{"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/compression-with-global-guidance-towards","title":"Compression with Global Guidance: Towards Training-free High-Resolution MLLMs Acceleration","arxiv_id":"2501.05179","date":"2025-01-09","proceeding":null,"authors":["Xuyang Liu","ZiMing Wang","Yuhang Han","Yingyao Wang","Jiale Yuan","Jun Song","Bo Zheng","Linfeng Zhang","Siteng Huang","Honggang Chen"],"abstract":"Multimodal large language models (MLLMs) have attracted considerable attention due to their exceptional performance in visual content understanding and reasoning. However, their inference efficiency has been a notable concern, as the increasing length of multimodal contexts leads to quadratic complexity. Token compression techniques, which reduce the number of visual tokens, have demonstrated their effectiveness in reducing computational costs. Yet, these approaches have struggled to keep pace with the rapid advancements in MLLMs, especially the AnyRes strategy in the context of high-resolution image understanding. In this paper, we propose a novel token compression method, GlobalCom$^2$, tailored for high-resolution MLLMs that receive both the thumbnail and multiple crops. GlobalCom$^2$ treats the tokens derived from the thumbnail as the \"commander\" of the entire token compression process, directing the allocation of retention ratios and the specific compression for each crop. In this way, redundant tokens are eliminated while important local details are adaptively preserved to the highest extent feasible. Empirical results across 10 benchmarks reveal that GlobalCom$^2$ achieves an optimal balance between performance and efficiency, and consistently outperforms state-of-the-art token compression methods with LLaVA-NeXT-7B/13B models. Our code is released at https://github.com/xuyang-liu16/GlobalCom2.","url_abs":"https://arxiv.org/abs/2501.05179v2","url_pdf":"https://arxiv.org/pdf/2501.05179v2.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":"compression-with-global-guidance-towards","repo_url":"https://github.com/xuyang-liu16/globalcom2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2501.05179","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.05179"}},"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/xuyang-liu16/globalcom2","reach":null}],"summary":{"ran_honours":1,"ran_fixture":1,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":"8a8eda9c70e50257","entry":"extract_actual_dimensions","repo":"xuyang-liu16/globalcom2","repo_kind":"official","path":"llava/model/llava_arch.py","file_url":"https://github.com/xuyang-liu16/globalcom2/blob/HEAD/llava/model/llava_arch.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8a8eda9c70e50257"}},{"code_sha256_prefix":"8c0724a8b73860d8","entry":"generate_scale_for_crop_features","repo":"xuyang-liu16/globalcom2","repo_kind":"official","path":"llava/model/llava_arch.py","file_url":"https://github.com/xuyang-liu16/globalcom2/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":"8c0724a8b73860d8"}},{"code_sha256_prefix":"0348912d1b5ea5a3","entry":"get_original_indices","repo":"xuyang-liu16/globalcom2","repo_kind":"official","path":"llava/model/llava_arch.py","file_url":"https://github.com/xuyang-liu16/globalcom2/blob/HEAD/llava/model/llava_arch.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0348912d1b5ea5a3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}