35 citations · 65 across the 28 of their papers we have counts for
29 papers
CultureVidBench: Benchmarking Cultural Understanding in Text-to-Video Generation
Xianjing Han, Yuhan Su, Yang Deng +3
Text-to-video (T2V) generation models have advanced rapidly, yet their ability to represent diverse cultural contexts remains underexplored. Existing benchmarks mainly focus on per…
Filter Learning for Subgraphs: Algebras and Performance Risk Bounds
Purui Zhang, Feng Ji, Yanan Zhao +2
Graph signal processing tasks that leverage spectral information typically assume access to the complete graph topology, which is often unavailable in practice. We propose a system…
Graph Distribution-valued Signals in Wasserstein Spaces: Theory and Applications
Yanan Zhao, Feng Ji, Xingchao Jian +1
We introduce a framework for graph signal processing (GSP) in which signals are represented as graph distribution-valued signals (GDSs), i.e., probability measures in a Wasserstein…
Optimal Sensor Placement via Graph-constrained Flow Matching
Feng Ji, Jingyang Dai, Wee Peng Tay +1
Optimal sensor placement is a fundamental problem in graph signal processing (GSP), where a limited number of sensors are deployed to reconstruct a continuous signal field. Existin…
Representation-Aligned Multi-Scale Personalization for Federated Learning
Wenfei Liang, Wee Peng Tay
In federated learning (FL), accommodating clients with diverse resource constraints remains a significant challenge. A widely adopted approach is to use a shared full-size model, f…
Contrastive Conformal Sets
Yahya Alkhatib, Wee Peng Tay
Contrastive learning produces coherent semantic feature embeddings by encouraging positive samples to cluster closely while separating negative samples. However, existing contrasti…
Uncertainty Principle for Vertex-Time Graph Signal Processing
Yanan Zhao, Xingchao Jian, Feng Ji +2
We present an uncertainty principle for graph signals in the vertex-time domain, unifying the classical time-frequency and graph uncertainty principles within a single framework. B…
Conformal Prediction for Multi-Source Detection on a Network
Xingchao Jian, Purui Zhang, Lan Tian +5
Detecting the origin of information or infection spread in networks is a fundamental challenge with applications in misinformation tracking, epidemiology, and beyond. We study the…
Modulo Video Recovery via Selective Spatiotemporal Vision Transformer
Tianyu Geng, Feng Ji, Wee Peng Tay
Conventional image sensors have limited dynamic range, causing saturation in high-dynamic-range (HDR) scenes. Modulo cameras address this by folding incident irradiance into a boun…
Adaptive Multi-view Graph Contrastive Learning via Fractional-order Neural Diffusion Networks
Yanan Zhao, Feng Ji, Jingyang Dai +4
Graph contrastive learning (GCL) learns node and graph representations by contrasting multiple views of the same graph. Existing methods typically rely on fixed, handcrafted views-…
Graph Distribution-valued Signals: A Wasserstein Space Perspective
Yanan Zhao, Feng Ji, Xingchao Jian +1
We introduce a novel framework for graph signal processing (GSP) that models signals as graph distribution-valued signals (GDSs), which are probability distributions in the Wassers…
CodeBoost: Boosting Code LLMs by Squeezing Knowledge from Code Snippets with RL
Sijie Wang, Quanjiang Guo, Kai Zhao +7
Code large language models (LLMs) have become indispensable tools for building efficient and automated coding pipelines. Existing models are typically post-trained using reinforcem…
Conformal Unlearning: A New Paradigm for Unlearning in Conformal Predictors
Yahya Alkhatib, Muhammad Ahmar Jamal, Wee Peng Tay
Conformal unlearning aims to ensure that a trained conformal predictor miscovers data points with specific shared characteristics, such as those from a particular label class, asso…
A Generalized Graph Signal Processing Framework for Multiple Hypothesis Testing over Networks
Xingchao Jian, Martin Gölz, Feng Ji +2
We consider the multiple hypothesis testing (MHT) problem over the joint domain formed by a graph and a measure space. On each sample point of this joint domain, we assign a hypoth…
Simple Graph Contrastive Learning via Fractional-order Neural Diffusion Networks
Yanan Zhao, Feng Ji, Kai Zhao +6
Graph Contrastive Learning (GCL) has recently made progress as an unsupervised graph representation learning paradigm. GCL approaches can be categorized into augmentation-based and…
Efficient Training of Neural Fractional-Order Differential Equation via Adjoint Backpropagation
Qiyu Kang, Xuhao Li, Kai Zhao +4
Fractional-order differential equations (FDEs) enhance traditional differential equations by extending the order of differential operators from integers to real numbers, offering g…
Distributed-Order Fractional Graph Operating Network
Kai Zhao, Xuhao Li, Qiyu Kang +5
We introduce the Distributed-order fRActional Graph Operating Network (DRAGON), a novel continuous Graph Neural Network (GNN) framework that incorporates distributed-order fraction…
PRFusion: Toward Effective and Robust Multi-Modal Place Recognition with Image and Point Cloud Fusion
Sijie Wang, Qiyu Kang, Rui She +3
Place recognition plays a crucial role in the fields of robotics and computer vision, finding applications in areas such as autonomous driving, mapping, and localization. Place rec…
Generalized Graph Signal Reconstruction via the Uncertainty Principle
Yanan Zhao, Xingchao Jian, Feng Ji +2
We introduce a novel uncertainty principle for generalized graph signals that extends classical time-frequency and graph uncertainty principles into a unified framework. By definin…
A Graph Signal Processing Perspective of Network Multiple Hypothesis Testing with False Discovery Rate Control
Xingchao Jian, Martin Gölz, Feng Ji +2
We consider a multiple hypothesis testing problem in a sensor network over the joint spatio-temporal domain. The sensor network is modeled as a graph, with each vertex representing…
FedSheafHN: Personalized Federated Learning on Graph-structured Data
Wenfei Liang, Yanan Zhao, Rui She +2
Personalized subgraph Federated Learning (FL) is a task that customizes Graph Neural Networks (GNNs) to individual client needs, accommodating diverse data distributions. However,…
Unleashing the Potential of Fractional Calculus in Graph Neural Networks with FROND
Qiyu Kang, Kai Zhao, Qinxu Ding +5
We introduce the FRactional-Order graph Neural Dynamical network (FROND), a new continuous graph neural network (GNN) framework. Unlike traditional continuous GNNs that rely on int…
PointDifformer: Robust Point Cloud Registration With Neural Diffusion and Transformer
Rui She, Qiyu Kang, Sijie Wang +7
Point cloud registration is a fundamental technique in 3-D computer vision with applications in graphics, autonomous driving, and robotics. However, registration tasks under challe…
PosDiffNet: Positional Neural Diffusion for Point Cloud Registration in a Large Field of View with Perturbations
Rui She, Sijie Wang, Qiyu Kang +5
Point cloud registration is a crucial technique in 3D computer vision with a wide range of applications. However, this task can be challenging, particularly in large fields of view…