cs.AI（2024-12-06）

📊 共 24 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) (19 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (19 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Question Answering for Decisionmaking in Green Building Design: A Multimodal Data Reasoning Method Driven by Large Language Models	GreenQA：基于大语言模型的多模态数据推理，助力绿色建筑设计决策	large language model multimodal chain-of-thought
2	Parametric-ControlNet: Multimodal Control in Foundation Models for Precise Engineering Design Synthesis	Parametric-ControlNet：面向工程设计的精确可控多模态生成模型	foundation model multimodal
3	The Prompt Canvas: A Literature-Based Practitioner Guide for Creating Effective Prompts in Large Language Models	提出Prompt Canvas框架，系统化整理LLM提示工程方法，为从业者提供统一指导。	large language model chain-of-thought
4	MTSpark: Enabling Multi-Task Learning with Spiking Neural Networks for Generalist Agents	MTSpark：利用脉冲神经网络实现多任务学习，面向通用智能体	generalist agent
5	A Survey of Large Language Model-Based Generative AI for Text-to-SQL: Benchmarks, Applications, Use Cases, and Challenges	综述基于大语言模型的Text-to-SQL生成式AI：基准、应用、用例与挑战	large language model
6	Are Frontier Large Language Models Suitable for Q&A in Science Centres?	评估前沿大语言模型在科技馆问答互动中的适用性，探索趣味性与准确性的平衡。	large language model
7	Can Large Language Models Serve as Effective Classifiers for Hierarchical Multi-Label Classification of Scientific Documents at Industrial Scale?	提出结合LLM与稠密检索的零样本分层多标签分类方法，用于工业级科学文档分类。	large language model
8	Flash Communication: Reducing Tensor Parallelization Bottleneck for Fast Large Language Model Inference	Flash Communication：通过低比特压缩加速大语言模型张量并行推理	large language model
9	GUIDE: A Global Unified Inference Engine for Deploying Large Language Models in Heterogeneous Environments	GUIDE：异构环境下LLM全局统一推理引擎，优化部署性能。	large language model
10	A Survey of Sustainability in Large Language Models: Applications, Economics, and Challenges	综述大型语言模型可持续性：应用、经济与挑战	large language model
11	PyTerrier-GenRank: The PyTerrier Plugin for Reranking with Large Language Models	PyTerrier-GenRank：用于大型语言模型重排序的PyTerrier插件	large language model
12	REGENT: A Retrieval-Augmented Generalist Agent That Can Act In-Context in New Environments	提出REGENT：一种检索增强的通用智能体，可在新环境中进行上下文学习	generalist agent	✅
13	Smoothie: Label Free Language Model Routing	Smoothie：一种无标签的语言模型路由方法，提升多任务场景下的模型选择。	large language model
14	From Voice to Value: Leveraging AI to Enhance Spoken Online Reviews on the Go	Vocalizer：利用AI增强语音在线评论，提升用户体验与参与度	large language model
15	Technology as uncharted territory: Contextual integrity and the notion of AI as new ethical ground	强调AI伦理应重视既有社会规范，避免道德创新优先于道德保护	foundation model
16	From Defects to Demands: A Unified, Iterative, and Heuristically Guided LLM-Based Framework for Automated Software Repair and Requirement Realization	提出基于LLM的统一迭代框架，实现自动化软件修复与需求实现	large language model
17	HyperGraphOS: A Meta Operating System for Science and Engineering	HyperGraphOS：面向科学与工程领域的元操作系统，实现复杂模型动态管理	large language model
18	Neuro-Symbolic Data Generation for Math Reasoning	提出神经符号数据生成框架，提升LLM在数学推理中的能力。	large language model
19	Privacy-Preserving Retrieval-Augmented Generation with Differential Privacy	提出差分隐私检索增强生成算法，在保护隐私的同时生成高质量答案。	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	🔗	⭐
20	DRL4AOI: A DRL Framework for Semantic-aware AOI Segmentation in Location-Based Services	提出DRL4AOI框架，利用深度强化学习解决LBS中语义感知的AOI分割问题	reinforcement learning deep reinforcement learning DRL	✅
21	Reinforcement Learning: An Overview	深度强化学习综述：全面回顾价值、策略、模型方法及LLM应用	reinforcement learning offline RL
22	Measuring Goal-Directedness	提出最大熵目标导向性(MEG)度量，用于评估因果模型和MDP中的目标导向性。	reinforcement learning inverse reinforcement learning

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
23	Neural Representation for Wireless Radiation Field Reconstruction: A 3D Gaussian Splatting Approach	提出基于3D高斯溅射的无线辐射场重建方法，用于无线信道建模。	3D gaussian splatting gaussian splatting splatting

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
24	Short-term Streamflow and Flood Forecasting based on Graph Convolutional Recurrent Neural Network and Residual Error Learning	提出基于图卷积循环神经网络和残差学习的短期流量和洪水预测方法	spatiotemporal

⬅️ 返回 cs.AI 首页 · 🏠 返回主页