cs.LG（2024-07-22）
📊 共 4 篇论文
🎯 兴趣领域导航
🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Attention Is All You Need But You Don't Need All Of It For Inference of Large Language Models | 通过选择性丢弃层，加速大语言模型Llama-v2的推理过程 | large language model | ||
| 2 | Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs | 提出目标导向的隐空间对抗训练，提升LLM对有害行为的鲁棒性 | large language model | ||
| 3 | Fundamental Limits of Prompt Compression: A Rate-Distortion Framework for Black-Box Language Models | 提出基于率失真理论的提示压缩框架，用于优化黑盒语言模型的提示。 | large language model |
🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 4 | Comprehensive Overview of Reward Engineering and Shaping in Advancing Reinforcement Learning Applications | 综述强化学习中奖励工程与塑造技术，提升算法效率与效果 | reinforcement learning reward shaping |