12 citations · 34 across the 12 of their papers we have counts for
15 papers
Diffusion Transformers are Provably Optimal In-context Generators
Guoji Fu, Tomoya Wakayama, Ryotaro Kawata +3
Generative foundation models are attracting interest for their ability to produce desired outputs from demonstrations given at inference time, without updating parameters. However,…
Intrinsic Wasserstein Rates for Score-Based Generative Models on Smooth Manifolds
Guoji Fu, Taiji Suzuki, Wee Sun Lee +1
Score-based generative models are trained in high-dimensional ambient spaces, yet many data distributions are supported on low-dimensional nonlinear structures. We prove that, for…
RelaxFlow: Text-Driven Amodal 3D Generation
Jiayin Zhu, Guoji Fu, Xiaolu Liu +3
Image-to-3D generation faces inherent semantic ambiguity under occlusion, where partial observation alone is often insufficient to determine object category. In this work, we forma…
Continual Reinforcement Learning by Planning with Online World Models
Zichen Liu, Guoji Fu, Chao Du +2
Continual reinforcement learning (CRL) refers to a naturalistic setting where an agent needs to endlessly evolve, by trial and error, to solve multiple tasks that are presented seq…
Exploration by Random Reward Perturbation
Haozhe Ma, Guoji Fu, Zhengding Luo +2
We introduce Random Reward Perturbation (RRP), a novel exploration strategy for reinforcement learning (RL). Our theoretical analyses demonstrate that adding zero-mean noise to env…
Approximation and Generalization Abilities of Score-based Neural Network Generative Models for Sub-Gaussian Distributions
Guoji Fu, Wee Sun Lee
This paper studies the approximation and generalization abilities of score-based neural network generative models (SGMs) in estimating an unknown distribution from i.i.d.…
Constrained Layout Generation with Factor Graphs
Mohammed Haroon Dupty, Yanfei Dong, Sicong Leng +4
This paper addresses the challenge of object-centric layout generation under spatial constraints, seen in multiple domains including floorplan design process. The design process ty…
Implicit Graph Neural Diffusion Networks: Convergence, Generalization, and Over-Smoothing
Guoji Fu, Mohammed Haroon Dupty, Yanfei Dong +1
Implicit Graph Neural Networks (GNNs) have achieved significant success in addressing graph learning problems recently. However, poorly designed implicit GNN layers may have limite…
Fairness-aware Message Passing for Graph Neural Networks
Huaisheng Zhu, Guoji Fu, Zhimeng Guo +3
Graph Neural Networks (GNNs) have shown great power in various domains. However, their predictions may inherit societal biases on sensitive attributes, limiting their adoption in r…
SyNDock: N Rigid Protein Docking via Learnable Group Synchronization
Yuanfeng Ji, Yatao Bian, Guoji Fu +2
The regulation of various cellular processes heavily relies on the protein complexes within a living cell, necessitating a comprehensive understanding of their three-dimensional st…
What Has Been Enhanced in my Knowledge-Enhanced Language Model?
Yifan Hou, Guoji Fu, Mrinmaya Sachan
Pretrained language models (LMs) do not capture factual knowledge very well. This has led to the development of a number of knowledge integration (KI) methods which aim to incorpor…
-Laplacian Based Graph Neural Networks
Guoji Fu, Peilin Zhao, Yatao Bian
Graph neural networks (GNNs) have demonstrated superior performance for semi-supervised node classification on graphs, as a result of their ability to exploit node features and top…
Understanding Graph Neural Networks from Graph Signal Denoising Perspectives
Guoji Fu, Yifan Hou, Jian Zhang +3
Graph neural networks (GNNs) have attracted much attention because of their excellent performance on tasks such as node classification. However, there is inadequate understanding o…
Learning Topological Representation for Networks via Hierarchical Sampling
Guoji Fu, Chengbin Hou, Xin Yao
The topological information is essential for studying the relationship between nodes in a network. Recently, Network Representation Learning (NRL), which projects a network into a…
Representation Learning for Heterogeneous Information Networks via Embedding Events
Guoji Fu, Bo Yuan, Qiqi Duan +1
Network representation learning (NRL) has been widely used to help analyze large-scale networks through mapping original networks into a low-dimensional vector space. However, exis…