A RL approach to enable cost-effective, intelligent interactions between a local agent and a remote LLM

Python code to implement LLM4Teach, a policy distillation approach for teaching reinforcement learning agents with Large Language Model

Python code to implement CO3, a fundamental-model based approach for open-world few-shot learning.

Python code to implement an efficient approach to unsupervised OOD detection with VAE

Python codes to implement Q-Net, a meta-learning method for few shot medical image segmentation

Adversarial Ensemble Training by Jointly Learning Label Dependencies and Member Models

Python code to implement hard sampling based task representation learning for robust offline meta RL

Code to implement Restormer-Plus, the Runner-up Solution to the GT-RAIN Challenge (CVPR 2023 UG2+ Track 3)

Python code to implement a commonsense knowledge inference module (CKIM) assisted deep learning method for visual object detection