A Toolbox for Adversarial Robustness Research

AGAIN: Adversarial Training with Attribution Span Enlargement and Hybrid Feature Fusion

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

The official PyTorch implementation - Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent from the Decision Boundary Perspective (CVPR'22).

(ICML 2024) The official code for EvoRainbow: Combining Improvements in Evolutionary Reinforcement Learning for Policy Search

Feature Separation and Recalibration (CVPR 2023 Highlights)

The official code of "Language-Driven Anchors for Zero-Shot Adversarial Robustness"

Official PyTorch implementation of ReBAT (ReBalanced Adversarial Training) in NeurIPS 2023 "Balance, Imbalance, and Rebalance: Understanding Robust Overfitting from a Minimax Game Perspective".

This is a project about Optical Character Recognition (OCR) in Vietnamese texts by using PaddleOCR and VietOCR.