Lei Yu

Neural Variational Inference for Text Processing

2015 · arXiv (Cornell University)

Recent advances in neural variational inference have spawned a renaissance in deep latent variable models. In this paper we introduce a generic variational inference framework for generative and conditional models of text. While traditional variational …

The SYSU System for the Interspeech 2015 Automatic Speaker Verification Spoofing and Countermeasures Challenge

2015 · arXiv (Cornell University)

Many existing speaker verification systems are reported to be vulnerable against different spoofing attacks, for example speaker-adapted speech synthesis, voice conversion, play back, etc. In order to detect these spoofed speech signals as a countermeasure, …

Analog-to-digital conversion revolutionized by deep learning

2018 · arXiv (Cornell University)

As the bridge between the analog world and digital computers, analog-to-digital converters are generally used in modern information systems such as radar, surveillance, and communications. For the configuration of analog-to-digital converters in future high-frequency broadband …

Learning and Evaluating General Linguistic Intelligence

2019 · arXiv (Cornell University)

We define general linguistic intelligence as the ability to reuse previously acquired knowledge about a language's lexicon, syntax, semantics, and pragmatic conventions to adapt to new tasks quickly. Using this definition, we analyze state-of-the-art natural …

A Mutual Information Maximization Perspective of Language Representation Learning

2020 · arXiv (Cornell University)

We show state-of-the-art word representation learning methods maximize an objective function that is a lower bound on the mutual information between different parts of a word sequence (i.e., a sentence). Our formulation provides an alternative …

Research on sensing node location technology based on AOA and fingerprint recognition

2022 · Journal of Physics Conference Series

Abstract In order to meet the needs of intelligent operation and maintenance of distribution networks, a large number of wireless sensors are deployed inside and outside the power grid for digital sensing and immediate control …

Enhanced Transformers for Radar Jamming Recognition

2023

The recognition of jamming type is a key step among advanced anti-jamming techniques. Currently, deep convolutional neural network (CNN)-based and recurrent neural network (RNN)-based methods have been used for radar jamming recognition. However, they both …

A Novel Jamming Signal Recognition Method Based on Data Augmentation Using 1D-GAN under Small Sample Condition

2023

Various jamming signals in the complex electromagnetic environment pose a serious threat to radar detection. Effective recognition of jamming type is of great significance for anti-jamming. In recent years, jamming recognition algorithms based on deep …

COPR: Continual Human Preference Learning via Optimal Policy Regularization

2024 · arXiv (Cornell University)

Reinforcement Learning from Human Feedback (RLHF) is commonly utilized to improve the alignment of Large Language Models (LLMs) with human preferences. Given the evolving nature of human preferences, continual alignment becomes more crucial and practical …

A NOVEL POINT CLOUD CLASSIFICATION METHOD BASED ON SUBSPACE EXTENSION AND ADAPTIVE MULTIDIMENSIONAL FEATURE MINING WITH APPLICATION TO HEALTH MONITORING OF OVERHEAD TRANSMISSION LINES. 138-149

2026 · Control and Intelligent Systems

In the health monitoring of overhead transmission line equipment,intelligent point cloud classification confronts two critical challenges:discontinuous extraction of transmission lines caused by large terrainelevation differences, and high costs associated with acquiringlabelled data.