article-journal

[Journal of Intelligence][2026] Bridging Cognitive Architecture and Developmental Measurement for Artificial General Intelligence

This article develops an operational formulation of the General–Specialized–Applicable (GSA) framework for artificial general intelligence (AGI) evaluation.

Yuqiu Fu, Yuxi Wang, Hongzhao Xie, Shiyun Zhao, Mingyuan Liu, Yujie Lu, Xinyi He, Zhenku Cheng, Yujia Peng, Zhenliang Zhang

[Journal of Intelligence][2026] Bridging Cognitive Architecture and Developmental Measurement for Artificial General Intelligence

[Journal of Psychological Science][2026] Human Intelligence-Inspired Testing for the Developmental Stages of Artificial General Intelligence: From General to Applicable

We proposed a human intelligence-inspired developmental testing framework for AGI to assess its progression from general to applied capabilities.

Yujia Peng, Xinyi He, Hongzhao Xie, Xizhi Xiao, Yuxi Wang, Song-Chun Zhu, Zhenliang Zhang

[Journal of Psychological Science][2026] Human Intelligence-Inspired Testing for the Developmental Stages of Artificial General Intelligence: From General to Applicable

[Neurocomputing][2026] A Low-Burden Attention Network Based on Asynchronous Mechanism for BCI Motor Intention Recognition

We propose an Asynchronous Spatial-Temporal Attention Network (AsyncST-Atten), which first extracts local features through shallow convolutions and then applies attention mechanisms to model their long-range temporal dependencies.

Jiaqi Ma, Guangyu Wang, Zhenliang Zhang, Lele Li, Tianjiao Zheng, Jie Zhao, Yanhe Zhu

[Neurocomputing][2026] A Low-Burden Attention Network Based on Asynchronous Mechanism for BCI Motor Intention Recognition

[RAL][2026] Active Kinematic Modeling for Precise Manipulation of Unseen Articulated Objects

We propose a novel Active Kinematic Modeling method (AKM), where robots actively interact with objects to overcome spurious correlations and achieve precise kinematic modeling.

Boyuan Zhang, Yuxuan Wang, Yizhou Wang, Wei Wang, Zhenliang Zhang

[RAL][2026] Active Kinematic Modeling for Precise Manipulation of Unseen Articulated Objects

[ScienceChina][2025] Ability Decomposition and Difficulty Quantification of Visual Tasks: Towards Systematic Evaluations of Artificial General Intelligence

We took the visual domain as a starting point and proposed an explainable system for task ability decomposition and difficulty level quantification of vision (TADDL-V).

Shaoyang Cui, Xinyi He, Jiaheng Han, Zhenliang Zhang, Yujia Peng

[ScienceChina][2025] Ability Decomposition and Difficulty Quantification of Visual Tasks: Towards Systematic Evaluations of Artificial General Intelligence

[TOMM][2024] Demonstrative Learning for Human-Agent Knowledge Transfer

We propose a comprehensive system that combines the SDL paradigm with the TDL paradigm in VR from a top-down perspective.

Xiaonuo Dongye, Haiyan Jiang, Dongdong Weng, Zhenliang Zhang

[TOMM][2024] Demonstrative Learning for Human-Agent Knowledge Transfer

[Engineering][2024] The tong test: Evaluating artificial general intelligence through dynamic embodied physical and social interactions

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.

Yujia Peng, Jiaheng Han, Zhenliang Zhang, Lifeng Fan, Tengyu Liu, Siyuan Qi, Xue Feng, Yuxi Ma, Yizhou Wang, Song-Chun Zhu

[Engineering][2024] The tong test: Evaluating artificial general intelligence through dynamic embodied physical and social interactions

[Engineering][2024] A reconfigurable data glove for reconstructing physical and virtual grasps

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.

Hangxin Liu, Zeyu Zhang, Ziyuan Jiao, Zhenliang Zhang, Mingchen Li, Chenfanfu Jiang, Yixin Zhu, Song-Chun Zhu

[Engineering][2024] A reconfigurable data glove for reconstructing physical and virtual grasps

[TOG][2023] Commonsense Knowledge-Driven Joint Reasoning Approach for Object Retrieval in Virtual Reality

we propose a commonsense knowledge-driven joint reasoning approach for object retrieval, where human grasping gestures and context are modeled using an And-Or graph (AOG).

Haiyan Jiang, Dongdong Weng, Xiaonuo Dongye, Le Luo, Zhenliang Zhang

[TOG][2023] Commonsense Knowledge-Driven Joint Reasoning Approach for Object Retrieval in Virtual Reality

[Virtual Reality][2023] DexHand: dexterous hand manipulation motion synthesis for virtual reality

We propose a neural network-based finger movement generation approach, enabling the generation of plausible hand motions interacting with objects.

Haiyan Jiang, Dongdong Weng, Zhen Song, Xiaonuo Dongye, Zhenliang Zhang

[Virtual Reality][2023] DexHand: dexterous hand manipulation motion synthesis for virtual reality