Li Zhang

Application and Practice of Information Technology under the Project Management of College Student’s Innovative and Entrepreneurial Training Program

2015 · Advances in economics, business and management research/Advances in Economics, Business and Management Research

With the most extensive coverage and as the most influential project ,College S tudents' Innovative and Entrepreneurial Training Program belonging to Teaching Quality and Reform Project of Undergraduate Teaching in Colleges and Universities ,the project …

The Tutor Training Method of the New College Teachers

2015

This paper combines the new teachers' needs and the college development together; it analyzes the existing problems in the training courses, colleges work, and even everyday life of young teachers. Then our colleges find a …

Nearly-optimal private LASSO

2015 · Neural Information Processing Systems

We present a nearly optimal differentially private version of the well known LASSO estimator. Our algorithm provides privacy protection with respect to each training example. The excess risk of our algorithm, compared to the non-private …

Learning Differentially Private Recurrent Language Models

2017 · arXiv (Cornell University)

We demonstrate that it is possible to train large recurrent language models with user-level differential privacy guarantees with only a negligible cost in predictive accuracy. Our work builds on recent advances in the training of …

Review of Deep Neural Network Based on Auto-encoder

2019 · DEStech Transactions on Computer Science and Engineering

Deep Learning gets a new research direction of machine learning. After years of deep learning development, researchers have put forward several types of neural network built on the Auto-encoder. In this article, firstly, the origins …

Research on Application of Blockchain Technology in Cloud-Network Collaboration

2020

With the deep integration of blockchain, cloud computing and 5G technology, the business model of the Internet is also undergoing subversive changes. Based on the current development trends of the industry, this article illustrates the …

Intent Detection with WikiHow

2020 · arXiv (Cornell University)

Modern task-oriented dialog systems need to reliably understand users' intents. Intent detection is most challenging when moving to new domains or new languages, since there is little annotated data. To address this challenge, we present …

TEAC: Intergrating Trust Region and Max Entropy Actor Critic for Continuous Control

2021

Trust region methods and maximum entropy methods are two state-of-the-art branches used in reinforcement learning (RL) for the benefits of stability and exploration in continuous environments, respectively. This paper proposes to integrate both branches in …

Efficient determination of enantiomeric ratios of α-hydroxy/amino acids from fermented milks via ion mobility-mass spectrometry.

2023 · PubMed

]-estradiol-3-benzoate-17β-chloroformate labeling-assisted ion mobility - mass spectrometry. Results revealed extensive variation in chiral HA/AA profiles among 15 fermented milks. A total of 14 D-HA/AAs were identified. d-Lactic acid and d-alanine appeared as the most discriminatory …

Bidirectional Self-Training with Multiple Anisotropic Prototypes for Domain Adaptive Semantic Segmentation

2022 · arXiv (Cornell University)

A thriving trend for domain adaptive segmentation endeavors to generate the high-quality pseudo labels for target domain and retrain the segmentor on them. Under this self-training paradigm, some competitive methods have sought to the latent-space …

TSUP Speaker Diarization System for Conversational Short-phrase Speaker Diarization Challenge

2022 · arXiv (Cornell University)

This paper describes the TSUP team's submission to the ISCSLP 2022 conversational short-phrase speaker diarization (CSSD) challenge which particularly focuses on short-phrase conversations with a new evaluation metric called conversational diarization error rate (CDER). In …

Research on Key Technologies of Smart City Building Interior Decoration Construction based on In-Depth Learning

2022 · International Journal of Advanced Computer Science and Applications

The intelligentization of building interior decoration construction is of great significance to the construction of smart city, and robot automation has brought an opportunity for this. Robot self-decoration is the development trend in the future. …

Effective Random Test Generation for Deep Learning Compilers

2023 · arXiv (Cornell University)

Deep learning compilers help address the difficulties of deploying deep learning models on diverse types of hardware. Testing deep learning compilers is highly crucial, because they are impacting countless AI applications that use them for …

Human-in-the-loop Schema Induction

2023

Tianyi Zhang, Isaac Tham, Zhaoyi Hou, Jiaxuan Ren, Leon Zhou, Hainiu Xu, Li Zhang, Lara J. Martin, Rotem Dror, Sha Li, Heng Ji, Martha Palmer, Susan Windisch Brown, Reece Suchocki, Chris Callison-Burch. Proceedings of the …

Curriculum Teaching and Research Based on Cloud Computing and Big Data

2024 · SHS Web of Conferences

This study investigates the integrated application of cloud computing and big data in the field of education and its impact on curriculum teaching. Through a comprehensive review of the fundamental principles, current applications, and relevant …

6MCBLM: Multi-scale CNN and BiLSTM-Attention Hybrid Model for IPv6 Target Generation

2024

Rapid scanning of IPv6 addresses is crucial for understanding the network profile of IPv6. However, due to the vast address space of IPv6, achieving complete traversal scanning is difficult. Therefore, the key to scanning the …

Imperfect Code Generation: Uncovering Weaknesses in Automatic Code Generation by Large Language Models

2024

The task of code generation has received significant attention in recent years, especially when the pre-trained large language models (LLMs) for code have consistently achieved state-of-the-art performance. However, there is currently a lack of a …

Research on Quality Evaluation of Multi-State Data of Substation Equipment Based on Game Theory Combined Weighting-Comprehensive Evaluation

2024

Based on the game theory combination weighting-comprehensive evaluation method, this paper proposes a new method for evaluating the quality of polymorphic data. By building a data quality evaluation system for five indicators of integrity, accuracy, …

Application of Contrastive Learning Based on ResNet34 in Unsupervised Image Classification

2025

In response to the problems of insufficient labeled data and feature complexity in industrial scenarios, this paper proposes an unsupervised contrastive learning model framework based on ResNet34. This method combines the powerful feature extraction capability …

A Vision for Auto Research with LLM Agents

2025 · arXiv (Cornell University)

This paper introduces Agent-Based Auto Research, a structured multi-agent framework designed to automate, coordinate, and optimize the full lifecycle of scientific research. Leveraging the capabilities of large language models (LLMs) and modular agent collaboration, the …

On the Difficulty of Evaluating Baselines: A Study on Recommender Systems

2019 · arXiv (Cornell University)

Numerical evaluations with comparisons to baselines play a central role when judging research in recommender systems. In this paper, we show that running baselines properly is difficult. We demonstrate this issue on two extensively studied …