{"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/internvl-scaling-up-vision-foundation-models","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","arxiv_id":"2312.14238","date":"2023-12-21","proceeding":"CVPR 2024 1","authors":["Zhe Chen","Jiannan Wu","Wenhai Wang","Weijie Su","Guo Chen","Sen Xing","Muyan Zhong","Qinglong Zhang","Xizhou Zhu","Lewei Lu","Bin Li","Ping Luo","Tong Lu","Yu Qiao","Jifeng Dai"],"abstract":"The exponential growth of large language models (LLMs) has opened up numerous possibilities for multimodal AGI systems. However, the progress in vision and vision-language foundation models, which are also critical elements of multi-modal AGI, has not kept pace with LLMs. In this work, we design a large-scale vision-language foundation model (InternVL), which scales up the vision foundation model to 6 billion parameters and progressively aligns it with the LLM, using web-scale image-text data from various sources. This model can be broadly applied to and achieve state-of-the-art performance on 32 generic visual-linguistic benchmarks including visual perception tasks such as image-level or pixel-level recognition, vision-language tasks such as zero-shot image/video classification, zero-shot image/video-text retrieval, and link with LLMs to create multi-modal dialogue systems. It has powerful visual capabilities and can be a good alternative to the ViT-22B. We hope that our research could contribute to the development of multi-modal large models. Code and models are available at https://github.com/OpenGVLab/InternVL.","url_abs":"https://arxiv.org/abs/2312.14238v3","url_pdf":"https://arxiv.org/pdf/2312.14238v3.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":"internvl-scaling-up-vision-foundation-models","repo_url":"https://github.com/opengvlab/internvl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"internvl-scaling-up-vision-foundation-models","repo_url":"https://github.com/opengvlab/internvl-mmdetseg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"image-to-text-retrieval","task_name":"Image-to-Text Retrieval"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"mmr-total","task_name":"MMR total"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"text-retrieval","task_name":"Text Retrieval"},{"task_slug":"video-classification","task_name":"Video Classification"},{"task_slug":"video-text-retrieval","task_name":"Video-Text Retrieval"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"},{"task_slug":"zero-shot-cross-modal-retrieval","task_name":"Zero-Shot Cross-Modal Retrieval"},{"task_slug":"zero-shot-transfer-image-classification","task_name":"Zero-Shot Transfer Image Classification"},{"task_slug":"zero-shot-video-retrieval","task_name":"Zero-Shot Video Retrieval"},{"task_slug":"zero-shot-image-retrieval","task_name":"Zero-shot Image Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-retrieval-on-flickr30k-cn","task":"Image Retrieval","dataset":"Flickr30k-CN","model":"InternVL-G-FT","rank_in_archive_order":1,"of":11,"metrics":{"R@1":"85.9","R@10":"97.1","R@5":"98.7"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-flickr30k-cn","task":"Image Retrieval","dataset":"Flickr30k-CN","model":"InternVL-C-FT","rank_in_archive_order":2,"of":11,"metrics":{"R@1":"85.2","R@10":"97.0","R@5":"98.5"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-text-retrieval-on-flickr30k","task":"Image-to-Text Retrieval","dataset":"Flickr30k","model":"InternVL-G-FT (finetuned, w/o ranking)","rank_in_archive_order":1,"of":11,"metrics":{"Recall@1":"97.9","Recall@10":"100","Recall@5":"100"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-text-retrieval-on-flickr30k","task":"Image-to-Text Retrieval","dataset":"Flickr30k","model":"InternVL-C-FT (finetuned, w/o ranking)","rank_in_archive_order":4,"of":11,"metrics":{"Recall@1":"97.2","Recall@10":"100","Recall@5":"100"},"uses_additional_data":false},{"leaderboard":"/sota/mmr-total-on-mrr-benchmark","task":"MMR total","dataset":"MRR-Benchmark","model":"InternVL2-8B","rank_in_archive_order":6,"of":14,"metrics":{"Total Column Score":"368"},"uses_additional_data":true},{"leaderboard":"/sota/mmr-total-on-mrr-benchmark","task":"MMR total","dataset":"MRR-Benchmark","model":"InternVL2-1B","rank_in_archive_order":12,"of":14,"metrics":{"Total Column Score":"237"},"uses_additional_data":true},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-dev","task":"Visual Question Answering (VQA)","dataset":"VQA v2 test-dev","model":"InternVL-C","rank_in_archive_order":10,"of":56,"metrics":{"Accuracy":"81.2"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-cross-modal-retrieval-on-coco-2014","task":"Zero-Shot Cross-Modal Retrieval","dataset":"COCO 2014","model":"InternVL-G","rank_in_archive_order":1,"of":18,"metrics":{"Image-to-text R@1":"74.9","Image-to-text R@10":"95.2","Image-to-text