cs.AI（2023-11-24）

📊 共 7 篇论文

🎯 兴趣领域导航

#	题目	一句话要点	标签
1	Efficient Open-world Reinforcement Learning via Knowledge Distillation and Autonomous Rule Discovery	提出基于知识蒸馏和自主规则发现的高效开放世界强化学习方法	reinforcement learning deep reinforcement learning distillation
2	Universal Jailbreak Backdoors from Poisoned Human Feedback	提出普适性监狱逃脱后门以应对RLHF模型的安全威胁	reinforcement learning RLHF large language model
3	How to ensure a safe control strategy? Towards a SRL for urban transit autonomous operation	提出SSA-DRL框架以解决城市轨道交通自主操作安全控制问题	reinforcement learning deep reinforcement learning DRL
4	Digital Twin-Native AI-Driven Service Architecture for Industrial Networks	提出数字双胞胎原生AI驱动服务架构以解决工业网络管理问题	reinforcement learning spatiotemporal

#	题目	一句话要点	标签
5	Large Language Models as Topological Structure Enhancers for Text-Attributed Graphs	提出利用大语言模型增强文本属性图的拓扑结构以提升节点分类性能	large language model
6	Human-Machine Cooperative Multimodal Learning Method for Cross-subject Olfactory Preference Recognition	提出多模态学习方法以解决跨主体嗅觉偏好识别问题	multimodal
7	Who is leading in AI? An analysis of industry AI research	分析行业AI研究，揭示领先企业贡献	large language model