Yuan Li

Emergence of Classical Objectivity of Quantum Darwinism in a Photonic Quantum Simulator

2018 · arXiv (Cornell University)

Quantum-to-classical transition is a fundamental open question in physics frontier. Quantum decoherence theory points out that the inevitable interaction with environment is a sink carrying away quantum coherence, which is responsible for the suppression of …

Research on Entity Mention Recognition based on LSTM

2019

This paper proposes an improved neural network structure based on LSTM for recognizing entities in sentences. The deep learning model of LSTM has a label offset problem when performing sequence labeling tasks, because it does …

On the Teaching Mode of the Integration of General Communication Technology and Command Specialty Based on TRIZ Theory

2020 · Proceedings of the International Conference on Modern Educational Technology and Innovation and Entrepreneurship (ICMETIE 2020)

On the basis of combing the disadvantages of traditional teaching mode of general communication technology and command specialty, this paper innovatively uses TRIZ tool in integrated training teaching, and realizes the optimization of training mode …

YNU-HPCC at SemEval-2020 Task 8: Using a Parallel-Channel Model for Memotion Analysis

2020

In recent years, the growing ubiquity of Internet memes on social media platforms, such as Facebook, Instagram, and Twitter, has become a topic of immense interest. However, the classification and recognition of memes is much …

Adversarial Attacks on Video Object Segmentation with Hard Region Discovery

2023 · arXiv (Cornell University)

Video object segmentation has been applied to various computer vision tasks, such as video editing, autonomous driving, and human-robot interaction. However, the methods based on deep neural networks are vulnerable to adversarial examples, which are …

A fusion algorithm of central classification index and local classification index based on B+ tree

2023

This paper introduces a content-based, data-centered data search system for large-scale databases. Firstly, this paper designs the system from data source tracking module, data mining module and system warning module respectively. Then the software design …

1+1>2: Can Large Language Models Serve as Cross-Lingual Knowledge Aggregators?

2024 · arXiv (Cornell University)

Large Language Models (LLMs) have garnered significant attention due to their remarkable ability to process information across various languages. Despite their capabilities, they exhibit inconsistencies in handling identical queries in different languages, presenting challenges for …

Few-Shot Joint Multimodal Entity-Relation Extraction via Knowledge-Enhanced Cross-modal Prompt Model

2024

Joint Multimodal Entity-Relation Extraction (JMERE) is a challenging task that aims to extract entities and their relations from textimage pairs in social media posts. Existing methods for JMERE require large amounts of labeled data. However, …

<scp>MetaAgents:</scp> Large Language Model Based Agents for Decision-Making on Teaming

2025 · Proceedings of the ACM on Human-Computer Interaction

Significant advancements have occurred in the application of Large Language Models (LLMs) for social simulations. Despite this, their abilities to perform teaming in task-oriented social events are underexplored. Such capabilities are crucial if LLMs are …

Pruning Self-Attention With Local and Syntactic Dependencies for Aspect Sentiment Triplet Extraction

2025 · IEEE Transactions on Audio Speech and Language Processing

Aspect-based sentiment triple extraction (ASTE) is a demanding and emerging subtask of aspect-based sentiment analysis (ABSA). The primary objective of ASTE is to extract aspect and opinion terms and their corresponding sentiment polarities from a …

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 …

Learning how to Active Learn: A Deep Reinforcement Learning Approach

2017

Active learning aims to select a small subset of data for annotation such that a classifier learned on the data is highly accurate. This is usually done using heuristic selection methods, however the effectiveness of …

Optimus: Organizing Sentences via Pre-trained Modeling of a Latent Space

2020

When trained effectively, the Variational Autoencoder (VAE) In this paper, we propose the first large-scale language VAE model OPTIMUS 1 . A universal latent embedding space for sentences is first pre-trained on large text corpus, …