{"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/cogvlm-visual-expert-for-pretrained-language","title":"CogVLM: Visual Expert for Pretrained Language Models","arxiv_id":"2311.03079","date":"2023-11-06","proceeding":null,"authors":["Weihan Wang","Qingsong Lv","Wenmeng Yu","Wenyi Hong","Ji Qi","Yan Wang","Junhui Ji","Zhuoyi Yang","Lei Zhao","Xixuan Song","Jiazheng Xu","Bin Xu","Juanzi Li","Yuxiao Dong","Ming Ding","Jie Tang"],"abstract":"We introduce CogVLM, a powerful open-source visual language foundation model. Different from the popular shallow alignment method which maps image features into the input space of language model, CogVLM bridges the gap between the frozen pretrained language model and image encoder by a trainable visual expert module in the attention and FFN layers. As a result, CogVLM enables deep fusion of vision language features without sacrificing any performance on NLP tasks. CogVLM-17B achieves state-of-the-art performance on 10 classic cross-modal benchmarks, including NoCaps, Flicker30k captioning, RefCOCO, RefCOCO+, RefCOCOg, Visual7W, GQA, ScienceQA, VizWiz VQA and TDIUC, and ranks the 2nd on VQAv2, OKVQA, TextVQA, COCO captioning, etc., surpassing or matching PaLI-X 55B. Codes and checkpoints are available at https://github.com/THUDM/CogVLM.","url_abs":"https://arxiv.org/abs/2311.03079v2","url_pdf":"https://arxiv.org/pdf/2311.03079v2.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":"cogvlm-visual-expert-for-pretrained-language","repo_url":"https://github.com/thudm/cogvlm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"cogvlm-visual-expert-for-pretrained-language","repo_url":"https://github.com/THUDM/CogAgent","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"cogvlm-visual-expert-for-pretrained-language","repo_url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/cogvlm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"cogvlm-visual-expert-for-pretrained-language","repo_url":"https://github.com/MS-P3/code5/tree/main/cogvlm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"1-image-2-2-stitching","task_name":"1 Image, 2*2 Stitching"},{"task_slug":"fs-mevqa","task_name":"FS-MEVQA"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"long-context-understanding","task_name":"Long-Context Understanding"},{"task_slug":null,"task_name":"TextVQA"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/fs-mevqa-on-sme","task":"FS-MEVQA","dataset":"SME","model":"GLM-4V","rank_in_archive_order":5,"of":7,"metrics":{"#Learning Samples (N)":"16","ACC":"34.23","BLEU-4":"14.45","CIDEr":"127.37","Detection":"0.89","METEOR":"17.53","ROUGE-L":"24.28","SPICE":"17.70"},"uses_additional_data":false},{"leaderboard":"/sota/long-context-understanding-on-mmneedle","task":"Long-Context Understanding","dataset":"MMNeedle","model":"CogVLM2-Llama-3","rank_in_archive_order":9,"of":12,"metrics":{"1 Image, 2*2 Stitching, Exact Accuracy":"7.3","1 Image, 4*4 Stitching, Exact Accuracy":"0.9","1 Image, 8*8 Stitching, Exact Accuracy":"0.1","10 Images, 1*1 Stitching, Exact Accuracy":"0","10 Images, 2*2 Stitching, Exact Accuracy":"0","10 Images, 4*4 Stitching, Exact Accuracy":"0","10 Images, 8*8 Stitching, Exact Accuracy":"0"},"uses_additional_data":false},{"leaderboard":"/sota/long-context-understanding-on-mmneedle","task":"Long-Context Understanding","dataset":"MMNeedle","model":"CogVLM-17B","rank_in_archive_order":11,"of":12,"metrics":{"1 Image, 2*2 Stitching, Exact Accuracy":"0","1 Image, 4*4 Stitching, Exact Accuracy":"0.1","1 Image, 8*8 Stitching, Exact Accuracy":"0.3","10 Images, 1*1 Stitching, Exact Accuracy":"0","10 Images, 2*2 Stitching, Exact Accuracy":"0","10 Images, 4*4 Stitching, Exact Accuracy":"0","10 Images, 8*8 Stitching, Exact Accuracy":"0"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-mm-vet","task":"Visual Question Answering","dataset":"MM-Vet","model":"GLM4 Vision","rank_in_archive_order":25,"of":231,"metrics":{"GPT-4 score":"63.9"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-mm-vet","task":"Visual Question Answering","dataset":"MM-Vet","model":"CogVLM(Vicuna-7B)","rank_in_archive_order":51,"of":231,"metrics":{"GPT-4 score":"52.8","Params":"17B"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-mm-vet-v2","task":"Visual Question Answering","dataset":"MM-Vet v2","model":"CogVLM-Chat","rank_in_archive_order":17,"of":24,"metrics":{"GPT-4 score":"45.1±0.2"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-vqa-on-core-mm","task":"Visual Question Answering (VQA)","dataset":"InfiMM-Eval","model":"CogVLM-Chat","rank_in_archive_order":4,"of":14,"metrics":{"Abductive":"47.88","Analogical":"28.75","Deductive":"36.75","Overall score":"37.16","Params":"17B"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2311.03079","atlas_url":"https://app.syntology.ai/?focus=2311.03079","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":"2311.03079"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2311.03079\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2311.03079"},"call":"get_concepts_for_paper(arxiv_id=\"2311.03079\")"}],"by_repo":[{"repo":"thudm/cogvlm","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":2,"harvested_for":["2312.08914","Hong_CogAgent_A_Visual_Language_Model_for_GUI_Agents_CVPR_2024_paper"],"harvested_for_calls":[{"arxiv_id":"2312.08914","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2312.08914"},"call":"get_harvested_code_for_paper(arxiv_id=\"2312.08914\")"}]},{"repo":"THUDM/CogAgent","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2312.08914"],"harvested_for_calls":[{"arxiv_id":"2312.08914","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2312.08914"},"call":"get_harvested_code_for_paper(arxiv_id=\"2312.08914\")"}]},{"repo":"2024-MindSpore-1/Code2","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"MS-P3/code5","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2405.18386"],"harvested_for_calls":[{"arxiv_id":"2405.18386","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2405.18386"},"call":"get_harvested_code_for_paper(arxiv_id=\"2405.18386\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"25525f55e0d72fd1b7b9af2a4606eb8e15379c33c58653e0ef5b7d2eb597f951","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}