11 citations · 25 across the 13 of their papers we have counts for
13 papers
Grounding Before Generalizing: How AI Differs from Humans in Causal Transfer
Liangru Xiang, Yuxi Ma, Zhihao Cao +2
Extracting abstract causal structures and applying them to novel situations is a hallmark of human intelligence. While Large Language Models (LLMs) and Vision Language Models (VLMs…
Integration of Robot and Scene Kinematics for Sequential Mobile Manipulation Planning
Ziyuan Jiao, Yida Niu, Zeyu Zhang +5
We present a Sequential Mobile Manipulation Planning (SMMP) framework that can solve long-horizon multi-step mobile manipulation tasks with coordinated whole-body motion, even when…
Multivariate Long-term Time Series Forecasting with Fourier Neural Filter
Chenheng Xu, Dan Wu, Yixin Zhu +1
Multivariate long-term time series forecasting has been suffering from the challenge of capturing both temporal dependencies within variables and spatial correlations across variab…
On the Complexity of Bayesian Generalization
Yu-Zhe Shi, Manjie Xu, John E. Hopcroft +6
We consider concept generalization at a large scale in the diverse and natural visual spectrum. Established computational modes (i.e., rule-based or similarity-based) are primarily…
Neural-Symbolic Recursive Machine for Systematic Generalization
Qing Li, Yixin Zhu, Yitao Liang +3
Current learning models often struggle with human-like systematic generalization, particularly in learning compositional rules from limited data and extrapolating them to novel com…
Latent Diffusion Energy-Based Model for Interpretable Text Modeling
Peiyu Yu, Sirui Xie, Xiaojian Ma +6
Latent space Energy-Based Models (EBMs), also known as energy-based priors, have drawn growing interests in generative modeling. Fueled by its flexibility in the formulation and st…
Emergent Graphical Conventions in a Visual Communication Game
Shuwen Qiu, Sirui Xie, Lifeng Fan +4
Humans communicate with graphical sketches apart from symbolic languages. Primarily focusing on the latter, recent studies of emergent communication overlook the sketches; they do…
Unsupervised Foreground Extraction via Deep Region Competition
Peiyu Yu, Sirui Xie, Xiaojian Ma +3
We present Deep Region Competition (DRC), an algorithm designed to extract foreground objects from images in a fully unsupervised manner. Foreground extraction can be viewed as a s…
Consolidating Kinematic Models to Promote Coordinated Mobile Manipulations
Ziyuan Jiao, Zeyu Zhang, Xin Jiang +4
We construct a Virtual Kinematic Chain (VKC) that readily consolidates the kinematics of the mobile base, the arm, and the object to be manipulated in mobile manipulations. Accordi…
Efficient Task Planning for Mobile Manipulation: a Virtual Kinematic Chain Perspective
Ziyuan Jiao, Zeyu Zhang, Weiqi Wang +4
We present a Virtual Kinematic Chain (VKC) perspective, a simple yet effective method, to improve task planning efficacy for mobile manipulation. By consolidating the kinematics of…
Learning Triadic Belief Dynamics in Nonverbal Communication from Videos
Lifeng Fan, Shuwen Qiu, Zilong Zheng +3
Humans possess a unique social cognition capability; nonverbal communication can convey rich social information among agents. In contrast, such crucial social characteristics are m…
Reconstructing Interactive 3D Scenes by Panoptic Mapping and CAD Model Alignments
Muzhi Han, Zeyu Zhang, Ziyuan Jiao +4
In this paper, we rethink the problem of scene reconstruction from an embodied agent's perspective: While the classic view focuses on the reconstruction accuracy, our new perspecti…
A Minimalist Dataset for Systematic Generalization of Perception, Syntax, and Semantics
Qing Li, Siyuan Huang, Yining Hong +3
Inspired by humans' exceptional ability to master arithmetic and generalize to new problems, we present a new dataset, Handwritten arithmetic with INTegers (HINT), to examine machi…