Tianyu Pang P2333

Achievements

Achievements

Organizations

Pinned Loading

1. Tencent-Hunyuan/UniRL Tencent-Hunyuan/UniRL Public

   UniRL is a Framework for Unified Multimodal Model Reinforcement Learning

   Python 903 62

2. Bag-of-Tricks-for-AT Bag-of-Tricks-for-AT Public

   Empirical tricks for training robust models (ICLR 2021)

   Python 259 26

3. Max-Mahalanobis-Training Max-Mahalanobis-Training Public

   Max Mahalanobis Training (ICML 2018 + ICLR 2020)

   Python 90 18

4. Reverse-Cross-Entropy Reverse-Cross-Entropy Public

   Reverse Cross Entropy for Adversarial Detection (NeurIPS 2018)

   Python 48 10

5. Adaptive-Diversity-Promoting Adaptive-Diversity-Promoting Public

   Adversarial Defense for Ensemble Models (ICML 2019)

   Python 61 11

6. SCORE SCORE Public

   A Self-Consistent Robust Error (ICML 2022)

   Python 69 5