明略科技 Mano Technical Report

2025-09-18

Graphical user interfaces (GUIs) are the primary medium for human-computer interaction, yet automating GUI interactions remains challenging due to the complexity of visual elements, dynamic environments, and the need for multi-step reasoning. Existing methods based on vision-language models (VLMs) often suffer from limited resolution, domain mismatch, and insufficient sequential decisionmaking capability. To address these issues, we propose Mano, a robust GUI agent built upon a multi-modal foundation model pre-trained on extensive web and computer system data. Our approach integrates a novel simulated environment for high-fidelity data generation, a three-stage training pipeline (supervised fine-tuning, offline reinforcement learning, and online reinforcement learning), and a verification module for error recovery. Mano demonstrates state-of-the-art performance on multiple GUI benchmarks, including Mind2Web and OSWorld, achieving significant improvements in success rate and operational accuracy. Our work provides new insights into the effective integration of reinforcement learning with VLMs for practical GUI agent deployment, highlighting the importance of domain-specific data, iterative training, and holistic reward design.

「2024生成式营销产学研讨会」在复旦大学管理学院举行

2024-05-13

5月10日，第8个中国品牌日之际， 2024生成式营销产学研讨会在复旦大学管理学院史带楼举行。

一种词向量的确定方法、装置、存储介质和电子装置

2024-04-19

本申请涉及一种词向量的确定方法、装置、存储介质和电子装置，其中，该方法包括：获取未登录词中包含的多个目标字符和获取每个目标字符的字符向量，其中，未登录词为不包含在预设词典中的词；确定目标字符在预设词典中的构词关系，其中，构词关系为目标字符与预设词典中包含的已登录词之间的关系；根据构词关系和每个字符向量确定未登录词的词向量。本申请解决了未登录词的词向量生成的效率较低的技术问题。