Yuan Xiaohan's Projects
Inspired by the idea of transfer learning, a combined approach is proposed. In the method, Deep Convolutional Neural Networks with Wide First-layer Kernel is used to extract features to classify the health conditions.
Official repository for the paper "ALERT: A Comprehensive Benchmark for Assessing Large Language Models’ Safety through Red Teaming"
About Code release for "Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy" (ICLR 2022 Spotlight), https://openreview.net/forum?id=LzQQ89U1qm_
A collection of AWESOME things about domian adaptation
Awesome-LLM: a curated list of Large Language Model
A curated list of security-related papers, articles, and resources focused on Large Language Models (LLMs). This repository aims to provide researchers, practitioners, and enthusiasts with insights into the security implications, challenges, and advancements surrounding these powerful models.
UP-TO-DATE LLM Watermark paper. 🔥🔥🔥
code for "Adversarial Feature Learning"
用python画冰墩墩!
Categorical Depth Distribution Network for Monocular 3D Object Detection (CVPR 2021 Oral)
🔮 ChatGPT Desktop Application (Mac, Windows and Linux)
CS231n 2019年春季学期课程作业
面向中文大模型价值观的评估与对齐研究
cvpr2021/cvpr2020/cvpr2019/cvpr2018/cvpr2017 论文/代码/解读/直播合集,极市团队整理
[CVPR2021] "Visualizing Adapted Knowledge in Domain Transfer". Visualization for domain adaptation. #explainable-ai
Code release for Discriminative Adversarial Domain Adaptation (AAAI2020).
Generate VOC format datasets from defective images in DAGM2007 dataset.
Official PyTorch implementation of DD3D: Is Pseudo-Lidar needed for Monocular 3D Object detection? (ICCV 2021), Dennis Park*, Rares Ambrus*, Vitor Guizilini, Jie Li, and Adrien Gaidon.
[CVPR2021] Pytorch implementation of Depth-conditioned Dynamic Message Propagation forMonocular 3D Object Detection.
DEEPSEC: A Uniform Platform for Security Analysis of Deep Learning Model
Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs
This project is to classify the state of the welding chip. Considering the complexity of the problem, only two classifications are carried out, namely normal and abnormal. Through the test of fully connected network, convolutional neural network and Fine-tuning Of Google Net, we found that fine-tuning of Google Net had the best effect, reaching the highest score of 70 out of a full score of 80.
Repository for few-shot learning machine learning projects
Few-shot Transfer Learning for Intelligent Fault Diagnosis of Machine