Quan Liu

Entity Hierarchy Construction for Repair Request Records

2016

A repair request record is an unstructured short text written by customers to describe quality problems of building products. The extraction of entities and the construction of a hierarchical structure can provide an efficient source …

Detecting Speaker Personas from Conversational Texts

2021 · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Personas are useful for dialogue response prediction.

A Perturbation-Based Policy Distillation Framework with Generative Adversarial Nets

2023

We study the problem of imitation learning in automated decision systems, in which a learner is trained to imitate an expert demonstrator. A widely used method is adversarial imitation learning that alternately optimizes a generator …

SHINE: Syntax-augmented Hierarchical Interactive Encoder for Zero-shot Cross-lingual Information Extraction

2023 · arXiv (Cornell University)

Zero-shot cross-lingual information extraction(IE) aims at constructing an IE model for some low-resource target languages, given annotations exclusively in some rich-resource languages. Recent studies based on language-universal features have shown their effectiveness and are attracting …

Spatial-Temporal Fusion Network with Hybrid Attention for Energy Expenditure Prediction Based on Multi-Sensor

2024

To reduce the measurement time of the metabolic energy expenditure in human-in-the-loop optimization, this paper proposes a spatial-temporal fusion network that combines convolutional neural network, multi-head attention and cross-attention mechanism in both temporal and frequency …

Deep Deterministic Strategy Gradient Method Using Plot Experience Playback

2024

The research on continuous control in reinforcement learning has been a hot topic in recent years. The Deep Deterministic Policy Gradient (DDPG) algorithm performs well in continuous control tasks. DDPG algorithm uses experience replay mechanism …

Fine-grained Multi-class Nuclei Segmentation with Molecular-empowered All-in-SAM Model

2025 · arXiv (Cornell University)

Purpose: Recent developments in computational pathology have been driven by advances in Vision Foundation Models, particularly the Segment Anything Model (SAM). This model facilitates nuclei segmentation through two primary methods: prompt-based zero-shot segmentation and the …

Glo-VLMs: Leveraging Vision-Language Models for Fine-Grained Diseased Glomerulus Classification

2025 · arXiv (Cornell University)

Vision-language models (VLMs) have shown considerable potential in digital pathology, yet their effectiveness remains limited for fine-grained, disease-specific classification tasks such as distinguishing between glomerular subtypes. The subtle morphological variations among these subtypes, combined with …