通智测试——基于动态具身物理社会交互环境的通用人工智能测试

The release of the generative pre-trained transformer(GPT)series has brought artificial general intelligence(AGI)to the forefront of the artificial intelligence(AI)field once again.However,the questions of how to define and evaluate AGI remain unclear.This perspective article proposes that the evaluation of AGI should be rooted in dynamic embodied physical and social interactions(DEPSI).More specifically,we propose five critical characteristics to be considered as AGI benchmarks and suggest the Tong test as an AGI evaluation system.The Tong test describes a value-and ability-oriented testing system that delineates five levels of AGI milestones through a virtual environment with DEPSI,allowing for infinite task generation.We contrast the Tong test with classical AI testing systems in terms of various aspects and propose a systematic evaluation system to promote standardized,quantitative,and objective benchmarks and evaluation of AGI.

用于重建物理和虚拟抓取的可重构数据手套

In this work,we present a reconfigurable data glove design to capture different modes of human hand-object interactions,which are critical in training embodied artificial intelligence(AI)agents for fine manipulation tasks.To achieve various downstream tasks with distinct features,our reconfigurable data glove operates in three modes sharing a unified backbone design that reconstructs hand gestures in real time.In the tactile-sensing mode,the glove system aggregates manipulation force via customized force sensors made from a soft and thin piezoresistive material;this design minimizes interference during complex hand movements.The virtual reality(VR)mode enables real-time interaction in a physically plausible fashion:A caging-based approach is devised to determine stable grasps by detecting collision events.Leveraging a state-of-the-art finite element method,the simulation mode collects data on fine-grained four-dimensionalmanipulation events comprising hand and object motions in three-dimensional space and how the object's physical properties(e.g.,stress and energy)change in accordance with manipulation over time.Notably,the glove system presented here is the first to use high-fidelity simulation to investigate the unobservable physical and causal factors behind manipulation actions.In a series of experiments,we characterize our data glove in terms of individual sensors and the overall system.More specifically,we evaluate the system's three modes by①recording hand gestures and associated forces,②improving manipulation fluency in VR,and③producing realistic simulation effects of various tool uses,respectively.Based on these three modes,our reconfigurable data glove collects and reconstructs fine-grained human grasp data in both physical and virtual environments,thereby opening up new avenues for the learning of manipulation skills for embodied AI agents.

Artificial Social Intelligence:A Comparative and Holistic View

In addition to a physical comprehension of the world,humans possess a high social intelligence-the intelligence that senses social events,infers the goals and intents of others,and facilitates social interaction.Notably,humans are distinguished from their closest primate cousins by their social cognitive skills as opposed to their physical counterparts.We believe that artificial social intelligence(ASI)will play a crucial role in shaping the future of artificial intelligence(AI).This article begins with a review of ASI from a cognitive science standpoint,including social perception,theory of mind(ToM),and social interaction.Next,we examine the recently-emerged computational counterpart in the AI community.Finally,we provide an in-depth discussion on topics related to ASI.

通讯式学习——统一的机器学习模式

在本文中,我们提出了一种沟通学习(CL)形式主义,它统一了现有的机器学习范式,如被动学习、主动学习、算法教学等,并促进了新的学习方法的发展。这种形式主义源于人类的合作交流,将学习视为一种交流过程,并将教育学与新兴的机器学习领域相结合。在机器学习中,除了随机抽样数据之外,教学洞察力有助于采用替代信息源,例如由乐于助人的老师提供的有意信息。更具体地说,在CL中,教师和学生相互协作交换信息,以传递和获取一定的知识。每个主体都有一个心智,心智包括主体的知识、效用和心理动态。为了建立有效的沟通,每个代理还需要估计其合作伙伴的想法。我们定义了足以进行这种递归建模的表达性心理表征和学习公式,这使CL具有与人类相当的学习效率。我们演示了CL在几个原型协作任务中的应用,并说明了这种形式化允许学习协议超越Shannon的通信限制。最后,我们通过提出学习的层次结构和定义学习的停止问题来展示我们对学习基础的贡献。

History dynamics of unified empire in China(770 BC to 476 BC)

The laws and regulations in human history can be revealed by computational models.From 221 before Christ(BC)to 1912 Anno Domini(AD),the unification pattern has dominated the main part of Chinese history for 2132 years.Before the emergence of the first unified empire,the Qin Empire in 221 BC,there existed the Eastern Zhou dynasty(770 BC to 221 BC).This long dynasty has two stages,and here we focus on the first stage.This Spring-Autumn stage was from 770 BC(with 148 states)to 476 BC(with 32 states).The whole country(China)is modelled as a multi‐agent system,which contains multiple local states.They behave autonomously under certain action rules(wars and conflicts),which forms the main reason for the annexations and disappearance of most states.Key factors(power,loyalty,bellicosity and alliance)have been considered in our model settings,and simulation outcomes will be monitored and collected.Eventually,an optimal solution is obtained,which well unveils the internal mechanism and statistical features of real big history.Furthermore,counterfactuals are used to explore the non‐linear effects of the key factors,which deepens the authors’understanding of civilisa-tion evolutions in human history.