-
Southern University of Science and Technology
- Singapore
- https://hongxin001.github.io/
Starred repositories
Materials for STAT 991: Topics In Modern Statistical Learning (UPenn, 2022 Spring) - uncertainty quantification, conformal prediction, calibration, etc
A Python toolbox for conformal prediction research on deep learning models, using PyTorch.
IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language Models
QLoRA: Efficient Finetuning of Quantized LLMs
A playbook for systematically maximizing the performance of deep learning models.
This repository contains a Jax implementation of conformal training corresponding to the ICLR'22 paper "learning optimal conformal classifiers".
Awesome Lists for Tenure-Track Assistant Professors and PhD students. (助理教授/博士生生存指南)
🚀AI拟声: 5秒内克隆您的声音并生成任意语音内容 Clone a voice in 5 seconds to generate arbitrary speech in real-time
Code for ICLR 2022 Paper, "Controlling Directions Orthogonal to a Classifier"
Distilling Model Failures as Directions in Latent Space
Official code for ICML 2022: Mitigating Neural Network Overconfidence with Logit Normalization
CVPR'20: Combating Noisy Labels by Agreement: A Joint Training Method with Co-Regularization
[NeurIPS 2021] Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training
autodp: A flexible and easy-to-use package for differential privacy
Repository for collection of research papers on privacy.
Adversarial Defense for Ensemble Models (ICML 2019)
Awesome Knowledge Distillation
Official Tensorflow implementation of U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation (ICLR 2020)
Code for 'Joint Optimization Framework for Learning with Noisy Labels'
Rob-GAN: Generator, Discriminator and Adversarial Attacker
A collection of important graph embedding, classification and representation learning papers with implementations.
Graph Distillation for Action Detection
Spatially Transformed Adversarial Examples with TensorFlow