The VoxCeleb Speaker Recognition Challenge(VoxSRC)是由英國牛津大學(xué)、韓國NAVER公司、美國斯坦福國際研究院語音技術(shù)與研究實驗室和麻省理工學(xué)院林肯實驗室組織聯(lián)合舉行的國際說話人識別競賽。今年的賽事競爭激烈，參與的全球知名研究機構(gòu)和企業(yè)包括約翰霍普金斯大學(xué)、昆山杜克大學(xué)、西北工業(yè)大學(xué)、騰訊、字節(jié)跳動、國音智能、三星、華為、搜狗等。
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.
以客戶為中心，集新模式與高質(zhì)量服務(wù)為一體
報告.jpg)
