RISTA前沿大讲堂第五季第十二期
承办单位：中国通信学会智能超表面技术专业委员会
报告嘉宾：李升波，清华大学教授
主持嘉宾：吴泳澎，上海交通大学教授
题目：Toward Physics-native Intelligence: World Model, Data Structure and Training Algorithm
摘要：As artificial intelligence advances beyond vision and language processing toward embodied systems—including autonomous driving and robotics—prevailing deep learning paradigms are confronting fundamental challenges. This talk presents a systematic overview of physics-native intelligence (Phi), covering its core design principles and methodologies for constructing its world model, data structure, and training algorithm. Four representative physics-native algorithms are elaborated: (1) RAD: A neural network optimizer engineered with built-in symplectic preservation to guarantee long-term training stability. (2) DACER: A reinforcement learning algorithm that equips neural network policies with the capacity to model multi-modal action distributions. (3) RACS: A ternary iteration framework for addressing safety constraints, which jointly learns the feasible region and optimal policy with provable monotonicity and convergence guarantees. (4) BOOM: An algorithm enabling bidirectional co-improvement with reliance on world model. By internalizing planning capabilities directly into the policy, it substantially enhances sample efficiency.
嘉宾介绍：李升波，清华大学车辆与运载学院、人工智能学院 教授/博导。入选国家高层次领军人才、教育部青年科学奖获得者、交通部科技创新领军人才等。他的研究构建了物理原生智能（Phi, physics-native intelligence）的模型、数据、算法设计框架，围绕绝对安全性保障理论，强化学习三元迭代算法，辛几何神经网络优化器，多模态隐式世界模型，几何约束贝叶斯滤波器及其自动驾驶/机器人应用做出了重要贡献。曾获国家科技进步二等奖、国家技术发明二等奖、中国汽车工业科技进步特等奖、中国自动化学会自然科学一等奖等。担任中国汽车工程学会人工智能分会首任主任、中国自动化学会汽车控制与智能化专委会副主任、中国智能网联汽车产业创新联盟人工智能工作组组长等。
