{"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/uni-perceiver-moe-learning-sparse-generalist","title":"Uni-Perceiver-MoE: Learning Sparse Generalist Models with Conditional MoEs","arxiv_id":"2206.04674","date":"2022-06-09","proceeding":null,"authors":["Jinguo Zhu","Xizhou Zhu","Wenhai Wang","Xiaohua Wang","Hongsheng Li","Xiaogang Wang","Jifeng Dai"],"abstract":"To build an artificial neural network like the biological intelligence system, recent works have unified numerous tasks into a generalist model, which can process various tasks with shared parameters and do not have any task-specific modules. While generalist models achieve promising results on various benchmarks, they have performance degradation on some tasks compared with task-specialized models. In this work, we find that interference among different tasks and modalities is the main factor to this phenomenon. To mitigate such interference, we introduce the Conditional Mixture-of-Experts (Conditional MoEs) to generalist models. Routing strategies under different levels of conditions are proposed to take both the training/inference cost and generalization ability into account. By incorporating the proposed Conditional MoEs, the recently proposed generalist model Uni-Perceiver can effectively mitigate the interference across tasks and modalities, and achieves state-of-the-art results on a series of downstream tasks via prompt tuning on 1% of downstream data. Moreover, the introduction of Conditional MoEs still holds the generalization ability of generalist models to conduct zero-shot inference on new tasks, e.g., video-text retrieval and video caption. Code and pre-trained generalist models shall be released.","url_abs":"https://arxiv.org/abs/2206.04674v2","url_pdf":"https://arxiv.org/pdf/2206.04674v2.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":"uni-perceiver-moe-learning-sparse-generalist","repo_url":"https://github.com/fundamentalvision/Uni-Perceiver","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-to-text-retrieval","task_name":"Image-to-Text Retrieval"},{"task_slug":"mixture-of-experts","task_name":"Mixture-of-Experts"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"text-retrieval","task_name":"Text Retrieval"},{"task_slug":"video-captioning","task_name":"Video Captioning"},{"task_slug":"video-classification","task_name":"Video Classification"},{"task_slug":"video-text-retrieval","task_name":"Video-Text Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2206.04674","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}