{"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/deepstack-deeply-stacking-visual-tokens-is","title":"DeepStack: Deeply Stacking Visual Tokens is Surprisingly Simple and Effective for LMMs","arxiv_id":"2406.04334","date":"2024-06-06","proceeding":null,"authors":["Lingchen Meng","Jianwei Yang","Rui Tian","Xiyang Dai","Zuxuan Wu","Jianfeng Gao","Yu-Gang Jiang"],"abstract":"Most large multimodal models (LMMs) are implemented by feeding visual tokens as a sequence into the first layer of a large language model (LLM). The resulting architecture is simple but significantly increases computation and memory costs, as it has to handle a large number of additional tokens in its input layer. This paper presents a new architecture DeepStack for LMMs. Considering $N$ layers in the language and vision transformer of LMMs, we stack the visual tokens into $N$ groups and feed each group to its aligned transformer layer \\textit{from bottom to top}. Surprisingly, this simple method greatly enhances the power of LMMs to model interactions among visual tokens across layers but with minimal additional cost. We apply DeepStack to both language and vision transformer in LMMs, and validate the effectiveness of DeepStack LMMs with extensive empirical results. Using the same context length, our DeepStack 7B and 13B parameters surpass their counterparts by \\textbf{2.7} and \\textbf{2.9} on average across \\textbf{9} benchmarks, respectively. Using only one-fifth of the context length, DeepStack rivals closely to the counterparts that use the full context length. These gains are particularly pronounced on high-resolution tasks, e.g., \\textbf{4.2}, \\textbf{11.0}, and \\textbf{4.0} improvements on TextVQA, DocVQA, and InfoVQA compared to LLaVA-1.5-7B, respectively. We further apply DeepStack to vision transformer layers, which brings us a similar amount of improvements, \\textbf{3.8} on average compared with LLaVA-1.5-7B.","url_abs":"https://arxiv.org/abs/2406.04334v1","url_pdf":"https://arxiv.org/pdf/2406.04334v1.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":[],"tasks":[{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":null,"task_name":"TextVQA"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"zeroshot-video-question-answer","task_name":"Zero-Shot Video Question Answer"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-question-answering-on-mm-vet","task":"Visual Question Answering","dataset":"MM-Vet","model":"DeepStack-L-HD (Vicuna-13B)","rank_in_archive_order":119,"of":231,"metrics":{"GPT-4 score":"39.3"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-video-question-answer-on-next-qa","task":"Zero-Shot Video Question Answer","dataset":"NExT-QA","model":"DeepStack-L(7B)","rank_in_archive_order":21,"of":27,"metrics":{"Accuracy":"61.0"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2406.04334","atlas_url":"https://app.syntology.ai/?focus=2406.04334","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2406.04334"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2406.04334\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2406.04334"},"call":"get_concepts_for_paper(arxiv_id=\"2406.04334\")"}],"by_repo":[],"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"},"code_links_note":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"1f2cd608993ef15bf1c30a02903bbecb5724a51f0b8e63e3ab0ed2790dc662eb","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}