cs.AI（2024-11-29）

📊 共 15 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) (10 🔗1) 支柱一：机器人控制 (Robot Control) (3 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (10 篇)

#题目一句话要点标签🔗⭐
1 Multimodal Whole Slide Foundation Model for Pathology 提出TITAN：一种用于病理学的多模态全切片基础模型，提升罕见疾病检索和癌症预后。 foundation model multimodal
2 VLSBench: Unveiling Visual Leakage in Multimodal Safety VLSBench：揭示多模态安全评估中视觉信息的文本泄露问题 large language model multimodal ✅
3 LUMIA: Linear probing for Unimodal and MultiModal Membership Inference Attacks leveraging internal LLM states LUMIA：利用LLM内部状态的线性探针进行单模态和多模态成员推理攻击检测 large language model multimodal
4 Scaling Transformers for Low-Bitrate High-Quality Speech Coding 提出基于Transformer和有限标量量化的语音编码模型，在极低码率下实现高质量语音 multimodal
5 Action Engine: Automatic Workflow Generation in FaaS Action Engine：利用工具增强的LLM自动生成FaaS工作流 large language model
6 Streamlining the review process: AI-generated annotations in research manuscripts 提出AnnotateGPT平台，利用LLM辅助学术论文评审，提升评审效率。 large language model
7 Generating a Low-code Complete Workflow via Task Decomposition and RAG 形式化任务分解与RAG为GenAI系统设计模式，并应用于低代码工作流生成。 foundation model
8 An AI-Driven Data Mesh Architecture Enhancing Decision-Making in Infrastructure Construction and Public Procurement 提出基于AI驱动的数据网格架构，提升基础设施建设和公共采购的决策效率。 large language model
9 Advanced System Integration: Analyzing OpenAPI Chunking for Retrieval-Augmented Generation 提出基于RAG的OpenAPI分块方法，优化LLM系统集成中的端点发现。 large language model
10 Knowledge Management for Automobile Failure Analysis Using Graph RAG 提出一种优化的Graph RAG方法，用于汽车故障分析知识管理。 large language model

🔬 支柱一：机器人控制 (Robot Control) (3 篇)

#题目一句话要点标签🔗⭐
11 PDDLFuse: A Tool for Generating Diverse Planning Domains PDDLFuse：生成多样化规划领域的工具，提升规划算法的泛化能力 domain randomization reinforcement learning large language model
12 FLARE: Toward Universal Dataset Purification against Backdoor Attacks 提出FLARE以解决后门攻击下的数据集净化问题 manipulation ✅
13 Quantized Delta Weight Is Safety Keeper 量化Delta权重在降低资源需求的同时，意外提升了微调语言模型的安全性。 manipulation

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
14 A Local Information Aggregation based Multi-Agent Reinforcement Learning for Robot Swarm Dynamic Task Allocation 提出基于局部信息聚合的多智能体强化学习方法，解决机器人集群动态任务分配问题。 reinforcement learning
15 o1-Coder: an o1 Replication for Coding O1-CODER：基于强化学习和蒙特卡洛树搜索的代码生成模型复现 reinforcement learning world model ✅

⬅️ 返回 cs.AI 首页 · 🏠 返回主页