cs.AI（2025-01-22）

📊 共 13 篇论文

🎯 兴趣领域导航

#	题目	一句话要点	标签
1	Understanding the LLM-ification of CHI: Unpacking the Impact of LLMs at CHI through a Systematic Literature Review	系统性文献综述揭示LLM在CHI研究中的应用、局限与未来机遇	large language model
2	MapColorAI: Designing Contextually Relevant Choropleth Map Color Schemes Using a Large Language Model	MapColorAI：利用大语言模型设计上下文相关的等值区域地图配色方案	large language model
3	Data Science Students Perspectives on Learning Analytics: An Application of Human-Led and LLM Content Analysis	结合RAG和LLM，分析数据科学学生对学习分析的视角	large language model
4	Revisit Self-Debugging with Self-Generated Tests for Code Generation	提出自生成测试的自调试方法，提升代码生成在复杂编程问题上的性能	large language model
5	Addressing Bias in Generative AI: Challenges and Research Opportunities in Information Management	提出解决生成式AI偏见的框架，提升信息管理系统在商业决策中的公平性和有效性。	large language model
6	FishBargain: An LLM-Empowered Bargaining Agent for Online Fleamarket Platform Sellers	FishBargain：面向闲置交易平台卖家的LLM议价智能体	large language model
7	Leveraging LLMs to Create a Haptic Devices' Recommendation System	利用LLM构建触觉设备推荐系统，解决触觉设备设计知识匮乏问题	large language model

#	题目	一句话要点	标签
8	Kimi k1.5: Scaling Reinforcement Learning with LLMs	Kimi k1.5：通过强化学习与长文本建模提升多模态大语言模型推理能力	reinforcement learning large language model
9	UAV-assisted Internet of Vehicles: A Framework Empowered by Reinforcement Learning and Blockchain	提出基于强化学习和区块链的无人机辅助车联网框架，实现可信赖的中继选择与协同。	reinforcement learning deep reinforcement learning PPO
10	Offline Critic-Guided Diffusion Policy for Multi-User Delay-Constrained Scheduling	提出SOCD算法，解决多用户延迟约束调度中的离线强化学习问题	reinforcement learning offline reinforcement learning diffusion policy
11	Reinforcement learning Based Automated Design of Differential Evolution Algorithm for Black-box Optimization	提出基于强化学习的差分进化算法自动设计框架，用于黑盒优化。	reinforcement learning
12	Deep Learning-Based Identification of Inconsistent Method Names: How Far Are We?	评估深度学习方法在识别不一致方法名上的局限性，并提出改进方向。	contrastive learning large language model
13	HEPPO-GAE: Hardware-Efficient Proximal Policy Optimization with Generalized Advantage Estimation	HEPPO-GAE：用于近端策略优化中广义优势估计的硬件高效加速器	reinforcement learning PPO