cs.AI（2023-12-10）

📊 共 7 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) (4) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗1) 支柱一：机器人控制 (Robot Control) (1)

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

#	题目	一句话要点	标签	🔗	⭐
1	Multimodality of AI for Education: Towards Artificial General Intelligence	多模态AI赋能教育：迈向通用人工智能的教育应用	multimodal
2	Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs	对比微调与检索增强生成，探究知识注入大语言模型的有效方法	large language model
3	Mutual Enhancement of Large and Small Language Models with Cross-Silo Knowledge Transfer	提出CrossLM，通过跨孤岛知识迁移实现大模型与小模型的互增强	large language model
4	Toward Open-ended Embodied Tasks Solving	提出DOG框架，解决具身智能在开放式任务中的规划与控制问题	embodied AI

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

#	题目	一句话要点	标签	🔗	⭐
5	Large Multimodal Model Compression via Efficient Pruning and Distillation at AntGroup	蚂蚁集团提出基于剪枝与蒸馏的多阶段压缩方法，用于压缩大型多模态模型AntGMM。	distillation multimodal	✅
6	Synergizing Quality-Diversity with Descriptor-Conditioned Reinforcement Learning	提出DCRL-MAP-Elites算法，利用描述符条件强化学习提升质量多样性算法在高维控制任务中的性能。	reinforcement learning

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
7	Graph-based Prediction and Planning Policy Network (GP3Net) for scalable self-driving in dynamic environments using Deep Reinforcement Learning	提出基于图预测与规划策略网络(GP3Net)，用于动态环境中可扩展的自动驾驶。	motion planning reinforcement learning deep reinforcement learning

⬅️ 返回 cs.AI 首页 · 🏠 返回主页