Yue Wu

A Location-Based Personalized Focused Search System for Physically Challenged People

2015 · Advances in computer science research

Physically Challenged people are a special part of society, which need more care. Because of the huge differences in physical conditions, qualities of life, locations and personal backgrounds, there exists a lot of challenges for …

Generating Adversarial Samples With Constrained Wasserstein Distance

2019 · IEEE Access

In recent years, deep neural network (DNN) approaches prove to be useful in many machine learning tasks, including classification. However, small perturbations that are carefully crafted by attackers can lead to the misclassification of the …

Automatic Modulation Recognition for Radar Signals via Multi-Branch ACSE Networks

2020 · IEEE Access

Automatic modulation recognition (AMR) for radar signals plays a significant role in electronic warfare. Conventional recognition methods may suffer from the recognition accuracy and the computation complexity under low signal-to-noise ratio (SNR) conditions. In this …

Nearly Minimax Optimal Regret for Learning Infinite-horizon Average-reward MDPs with Linear Function Approximation

2021 · arXiv (Cornell University)

We study reinforcement learning in an infinite-horizon average-reward setting with linear function approximation, where the transition probability function of the underlying Markov Decision Process (MDP) admits a linear form over a feature mapping of the …

Model Sparsification for Communication-Efficient Multi-Party Learning via Contrastive Distillation in Image Classification

2023 · IEEE Transactions on Emerging Topics in Computational Intelligence

Multi-party learning allows all parties to train a joint model under legal and practical constraints without private data transmission. Related research can perform multi-party learning tasks on homogeneous data through deep networks. However, due to …

E-DoH: Elegantly Detecting the Depths of Open DoH Service on the Internet

2024 · arXiv (Cornell University)

In recent years, DNS over Encrypted (DoE) methods have been regarded as a novel trend within the realm of the DNS ecosystem. In these DoE methods, DNS over HTTPS (DoH) provides encryption to protect data …

DISC: Dynamic Decomposition Improves LLM Inference Scaling

2025 · arXiv (Cornell University)

Inference scaling methods for LLMs often rely on decomposing problems into steps (or groups of tokens), followed by sampling and selecting the best next steps. However, these steps and their sizes are often predetermined or …