{"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/multimodal-few-shot-learning-with-frozen","title":"Multimodal Few-Shot Learning with Frozen Language Models","arxiv_id":"2106.13884","date":"2021-06-25","proceeding":"NeurIPS 2021 12","authors":["Maria Tsimpoukelli","Jacob Menick","Serkan Cabi","S. M. Ali Eslami","Oriol Vinyals","Felix Hill"],"abstract":"When trained at sufficient scale, auto-regressive language models exhibit the notable ability to learn a new language task after being prompted with just a few examples. Here, we present a simple, yet effective, approach for transferring this few-shot learning ability to a multimodal setting (vision and language). Using aligned image and caption data, we train a vision encoder to represent each image as a sequence of continuous embeddings, such that a pre-trained, frozen language model prompted with this prefix generates the appropriate caption. The resulting system is a multimodal few-shot learner, with the surprising ability to learn a variety of new tasks when conditioned on examples, represented as a sequence of multiple interleaved image and text embeddings. We demonstrate that it can rapidly learn words for new objects and novel visual categories, do visual question-answering with only a handful of examples, and make use of outside knowledge, by measuring a single model on a variety of established and new benchmarks.","url_abs":"https://arxiv.org/abs/2106.13884v2","url_pdf":"https://arxiv.org/pdf/2106.13884v2.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":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"question-answering","task_name":"Question Answering"},{"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/visual-question-answering-on-ok-vqa","task":"Visual Question Answering (VQA)","dataset":"OK-VQA","model":"Frozen","rank_in_archive_order":37,"of":37,"metrics":{"Accuracy":" 5.9"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-val","task":"Visual Question Answering (VQA)","dataset":"VQA v2 val","model":"Frozen","rank_in_archive_order":11,"of":11,"metrics":{"Accuracy":"29.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.13884","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}