Search Results for author:
Found 2 papers, 0 papers with code
Adaptive Dense Reward: Understanding the Gap Between Action and Reward Space in Alignment
Our method improves the success rate on adversarial samples by 10\% compared to the sample-wise approach, and achieves a 1. 3\% improvement on evaluation benchmarks such as MMLU, GSM8K, HumanEval, etc.
Learning Robust and Lightweight Model through Separable Structured Transformations
Learning deep models with both lightweight and robustness is necessary for these equipments.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
