{"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/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":{"atlas_url":"https://app.syntology.ai/?focus=2311.03079","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}