Zhou Yu

A sensor scheduling algorithm with radiation control based on POMDP

2017

Aiming at the radiation control problem for sensor scheduling, a sensor scheduling algorithm based on partially observable Markov decision process (POMDP) is proposed. The target model is set up in the three-dimensional space, and the …

Structured Content Preservation for Unsupervised Text Style Transfer

2018 · arXiv (Cornell University)

Text style transfer aims to modify the style of a sentence while keeping its content unchanged. Recent style transfer systems often fail to faithfully preserve the content after changing the style. This paper proposes a …

Understanding the Evolution of Blockchain Ecosystems: A Longitudinal Measurement Study of Bitcoin, Ethereum, and EOSIO

2021 · arXiv (Cornell University)

The continuing expansion of the blockchain ecosystems has attracted much attention from the research community. However, although a large number of research studies have been proposed to understand the diverse characteristics of individual blockchain systems …

Trade or Trick?

2022

The prosperity of the cryptocurrency ecosystem drives the need for digital asset trading platforms. Uniswap, as the most prominent cryptocurrency decentralized exchange (DEX), is continuing to attract scammers, with fraudulent cryptocurrencies flooding in the ecosystem. …

Pre-Finetuning for Few-Shot Emotional Speech Recognition

2023 · arXiv (Cornell University)

Speech models have long been known to overfit individual speakers for many classification tasks. This leads to poor generalization in settings where the speakers are out-of-domain or out-of-distribution, as is common in production environments. We …

State Value Generation with Prompt Learning and Self-Training for Low-Resource Dialogue State Tracking

2024 · arXiv (Cornell University)

Recently, low-resource dialogue state tracking (DST) has received increasing attention. First obtaining state values then based on values to generate slot types has made great progress in this task. However, obtaining state values is still …

The Mirrored Influence Hypothesis: Efficient Data Influence Estimation by Harnessing Forward Passes

2024

Large-scale black-box models have become ubiquitous across numerous applications. Understanding the influence of individual training data sources on predictions made by these models is crucial for improving their trustworthiness. Current influence estimation techniques involve computing …

Mind the Gap: Linguistic Divergence and Adaptation Strategies in Human-LLM Assistant vs. Human-Human Interactions

2025 · arXiv (Cornell University)

As Large Language Models (LLMs) are increasingly deployed in customer-facing applications, a critical yet underexplored question is how users communicate differently with LLM chatbots compared to human agent. In this study, we present empirical evidence …

Domain Adaptive Dialog Generation via Meta Learning

2019

Domain adaptation is an essential task in dialog system building because there are so many new dialog tasks created for different needs every day. Collecting and annotating training data for these new tasks is costly …

INSPIRED: Toward Sociable Recommendation Dialog Systems

2020

In recommendation dialogs, humans commonly disclose their preference and make recommendations in a friendly manner. However, this is a challenge in developing a sociable recommendation dialog system, due to the lack of dialog dataset annotated …