{"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/sparsevlm-visual-token-sparsification-for","title":"SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference","arxiv_id":"2410.04417","date":"2024-10-06","proceeding":null,"authors":["Yuan Zhang","Chun-Kai Fan","Junpeng Ma","Wenzhao Zheng","Tao Huang","Kuan Cheng","Denis Gudovskiy","Tomoyuki Okuno","Yohei Nakata","Kurt Keutzer","Shanghang Zhang"],"abstract":"In vision-language models (VLMs), visual tokens usually consume a significant amount of computational overhead, despite their sparser information density compared to text tokens. To address this, most existing methods learn a network to prune redundant visual tokens and require additional training data. Differently, we propose an efficient training-free token optimization mechanism dubbed SparseVLM without extra parameters or fine-tuning costs. Concretely, given that visual tokens complement text tokens in VLMs for linguistic reasoning, we select visual-relevant text tokens to rate the significance of vision tokens within the self-attention matrix extracted from the VLMs. Then we progressively prune irrelevant tokens. To maximize sparsity while retaining essential information, we introduce a rank-based strategy to adaptively determine the sparsification ratio for each layer, alongside a token recycling method that compresses pruned tokens into more compact representations. Experimental results show that our SparseVLM improves the efficiency of various VLMs across a range of image and video understanding tasks. In particular, LLaVA equipped with SparseVLM reduces 61% to 67% FLOPs with a compression ratio of 78% while maintaining 93% of the accuracy. Our code is available at https://github.com/Gumpest/SparseVLMs.","url_abs":"https://arxiv.org/abs/2410.04417v2","url_pdf":"https://arxiv.org/pdf/2410.04417v2.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":"sparsevlm-visual-token-sparsification-for","repo_url":"https://github.com/gumpest/sparsevlms","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"video-understanding","task_name":"Video Understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.04417","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.04417"}},"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":"deterministic:regex_extraction","url":"https://github.com/Gumpest/SparseVLMs","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gumpest/sparsevlms","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":3,"ran":2,"ran_violates":1,"ran_honours":1,"ran_fixture":1,"unverified":2},"by_repo_kind":{"official":{"samples":10,"ran":8,"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":"20e4f665698a3d18","entry":"collate_fn","repo":"Gumpest/SparseVLMs","repo_kind":"official","path":"llava/eval/model_vqa_loader.py","file_url":"https://github.com/Gumpest/SparseVLMs/blob/HEAD/llava/eval/model_vqa_loader.py","link_basis":"harvester_set","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":"20e4f665698a3d18"}},{"code_sha256_prefix":"7e03b180fa317c9a","entry":"divide_to_patches","repo":"Gumpest/SparseVLMs","repo_kind":"official","path":"llava/mm_utils.py","file_url":"https://github.com/Gumpest/SparseVLMs/blob/HEAD/llava/mm_utils.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":"7e03b180fa317c9a"}},{"code_sha256_prefix":"42a46570620cd9fa","entry":"get_chunk","repo":"Gumpest/SparseVLMs","repo_kind":"official","path":"llava/eval/model_vqa.py","file_url":"https://github.com/Gumpest/SparseVLMs/blob/HEAD/llava/eval/model_vqa.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"42a46570620cd9fa"}},{"code_sha256_prefix":"bae18947b56f2be1","entry":"is_none","repo":"Gumpest/SparseVLMs","repo_kind":"official","path":"llava/eval/model_vqa_mmbench.py","file_url":"https://github.com/Gumpest/SparseVLMs/blob/HEAD/llava/eval/model_vqa_mmbench.py","link_basis":"harvester_set","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":"bae18947b56f2be1"}},{"code_sha256_prefix":"9b3c1cb391672ccb","entry":"load_image","repo":"Gumpest/SparseVLMs","repo_kind":"official","path":"predict.py","file_url":"https://github.com/Gumpest/SparseVLMs/blob/HEAD/predict.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"code_sha256_prefix":"468eedeba67f1b00","entry":"resize_and_pad_image","repo":"Gumpest/SparseVLMs","repo_kind":"official","path":"llava/mm_utils.py","file_url":"https://github.com/Gumpest/SparseVLMs/blob/HEAD/llava/mm_utils.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":"468eedeba67f1b00"}},{"code_sha256_prefix":"3999ff487573f32c","entry":"select_best_resolution","repo":"Gumpest/SparseVLMs","repo_kind":"official","path":"llava/mm_utils.py","file_url":"https://github.com/Gumpest/SparseVLMs/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":"3999ff487573f32c"}},{"code_sha256_prefix":"076c252c52cbb161","entry":"split_list","repo":"Gumpest/SparseVLMs","repo_kind":"official","path":"llava/eval/model_vqa.py","file_url":"https://github.com/Gumpest/SparseVLMs/blob/HEAD/llava/eval/model_vqa.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"076c252c52cbb161"}},{"code_sha256_prefix":"2a51f45ccb12aecd","entry":"attn_postprocess_topk","repo":"gumpest/sparsevlms","repo_kind":"official","path":"llava/model/language_model/score.py","file_url":"https://github.com/gumpest/sparsevlms/blob/HEAD/llava/model/language_model/score.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":"2a51f45ccb12aecd"}},{"code_sha256_prefix":"c78113f1d1fb9ba3","entry":"select_attn_head_by_sum","repo":"gumpest/sparsevlms","repo_kind":"official","path":"llava/model/language_model/score.py","file_url":"https://github.com/gumpest/sparsevlms/blob/HEAD/llava/model/language_model/score.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":"c78113f1d1fb9ba3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}