":"6ad69145ddabafe5","entry":"memory_bank_compress_MALLM","repo":"sczwangxiao/video-flexreduc","repo_kind":"official","path":"retake/visual_compression.py","file_url":"https://github.com/sczwangxiao/video-flexreduc/blob/HEAD/retake/visual_compression.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6ad69145ddabafe5"}},{"code_sha256_prefix":"5f9f5bd51036cfc1","entry":"memory_bank_compress_MALLM_hard","repo":"sczwangxiao/video-flexreduc","repo_kind":"official","path":"retake/visual_compression.py","file_url":"https://github.com/sczwangxiao/video-flexreduc/blob/HEAD/retake/visual_compression.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5f9f5bd51036cfc1"}},{"code_sha256_prefix":"0366d231d1eb184f","entry":"memory_bank_compress_keyframe","repo":"sczwangxiao/video-flexreduc","repo_kind":"official","path":"retake/visual_compression.py","file_url":"https://github.com/sczwangxiao/video-flexreduc/blob/HEAD/retake/visual_compression.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0366d231d1eb184f"}},{"code_sha256_prefix":"a83c7315b78d5c2c","entry":"patch_llava_onevision_config","repo":"sczwangxiao/video-flexreduc","repo_kind":"official","path":"retake/monkeypatch.py","file_url":"https://github.com/sczwangxiao/video-flexreduc/blob/HEAD/retake/monkeypatch.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a83c7315b78d5c2c"}},{"code_sha256_prefix":"d7609a472ef2dd0d","entry":"patch_qwen2_5_vl_config","repo":"sczwangxiao/video-flexreduc","repo_kind":"official","path":"retake/monkeypatch.py","file_url":"https://github.com/sczwangxiao/video-flexreduc/blob/HEAD/retake/monkeypatch.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d7609a472ef2dd0d"}},{"code_sha256_prefix":"8601a846757deb14","entry":"patch_qwen2vl_config","repo":"sczwangxiao/video-flexreduc","repo_kind":"official","path":"retake/monkeypatch.py","file_url":"https://github.com/sczwangxiao/video-flexreduc/blob/HEAD/retake/monkeypatch.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8601a846757deb14"}},{"code_sha256_prefix":"8a68c201ee613f88","entry":"retake_LlavaOnevisionForConditionalGeneration_get_chunk_size","repo":"sczwangxiao/video-flexreduc","repo_kind":"official","path":"retake/llava_onevision.py","file_url":"https://github.com/sczwangxiao/video-flexreduc/blob/HEAD/retake/llava_onevision.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8a68c201ee613f88"}},{"code_sha256_prefix":"7ddc25ea1dac67d2","entry":"retake_LlavaOnevisionForConditionalGeneration_segment_input_ids","repo":"sczwangxiao/video-flexreduc","repo_kind":"official","path":"retake/llava_onevision.py","file_url":"https://github.com/sczwangxiao/video-flexreduc/blob/HEAD/retake/llava_onevision.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7ddc25ea1dac67d2"}},{"code_sha256_prefix":"eab30ba8c4d44a11","entry":"retake_Qwen2VLForConditionalGeneration_segment_input_ids","repo":"sczwangxiao/video-flexreduc","repo_kind":"official","path":"retake/qwen2_vl.py","file_url":"https://github.com/sczwangxiao/video-flexreduc/blob/HEAD/retake/qwen2_vl.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eab30ba8c4d44a11"}},{"code_sha256_prefix":"e5124ec09df7329d","entry":"retake_Qwen2_5_VLForConditionalGeneration_get_chunk_size","repo":"sczwangxiao/video-flexreduc","repo_kind":"official","path":"retake/qwen2_5_vl.py","file_url":"https://github.com/sczwangxiao/video-flexreduc/blob/HEAD/retake/qwen2_5_vl.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e5124ec09df7329d"}},{"code_sha256_prefix":"676b41a7d2ba0916","entry":"retake_Qwen2_5_VLForConditionalGeneration_segment_input_ids","repo":"sczwangxiao/video-flexreduc","repo_kind":"official","path":"retake/qwen2_5_vl.py","file_url":"https://github.com/sczwangxiao/video-flexreduc/blob/HEAD/retake/qwen2_5_vl.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"676b41a7d2ba0916"}},{"code_sha256_prefix":"e03d53ba9d4f9ae5","entry":"rotate_half","repo":"sczwangxiao/video-flexreduc","repo_kind":"official","path":"retake/longvideo_cache.py","file_url":"https://github.com/sczwangxiao/video-flexreduc/blob/HEAD/retake/longvideo_cache.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e03d53ba9d4f9ae5"}},{"code_sha256_prefix":"2a31a1d556220646","entry":"trimm_results","repo":"sczwangxiao/video-flexreduc","repo_kind":"official","path":"retake/infer_eval.py","file_url":"https://github.com/sczwangxiao/video-flexreduc/blob/HEAD/retake/infer_eval.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2a31a1d556220646"}},{"code_sha256_prefix":"8971bec8b941516b","entry":"apply_multimodal_rotary_pos_emb","repo":"sczwangxiao/video-flexreduc","repo_kind":"official","path":"retake/longvideo_cache.py","file_url":"https://github.com/sczwangxiao/video-flexreduc/blob/HEAD/retake/longvideo_cache.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8971bec8b941516b"}},{"code_sha256_prefix":"1c4242b450f2a4ac","entry":"eval_mlvu_results","repo":"sczwangxiao/video-flexreduc","repo_kind":"official","path":"retake/dataset_utils.py","file_url":"https://github.com/sczwangxiao/video-flexreduc/blob/HEAD/retake/dataset_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1c4242b450f2a4ac"}},{"code_sha256_prefix":"feee0c01f58c3b2e","entry":"eval_videomme_results","repo":"sczwangxiao/video-flexreduc","repo_kind":"official","path":"retake/dataset_utils.py","file_url":"https://github.com/sczwangxiao/video-flexreduc/blob/HEAD/retake/dataset_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"feee0c01f58c3b2e"}},{"code_sha256_prefix":"b9e6d7a085769799","entry":"retake_Qwen2VLAttention_forward","repo":"sczwangxiao/video-flexreduc","repo_kind":"official","path":"retake/qwen2_vl.py","file_url":"https://github.com/sczwangxiao/video-flexreduc/blob/HEAD/retake/qwen2_vl.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b9e6d7a085769799"}},{"code_sha256_prefix":"508f605be1850961","entry":"retake_Qwen2VLForConditionalGeneration_compress_video_tokens","repo":"sczwangxiao/video-flexreduc","repo_kind":"official","path":"retake/qwen2_vl.py","file_url":"https://github.com/sczwangxiao/video-flexreduc/blob/HEAD/retake/qwen2_vl.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"508f605be1850961"}},{"code_sha256_prefix":"8104fe56ba8a1b10","entry":"retake_Qwen2_5_VLAttention_forward","repo":"sczwangxiao/video-flexreduc","repo_kind":"official","path":"retake/qwen2_5_vl.py","file_url":"https://github.com/sczwangxiao/video-flexreduc/blob/HEAD/retake/qwen2_5_vl.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8104fe56ba8a1b10"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}