cs.AI（2024-11-12）

📊 共 17 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (12) 支柱二：RL算法与架构 (RL & Architecture) (5)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (12 篇)

#题目一句话要点标签🔗⭐
1 Leveraging Multimodal Models for Enhanced Neuroimaging Diagnostics in Alzheimer's Disease 利用多模态模型增强阿尔茨海默病神经影像诊断 large language model multimodal
2 Is Cognition Consistent with Perception? Assessing and Mitigating Multimodal Knowledge Conflicts in Document Understanding 提出多模态知识一致性微调方法，解决文档理解中认知与感知冲突问题 large language model multimodal
3 Challenges in Guardrailing Large Language Models for Science 为科学领域大语言模型构建安全护栏，应对时间敏感性等挑战 large language model
4 Can adversarial attacks by large language models be attributed? 研究表明，仅凭LLM输出难以归因对抗攻击，模型数量爆炸加剧了归因难度。 large language model
5 Training Data for Large Language Model 综述大规模语言模型训练数据，关注数据规模、类型、处理流程与开源数据集。 large language model
6 Improving Grapheme-to-Phoneme Conversion through In-Context Knowledge Retrieval with Large Language Models 提出基于大语言模型上下文知识检索的字素音素转换方法，提升歧义消解能力 large language model
7 Evaluating ChatGPT-3.5 Efficiency in Solving Coding Problems of Different Complexity Levels: An Empirical Analysis 评估ChatGPT-3.5在解决不同难度编码问题上的效率：一项实证分析 large language model chain-of-thought
8 Towards Low-bit Communication for Tensor Parallel LLM Inference 提出一种低比特通信量化方法，用于张量并行LLM推理，降低通信开销。 large language model
9 BudgetMLAgent: A Cost-Effective LLM Multi-Agent system for Automating Machine Learning Tasks 提出BudgetMLAgent，一种低成本LLM多智能体系统，用于自动化机器学习任务。 large language model
10 Retrieval, Reasoning, Re-ranking: A Context-Enriched Framework for Knowledge Graph Completion 提出KGR3框架，通过检索、推理和重排序增强知识图谱补全。 large language model
11 A Comprehensive Survey of AI-Driven Advancements and Techniques in Automated Program Repair and Code Generation 综述AI驱动的自动化程序修复与代码生成技术进展，聚焦大语言模型应用 large language model
12 LLM App Squatting and Cloning LLM应用商店中恶意应用泛滥：提出LLMappCrazy工具，大规模分析应用抢注和克隆问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
13 Learning with Less: Knowledge Distillation from Large Language Models via Unlabeled Data 提出LLKD：利用无标签数据，通过知识蒸馏从大语言模型中学习，提升小模型性能。 distillation large language model
14 Constrain Alignment with Sparse Autoencoders 提出基于稀疏自编码器的特征级约束偏好优化方法，高效稳定地对齐大型语言模型。 reinforcement learning RLHF DPO
15 World Models: The Safety Perspective 分析世界模型安全性，为AI Agent可信应用提供技术挑战与展望 world model large language model
16 SAV-SE: Scene-aware Audio-Visual Speech Enhancement with Selective State Space Model 提出SAV-SE以解决语音增强中的环境视觉信息缺失问题 Mamba state space model
17 Exploring Multi-Agent Reinforcement Learning for Unrelated Parallel Machine Scheduling 提出基于多智能体强化学习的并行机调度方法，解决复杂工业调度难题。 reinforcement learning PPO

⬅️ 返回 cs.AI 首页 · 🏠 返回主页