{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/a-stitch-in-time-saves-nine-small-vlm-is-a","title":"A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs","arxiv_id":"2412.03324","date":"2024-12-04","proceeding":"CVPR 2025 1","authors":["Wangbo Zhao","Yizeng Han","Jiasheng Tang","Zhikai Li","Yibing Song","Kai Wang","Zhangyang Wang","Yang You"],"abstract":"Vision-language models (VLMs) have shown remarkable success across various multi-modal tasks, yet large VLMs encounter significant efficiency challenges due to processing numerous visual tokens. A promising approach to accelerating large VLM inference is using partial information, such as attention maps from specific layers, to assess token importance and prune less essential tokens. However, our study reveals three key insights: (i) Partial attention information is insufficient for accurately identifying critical visual tokens, resulting in suboptimal performance, especially at low token retention ratios; (ii) Global attention information, such as the attention map aggregated across all layers, more effectively preserves essential tokens and maintains comparable performance under aggressive pruning. However, the attention maps from all layers requires a full inference pass, which increases computational load and is therefore impractical in existing methods; and (iii) The global attention map aggregated from a small VLM closely resembles that of a large VLM, suggesting an efficient alternative. Based on these findings, we introduce a \\textbf{training-free} method, \\underline{\\textbf{S}}mall VLM \\underline{\\textbf{G}}uidance for accelerating \\underline{\\textbf{L}}arge VLMs (\\textbf{SGL}). Specifically, we employ the attention map aggregated from a small VLM to guide visual token pruning in a large VLM. Additionally, an early exiting mechanism is developed to fully use the small VLM's predictions, dynamically invoking the larger VLM only when necessary, yielding a superior trade-off between accuracy and computation. Extensive evaluations across 11 benchmarks demonstrate the effectiveness and generalizability of SGL, achieving up to 91\\% pruning ratio for visual tokens while retaining competitive performance.","url_abs":"https://arxiv.org/abs/2412.03324v2","url_pdf":"https://arxiv.org/pdf/2412.03324v2.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":"a-stitch-in-time-saves-nine-small-vlm-is-a","repo_url":"https://github.com/NUS-HPC-AI-Lab/SGL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":null}],"tasks":[{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"early-exiting","method_name":"Early exiting"},{"method_slug":"pruning","method_name":"Pruning"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-question-answering-on-mm-vet","task":"Visual Question Answering","dataset":"MM-Vet","model":"InternVL2-26B (SGP, token ratio 64%)","rank_in_archive_order":19,"of":231,"metrics":{"GPT-4 score":"65.60","Params":"26B"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-mm-vet","task":"Visual Question Answering","dataset":"MM-Vet","model":"InternVL2-26B (SGP, token ratio 35%)","rank_in_archive_order":28,"of":231,"metrics":{"GPT-4 score":"63.20","Params":"26B"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-mm-vet","task":"Visual Question Answering","dataset":"MM-Vet","model":"InternVL2-26B (SGP, token ratio 9%)","rank_in_archive_order":54,"of":231,"metrics":{"GPT-4 score":"52.10","Params":"26B"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2412.03324","atlas_url":"https://app.syntology.ai/?focus=2412.03324","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.03324"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2412.03324"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2412.03324"},"call":"get_harvested_code_for_paper(arxiv_id=\"2412.03324\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2412.03324"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2412.03324\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2412.03324"},"call":"get_concepts_for_paper(arxiv_id=\"2412.03324\")"}],"by_repo":[{"repo":"NUS-HPC-AI-Lab/SGL","kind":"official","samples":1,"ran":0,"instrument":0,"unverified":1}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2412.03324.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2412.03324.svg"},"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/NUS-HPC-AI-Lab/SGL","reach":null}],"summary":{"ran_violates":2,"ran_honours":2,"unverified":1},"n_samples":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":1,"ran":0,"n_ran_checked":0,"n_instrument":0,"repositories":1},"unlocated":{"samples":4,"ran":4,"n_ran_checked":4,"n_instrument":0,"repositories":0,"is":"identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded"}},"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":5,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":0,"n_ran_without_level_date":4,"n_ran_signature_not_shown":0,"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"5f3bdd5f3304a0e0","code_sha256_prefix":"5f3bdd5f3304a0e0","entry":"version_cmp","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_violates","verification_level":2,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"v1:str/0/str, v2:str/0/str, op:str/0/str","fixture_out_type":"bool","code_page":"/code/version-cmp","census":null,"licence":null,"inline_ok":false,"inline_ok_link":false,"withheld_clause":"this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it","mcp_get_code":{"code_sha256":"5f3bdd5f3304a0e0"}},{"code_sha256":"e159a001bd4cbfaa","code_sha256_prefix":"e159a001bd4cbfaa","entry":"evaluate_exact_match_accuracy","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"signature":"entries:list/1/dict","fixture_out_type":"float","code_page":"/code/evaluate-exact-match-accuracy","census":null,"licence":null,"inline_ok":false,"inline_ok_link":false,"withheld_clause":"this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it","mcp_get_code":{"code_sha256":"e159a001bd4cbfaa"}},{"code_sha256":"4ffcad52354b4806","code_sha256_prefix":"4ffcad52354b4806","entry":"evaluate_relaxed_accuracy","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"signature":"entries:list/1/dict","fixture_out_type":"float","code_page":"/code/evaluate-relaxed-accuracy","census":null,"licence":null,"inline_ok":false,"inline_ok_link":false,"withheld_clause":"this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it","mcp_get_code":{"code_sha256":"4ffcad52354b4806"}},{"code_sha256":"b3c8680ebd8739af","code_sha256_prefix":"b3c8680ebd8739af","entry":"relaxed_correctness","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"target:str/0/str, prediction:str/0/str, max_relative_change:float/0/float","fixture_out_type":"bool","code_page":"/code/relaxed-correctness","census":null,"licence":null,"inline_ok":false,"inline_ok_link":false,"withheld_clause":"this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it","mcp_get_code":{"code_sha256":"b3c8680ebd8739af"}},{"code_sha256":"88a4b26411ded833","code_sha256_prefix":"88a4b26411ded833","entry":"get_attention_rank","repo":"NUS-HPC-AI-Lab/SGL","repo_kind":"official","path":"internvl/model/internvl_chat/modeling_internvl_chat.py","file_url":"https://github.com/NUS-HPC-AI-Lab/SGL/blob/HEAD/internvl/model/internvl_chat/modeling_internvl_chat.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, NUS-HPC-AI-Lab/SGL when it was checked","mcp_get_code":{"code_sha256":"88a4b26411ded833"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"3e2be10282c2c82892a2a677f2cebafbe995c3efd3eeca1df447e238129d3025","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}