29 citations · 32 across the 7 of their papers we have counts for
7 papers
4DGS-WAM: Bridging Past and Future with an Object-Centric World Action Model based on 4D Gaussian Splatting
Yueen Ma, Zenglin Xu, Irwin King
Current world action models (WAMs) typically operate on 2D visual data. These models can achieve exceptional visual quality, but they lack explicit spatial structure for individual…
X-GS: An Extensible Framework for Perceiving and Thinking with 3D Gaussian Splatting
Yueen Ma, Zenglin Xu, Irwin King
3D Gaussian Splatting (3DGS) has emerged as a powerful technique for novel view synthesis, subsequently extending into numerous spatial AI applications. However, most existing 3DGS…
3D-MoE: Towards Spatial Intelligence with Mixture-of-Experts for 3D Reasoning and Action Generation
Yueen Ma, Zenglin Xu, Yuzheng Zhuang +2
Spatial intelligence, encompassing 3D perception and reasoning, is the essential next frontier of AI. Scaling current 3D vision-language models (VLMs) that rely on dense Transforme…
Astra: Efficient Transformer Architecture and Contrastive Dynamics Learning for Embodied Instruction Following
Yueen Ma, Dafeng Chi, Shiguang Wu +3
Vision-language-action models have gained significant attention for their ability to model multimodal sequences in embodied instruction following tasks. However, most existing mode…
A Survey on Vision-Language-Action Models for Embodied AI
Yueen Ma, Zixing Song, Yuzheng Zhuang +2
Embodied AI is widely recognized as a cornerstone of artificial general intelligence (AGI) because it involves controlling embodied agents to perform tasks in the physical world. B…
VOLTA: Improving Generative Diversity by Variational Mutual Information Maximizing Autoencoder
Yueen Ma, Dafeng Chi, Jingjing Li +3
The natural language generation domain has witnessed great success thanks to Transformer models. Although they have achieved state-of-the-art generative quality, they often neglect…
Graph Component Contrastive Learning for Concept Relatedness Estimation
Yueen Ma, Zixing Song, Xuming Hu +3
Concept relatedness estimation (CRE) aims to determine whether two given concepts are related. Existing methods only consider the pairwise relationship between concepts, while over…