R@5":"91.3","Text-to-image R@1":"58.6","Text-to-image R@10":"88.0","Text-to-image R@5":"81.3"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-cross-modal-retrieval-on-coco-2014","task":"Zero-Shot Cross-Modal Retrieval","dataset":"COCO 2014","model":"InternVL-C","rank_in_archive_order":4,"of":18,"metrics":{"Image-to-text R@1":"70.6","Image-to-text R@10":"93.5","Image-to-text R@5":"89.0","Text-to-image R@1":"54.1","Text-to-image R@10":"84.6","Text-to-image R@5":"77.3"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-cross-modal-retrieval-on-flickr30k","task":"Zero-Shot Cross-Modal Retrieval","dataset":"Flickr30k","model":"InternVL-G","rank_in_archive_order":1,"of":22,"metrics":{"Image-to-text R@1":"95.7","Image-to-text R@10":"99.9","Image-to-text R@5":"99.7","Text-to-image R@1":"85.0","Text-to-image R@10":"98.6","Text-to-image R@5":"97.0"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-cross-modal-retrieval-on-flickr30k","task":"Zero-Shot Cross-Modal Retrieval","dataset":"Flickr30k","model":"InternVL-C","rank_in_archive_order":3,"of":22,"metrics":{"Image-to-text R@1":"94.7","Image-to-text R@10":"99.9","Image-to-text R@5":"99.6","Text-to-image R@1":"81.7","Text-to-image R@10":"98.2","Text-to-image R@5":"96.0"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-cn","task":"Zero-Shot Transfer Image Classification","dataset":"CN-ImageNet","model":"InternVL-C","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy (Private)":"64.5"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-17","task":"Zero-Shot Transfer Image Classification","dataset":"Food-101","model":"InternVL-C","rank_in_archive_order":3,"of":5,"metrics":{"Top 1 Accuracy":"95.3"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-1","task":"Zero-Shot Transfer Image Classification","dataset":"ImageNet","model":"InternVL-C","rank_in_archive_order":10,"of":23,"metrics":{"Accuracy (Private)":"83.2"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-3","task":"Zero-Shot Transfer Image Classification","dataset":"ImageNet V2","model":"InternVL-C","rank_in_archive_order":8,"of":13,"metrics":{"Accuracy (Private)":"77.3"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-5","task":"Zero-Shot Transfer Image Classification","dataset":"ImageNet-A","model":"InternVL-C","rank_in_archive_order":7,"of":13,"metrics":{"Accuracy (Private)":"83.8"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-8","task":"Zero-Shot Transfer Image Classification","dataset":"ImageNet-Sketch","model":"InternVL-C","rank_in_archive_order":5,"of":7,"metrics":{"Accuracy (Private)":"73.9"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-6","task":"Zero-Shot Transfer Image Classification","dataset":"ObjectNet","model":"InternVL-C","rank_in_archive_order":6,"of":9,"metrics":{"Accuracy (Private)":"80.6"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-video-retrieval-on-msr-vtt-full","task":"Zero-Shot Video Retrieval","dataset":"MSR-VTT-full","model":"InternVL-G","rank_in_archive_order":1,"of":3,"metrics":{"text-to-video R@1":"46.3","text-to-video R@10":"79.6","text-to-video R@5":"70.5","video-to-text R@1":"42.4","video-to-text R@10":"75.4","video-to-text R@5":"65.9"},"uses_additional_data":true},{"leaderboard":"/sota/zero-shot-video-retrieval-on-msr-vtt-full","task":"Zero-Shot Video Retrieval","dataset":"MSR-VTT-full","model":"InternVL-C","rank_in_archive_order":2,"of":3,"metrics":{"text-to-video R@1":"44.7","text-to-video R@10":"78.4","text-to-video R@5":"68.2","video-to-text R@1":"40.2","video-to-text R@10":"74.1","video-to-text R@5":"63.1"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2312.14238","atlas_url":"https://app.syntology.ai/?focus=2312.14238","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.14238"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/opengvlab/internvl-mmdetseg","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/opengvlab/internvl","reach":null}],"summary":{"ran":2},"by_repo_kind":{"listed":{"samples":2,"ran":2,"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":2,"samples":[{"code_sha256_prefix":"726773e9a4284528","entry":"MSDeformAttn","repo":"opengvlab/internvl-mmdetseg","repo_kind":"listed","path":"ops/deformable_attention/modules/ms_deform_attn.py","file_url":"https://github.com/opengvlab/internvl-mmdetseg/blob/HEAD/ops/deformable_attention/modules/ms_deform_attn.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"726773e9a4284528"}},{"code_sha256_prefix":"b46ff70ae52234da","entry":"MSDeformAttnFunction","repo":"opengvlab/internvl-mmdetseg","repo_kind":"listed","path":"ops/deformable_attention/modules/ms_deform_attn.py","file_url":"https://github.com/opengvlab/internvl-mmdetseg/blob/HEAD/ops/deformable_attention/modules/ms_deform_attn.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b46ff70ae52234da"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}