cs.AI（2024-10-29）

📊 共 8 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (4 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1) 支柱五：交互与反应 (Interaction & Reaction) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (4 篇)

#题目一句话要点标签🔗⭐
1 ADAM: An Embodied Causal Agent in Open-World Environments ADAM：一个在开放世界环境中具身因果智能体 large language model multimodal ✅
2 Advancing Agentic Systems: Dynamic Task Decomposition, Tool Integration and Evaluation using Novel Metrics and Dataset 提出Agentic系统框架与评估方法，提升复杂任务处理的响应性和可扩展性。 large language model
3 MARCO: Multi-Agent Real-time Chat Orchestration 提出MARCO：一个用于自动化任务的多智能体实时聊天编排框架 large language model
4 Rethinking Code Refinement: Learning to Judge Code Efficiency 提出基于代码语言模型的代码效率判别方法，用于评估代码改进效果。 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
5 Robot Policy Learning with Temporal Optimal Transport Reward 提出基于时序最优传输奖励的机器人策略学习方法，提升模仿学习效果 reinforcement learning policy learning ✅
6 Predicting Future Actions of Reinforcement Learning Agents 针对不同类型强化学习智能体，提出基于内部状态和模拟的未来行为预测方法。 reinforcement learning world model
7 From Silos to Systems: Process-Oriented Hazard Analysis for AI Systems 提出面向AI系统的过程导向型风险分析方法PHASE，系统性识别和缓解AI系统风险。 reinforcement learning affordance

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#题目一句话要点标签🔗⭐
8 $\mathsf{OPA}$: One-shot Private Aggregation with Single Client Interaction and its Applications to Federated Learning 提出OPA以解决安全计算中的交互成本问题 OMOMO

⬅️ 返回 cs.AI 首页 · 🏠 返回主页