Chunhui Zhang

USCL: Pretraining Deep Ultrasound Image Diagnosis Model through Video Contrastive Representation Learning

2020 · arXiv (Cornell University)

Most deep neural networks (DNNs) based ultrasound (US) medical image analysis models use pretrained backbones (e.g., ImageNet) for better model generalization. However, the domain gap between natural and medical images causes an inevitable performance bottleneck. …

Boosting Graph Neural Networks via Adaptive Knowledge Distillation

2022 · arXiv (Cornell University)

Graph neural networks (GNNs) have shown remarkable performance on diverse graph mining tasks. Although different GNNs can be unified as the same message passing framework, they learn complementary knowledge from the same graph. Knowledge distillation …

Topology Abstraction-Based Routing Scheme for Secret-Key Provisioning in Hybrid GEO/LEO Quantum Satellite Networks

2023 · Entropy

Quantum key distribution (QKD) is a promising technique to resist the threat against quantum computers. However, the high loss of quantum signals over a long-distance optical fiber is an obstacle for QKD in the intercontinental …

Do Theory of Mind Benchmarks Need Explicit Human-like Reasoning in Language Models?

2025 · arXiv (Cornell University)

Theory of Mind (ToM), the ability to attribute mental states to others, is fundamental for human social intelligence and a critical capability for advanced Artificial Intelligence. Recent advancements in Large Language Models (LLMs) have shown …