Shuo Yang

Quantum error mitigation via matrix product operators

2022 · arXiv (Cornell University)

In the era of noisy intermediate-scale quantum (NISQ) devices, the number of controllable hardware qubits is insufficient to implement quantum error correction (QEC). As an alternative, quantum error mitigation (QEM) can suppress errors in measurement …

Reliable Label Correction is a Good Booster When Learning with Extremely Noisy Labels

2022 · arXiv (Cornell University)

Learning with noisy labels has aroused much research interest since data annotations, especially for large-scale datasets, may be inevitably imperfect. Recent approaches resort to a semi-supervised learning problem by dividing training samples into clean and …

Mask and Regenerate: A Classifier-based Approach for Unpaired Sentiment Transformation of Reviews for Electronic Commerce Websites.

2022

Style transfer is the task of transferring a sentence into the target style while keeping its content. The major challenge is that parallel corpora are not available for various domains. In this paper, we propose …

Sentiment Analysis of COVID-19 on Weibo text using optimized Bi-LSTM model

2023 · Research Square

Abstract The outbreak of Coronavirus disease 2019 (COVID-19) poses a major challenge for China. Sentiment analysis of texts on social media such as Sina-Weibo in China can be useful for adjusting outbreak prevention policies and …

Definition and Detection of Defects in NFT Smart Contracts

2023 · arXiv (Cornell University)

Recently, the birth of non-fungible tokens (NFTs) has attracted great attention. NFTs are capable of representing users' ownership on the blockchain and have experienced tremendous market sales due to their popularity. Unfortunately, the high value …

Data-efficient Fine-tuning for LLM-based Recommendation

2024 · arXiv (Cornell University)

Leveraging Large Language Models (LLMs) for recommendation has recently garnered considerable attention, where fine-tuning plays a key role in LLMs' adaptation. However, the cost of fine-tuning LLMs on rapidly expanding recommendation data limits their practical …

Bridging the Gap: Unpacking the Hidden Challenges in Knowledge Distillation for Online Ranking Systems

2024

Knowledge Distillation (KD) is a powerful approach for compressing a large model into a smaller, more efficient model, particularly beneficial for latency-sensitive applications like recommender systems. However, current KD research predominantly focuses on Computer Vision …

AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety Basin

2025 · arXiv (Cornell University)

Fine-tuning large language models (LLMs) improves performance but introduces critical safety vulnerabilities: even minimal harmful data can severely compromise safety measures. We observe that perturbations orthogonal to the alignment direction - defined by weight differences …

Doubling Your Data in Minutes: Ultra-fast Tabular Data Generation via LLM-Induced Dependency Graphs

2025 · arXiv (Cornell University)

Tabular data is critical across diverse domains, yet high-quality datasets remain scarce due to privacy concerns and the cost of collection. Contemporary approaches adopt large language models (LLMs) for tabular augmentation, but exhibit two major …