Search Results for author:
Found 2 papers, 2 papers with code
RICE: Breaking Through the Training Bottlenecks of Reinforcement Learning with Explanation
In this paper, we propose RICE, an innovative refining scheme for reinforcement learning that incorporates explanation methods to break through the training bottlenecks.
Assessing Prompt Injection Risks in 200+ Custom GPTs
In the rapidly evolving landscape of artificial intelligence, ChatGPT has been widely used in various applications.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
