cs.LG（2024-05-02）
📊 共 5 篇论文 | 🔗 3 篇有代码
🎯 兴趣领域导航
🔬 支柱九：具身大模型 (Embodied Foundation Models) (4 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | A separability-based approach to quantifying generalization: which layer is best? | 提出一种基于可分性的泛化能力评估方法，用于确定深度网络中最适合泛化的层。 | foundation model | ✅ | |
| 2 | ALCM: Autonomous LLM-Augmented Causal Discovery Framework | 提出ALCM框架，结合LLM与因果发现算法，自动生成更准确可解释的因果图。 | large language model | ||
| 3 | COPAL: Continual Pruning in Large Language Generative Models | 提出COPAL以解决大语言生成模型的持续适应性问题 | large language model | ||
| 4 | Boosting Jailbreak Attack with Momentum | 提出动量加速GCG攻击（MAC），提升LLM越狱攻击的成功率和效率。 | large language model | ✅ |
🔬 支柱一：机器人控制 (Robot Control) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 5 | Plan-Seq-Learn: Language Model Guided RL for Solving Long Horizon Robotics Tasks | Plan-Seq-Learn：利用语言模型引导强化学习解决长时程机器人任务 | motion planning reinforcement learning large language model | ✅ |