cs.LG(2024-07-06)

📊 共 6 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九:具身大模型 (Embodied Foundation Models) (3 🔗1) 支柱二:RL算法与架构 (RL & Architecture) (2) 支柱四:生成式动作 (Generative Motion) (1)

🔬 支柱九:具身大模型 (Embodied Foundation Models) (3 篇)

#题目一句话要点标签🔗
1 RULE: Reliable Multimodal RAG for Factuality in Medical Vision Language Models 提出RULE,通过可靠多模态RAG提升医学视觉语言模型的事实准确性 multimodal
2 Synthetic Data Aided Federated Learning Using Foundation Models 提出DPSDA-FL,利用合成数据和联邦学习解决非独立同分布数据下的模型性能下降问题。 foundation model
3 Code Less, Align More: Efficient LLM Fine-tuning for Code Generation with Data Pruning 提出基于数据剪枝的高效LLM微调方法,提升代码生成性能 large language model

🔬 支柱二:RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗
4 A Novel Bifurcation Method for Observation Perturbation Attacks on Reinforcement Learning Agents: Load Altering Attacks on a Cyber Physical Power System 提出基于分岔层的新型观测扰动攻击方法,用于攻击强化学习控制的电力系统 reinforcement learning deep reinforcement learning DRL
5 Multi-agent Off-policy Actor-Critic Reinforcement Learning for Partially Observable Environments 提出一种基于社交学习的多智能体离策略Actor-Critic算法,用于解决部分可观测环境下的强化学习问题。 reinforcement learning

🔬 支柱四:生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗
6 Balance of Number of Embedding and their Dimensions in Vector Quantization 提出自适应动态量化方法,优化VQ-VAE中码本大小与嵌入维度的平衡。 VQ-VAE

⬅️ 返回 cs.LG 首页 · 🏠 返回主页