Chang Liu

Preliminary Exploration of the Effect of Time Constraint on Search Interactions on Webpages

2016

This study explored the effect of time constraint on searchers' interactions during two kinds of tasks through conducting a user experiment. The results demonstrated users' did not tend to accelerate their reading or decision speed …

Intention Propagation for Multi-agent Reinforcement Learning

2021

A hallmark of an AI agent is to mimic human beings to understand and interact with others. In this paper, we propose a \emph{collaborative} multi-agent reinforcement learning algorithm to learn a \emph{joint} policy through the …

Rumor-robust Decentralized Gaussian Process Learning, Fusion, and Planning for Modeling Multiple Moving Targets

2020 · arXiv (Cornell University)

This paper presents a decentralized Gaussian Process (GP) learning, fusion, and planning (RESIN) formalism for mobile sensor networks to actively learn target motion models. RESIN is characterized by both computational and communication efficiency, and the …

Towards Aggregated Features: A Novel Proxy Detection Method Using NetFlow Data

2020

Proxies can provide privacy and anonymity protection for users, but can also be exploited by attackers to hide their malicious behaviors. In order to strengthen the monitoring and management of network, proxy detection has become …

BioGen: Generating Biography Summary under Table Guidance on Wikipedia

2021

Capturing the salient information from an input article has been a long-standing challenge for summarization. On Wikipedia, most of the wiki pages about people contain a factual table that lists the basic properties of the …

Transformer-based unsupervised patient representation learning based on medical claims for risk stratification and analysis

2021

The claims data, containing medical codes, services information, and incurred expenditure, can be a good resource for estimating an individual's health condition and medical risk level. In this study, we developed Transformer-based Multimodal AutoEncoder (TMAE), …

Statistical analysis of songs by composers of the Romantic era: A comparison of F. Schubert and his contemporaries

2021 · Música Hodie

The study investigates musical compositions via quantification using mathematical methods. The investigation is based on Franz Schubert’s song cycle Die Winterreise, Robert Schumann’s song cycle Myrthen, and on works by other composers. The study obtained …

Local Manifold Augmentation for Multiview Semantic Consistency

2022 · arXiv (Cornell University)

Multiview self-supervised representation learning roots in exploring semantic consistency across data of complex intra-class variation. Such variation is not directly accessible and therefore simulated by data augmentations. However, commonly adopted augmentations are handcrafted and limited …

Incubation and Verification Processes in Information Seeking: A Case Study in the Context of Autonomous Learning

2023

Autonomous learning regards students as the center and orientation rather than teachers’ guidance. During autonomous learning, information seeking is not only a process of interactions with systems and stakeholders, but also a process of learning …

Blockchain-based Regulatory Framework for Logistics Management

2023

Logistics transportation have developed rapidly in recent years. As technology advances, the goods that can be transported by logistics are becoming more and more expensive. Besides, due to the increasing demand for transportation, complex logistics …

Global Wagon Web: Enabling a Semantic-Enhanced Framework for Vehicle Infrastructure Cooperative System

2023

The core technology of Vehicle Infrastructure Cooperative System (VICS) has progressed to a “cooperative perception” phase, which necessitates an efficient, reliable and cost-effective information sharing mechanism. However, existing approaches are insufficient to meet the requirements …

Convolutional Unscented Kalman Filter for Multi-Object Tracking With Outliers

2024 · IEEE Transactions on Intelligent Vehicles

Multi-object tracking (MOT) is an essential technique for navigation in autonomous driving. In tracking-by-detection systems, biases, false positives, and misses, which are referred to as outliers, are inevitable due to complex traffic scenarios. Recent tracking …

Conditional-Balanced Adversarial Delta Tuning for Cross-Domain Implicit Discourse Relation Recognition

2025

Implicit discourse relation recognition (IDRR) is faced with a domain dilemma. Recent studies have achieved breakthroughs in standard datasets, while they are not appropriate in domains with insufficient data, such as bio-medicine. In this paper, …

Addressing Graph Anomaly Detection via Causal Edge Separation and Spectrum

2025 · arXiv (Cornell University)

In the real world, anomalous entities often add more legitimate connections while hiding direct links with other anomalous entities, leading to heterophilic structures in anomalous networks that most GNN-based techniques fail to address. Several works …

SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning

2017 · arXiv (Cornell University)

Synthesizing SQL queries from natural language is a long-standing open problem and has been attracting considerable interest recently. Toward solving the problem, the de facto approach is to employ a sequence-to-sequence-style model. Such an approach …

Noninvasive Self-attention for Side Information Fusion in Sequential Recommendation

2021 · Proceedings of the AAAI Conference on Artificial Intelligence

Sequential recommender systems aim to model users’ evolving interests from their historical behaviors, and hence make customized time-relevant recommendations. Compared with traditional models, deep learning approaches such as CNN and RNN have achieved remarkable advancements …