| 1 |
PromSec: Prompt Optimization for Secure Generation of Functional Source Code with Large Language Models (LLMs) |
PromSec：通过提示优化，安全生成大语言模型的功能性源代码 |
contrastive learning large language model |
|
|
| 2 |
Evaluating Defences against Unsafe Feedback in RLHF |
评估RLHF中针对不安全反馈的防御机制，揭示现有方法的局限性。 |
reinforcement learning RLHF large language model |
|
|
| 3 |
Training Language Models to Self-Correct via Reinforcement Learning |
提出SCoRe，通过强化学习显著提升大语言模型的自我纠错能力 |
reinforcement learning large language model |
|
|
| 4 |
Privacy-Preserving Student Learning with Differentially Private Data-Free Distillation |
提出基于差分隐私无数据蒸馏的隐私保护学生学习方法 |
teacher-student distillation |
|
|
| 5 |
Assessing the Zero-Shot Capabilities of LLMs for Action Evaluation in RL |
提出CALM框架，利用LLM零样本能力解决强化学习中的动作评估问题 |
reinforcement learning reward shaping large language model |
|
|
| 6 |
Revisiting Semi-supervised Adversarial Robustness via Noise-aware Online Robust Distillation |
提出SNORD框架，通过噪声感知在线鲁棒蒸馏提升半监督对抗鲁棒性，无需预训练模型。 |
distillation |
|
|
| 7 |
Disentangling Recognition and Decision Regrets in Image-Based Reinforcement Learning |
提出基于图像强化学习的识别后悔与决策后悔解耦方法，提升泛化性能 |
reinforcement learning |
|
|
| 8 |
The Central Role of the Loss Function in Reinforcement Learning |
强化学习中损失函数的中心作用：影响样本效率和自适应性 |
reinforcement learning |
|
|
| 9 |
VCAT: Vulnerability-aware and Curiosity-driven Adversarial Training for Enhancing Autonomous Vehicle Robustness |
提出VCAT，增强自动驾驶车辆在对抗攻击下的鲁棒性 |
reinforcement learning distillation |
✅ |
|