cs.LG（2024-09-24）
📊 共 5 篇论文
🎯 兴趣领域导航
🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Federated Large Language Models: Current Progress and Future Directions | 综述联邦大语言模型(FedLLM)的最新进展与未来方向，聚焦微调与提示学习。 | large language model | ||
| 2 | The Dark Side of Rich Rewards: Understanding and Mitigating Noise in VLM Rewards | 提出BiMI奖励函数，解决VLM奖励中的噪声问题，提升具身智能导航性能 | multimodal | ||
| 3 | Quality Matters: Evaluating Synthetic Data for Tool-Using LLMs | 提出两种数据质量评估方法，提升工具型LLM的合成数据训练效果 | large language model | ||
| 4 | Merging LoRAs like Playing LEGO: Pushing the Modularity of LoRA to Extremes Through Rank-Wise Clustering | 提出LoRA-LEGO框架以优化LoRA合并问题 | large language model | ||
| 5 | iGAiVA: Integrated Generative AI and Visual Analytics in a Machine Learning Workflow for Text Classification | 提出iGAiVA，利用可视分析指导生成式AI进行文本分类数据增强，提升模型精度。 | large language model |