cs.AI（2024-09-30）

📊 共 24 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (14 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (8 🔗1) 支柱八：物理动画 (Physics-based Animation) (1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (14 篇)

#题目一句话要点标签🔗⭐
1 Robin3D: Improving 3D Large Language Model via Robust Instruction Tuning Robin3D：通过鲁棒指令调优提升3D大型语言模型性能 large language model multimodal instruction following
2 Efficient Driving Behavior Narration and Reasoning on Edge Device Using Large Language Models 提出基于边缘设备LLM的驾驶行为叙述与推理框架，提升响应速度与性能 large language model
3 Law of the Weakest Link: Cross Capabilities of Large Language Models CrossEval：揭示大语言模型跨能力短板，推动复杂场景性能优化 large language model
4 A Knowledge-Informed Large Language Model Framework for U.S. Nuclear Power Plant Shutdown Initiating Event Classification for Probabilistic Risk Assessment 提出一种知识驱动的大语言模型框架，用于美国核电站停堆初始事件分类。 large language model
5 GUNDAM: Aligning Large Language Models with Graph Understanding GUNDAM：通过图理解对齐大型语言模型，提升图结构数据推理能力 large language model
6 What is the Role of Large Language Models in the Evolution of Astronomy Research? 探索大型语言模型在天文学研究中的作用与潜力 large language model
7 Mitigating Propensity Bias of Large Language Models for Recommender Systems 提出CLLMR框架，缓解大语言模型推荐系统中的倾向性偏差和维度坍塌问题 large language model
8 Customized Information and Domain-centric Knowledge Graph Construction with Large Language Models 提出基于知识图谱的框架，利用大语言模型构建定制化领域知识，提升网络物理系统规划。 large language model
9 On The Planning Abilities of OpenAI's o1 Models: Feasibility, Optimality, and Generalizability 评估OpenAI o1模型在规划任务中的可行性、最优性和泛化能力 large language model ✅
10 What Information Contributes to Log-based Anomaly Detection? Insights from a Configurable Transformer-Based Approach 提出可配置Transformer的日志异常检测方法，探究不同信息对异常检测的贡献。 TAMP
11 Interactive Speculative Planning: Enhance Agent Efficiency through Co-design of System and User Interface 提出交互式推测规划，通过系统与用户界面协同设计提升Agent效率 large language model
12 LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigation 针对代码生成中LLM幻觉问题，提出RAG方法并在仓库级场景验证有效性 large language model ✅
13 Resource Allocation for Stable LLM Training in Mobile Edge Computing 提出基于移动边缘计算的LLM稳定训练资源分配方案，优化能耗与延迟。 large language model
14 Semantic Alignment-Enhanced Code Translation via an LLM-Based Multi-Agent System 提出TRANSAGENT，利用多Agent协同和语义对齐提升LLM代码翻译质量 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (8 篇)

#题目一句话要点标签🔗⭐
15 Mitigating Backdoor Threats to Large Language Models: Advancement and Challenges 综述性研究：大型语言模型后门攻击的威胁、防御与挑战 reinforcement learning RLHF large language model
16 Meta Reinforcement Learning Approach for Adaptive Resource Optimization in O-RAN 提出基于元深度强化学习的自适应资源优化方法，提升O-RAN网络管理性能。 reinforcement learning deep reinforcement learning DRL
17 Enhancing GANs with Contrastive Learning-Based Multistage Progressive Finetuning SNN and RL-Based External Optimization 提出基于对比学习的多阶段渐进微调SNN与RL优化GAN，提升病理图像生成质量。 reinforcement learning contrastive learning
18 Stream-level flow matching with Gaussian processes 提出基于高斯过程的流级别匹配方法，提升连续归一化流的生成质量。 flow matching
19 Inferring Preferences from Demonstrations in Multi-objective Reinforcement Learning 提出动态权重偏好推断算法，从演示中学习多目标强化学习偏好 reinforcement learning
20 SWIM: Short-Window CNN Integrated with Mamba for EEG-Based Auditory Spatial Attention Decoding 提出SWIM模型，结合短窗CNN与Mamba，用于脑电信号的听觉空间注意力解码。 Mamba ✅
21 Dynamic Policy Fusion for User Alignment Without Re-Interaction 提出动态策略融合方法，无需重交互实现用户偏好对齐 reinforcement learning deep reinforcement learning
22 Possible Principles for Aligned Structure Learning Agents 提出一种基于结构学习的人工智能对齐框架，旨在构建能理解人类偏好的智能体。 world model representation learning

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

#题目一句话要点标签🔗⭐
23 StreamEnsemble: Predictive Queries over Spatiotemporal Streaming Data StreamEnsemble：针对时空流数据的预测查询，动态选择和分配机器学习模型。 spatiotemporal

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
24 The age of spiritual machines: Language quietus induces synthetic altered states of consciousness in artificial intelligence 语言静默诱导AI产生合成的意识改变状态 manipulation multimodal

⬅️ 返回 cs.AI 首页 · 🏠 返回主页