cs.AI（2025-04-18）

📊 共 21 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (16) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (16 篇)

#题目一句话要点标签🔗⭐
1 6G WavesFM: A Foundation Model for Sensing, Communication, and Localization WavesFM：用于通信、感知和定位的6G无线通信基础模型 foundation model
2 Metacognition and Uncertainty Communication in Humans and Large Language Models 探讨LLM的元认知能力与不确定性沟通，对比人机差异以促进人机协作。 large language model
3 Multi-Stage Retrieval for Operational Technology Cybersecurity Compliance Using Large Language Models: A Railway Casestudy 提出基于LLM多阶段检索的OT网络安全合规性验证方法，以应对铁路等关键基础设施的网络安全挑战。 large language model
4 Large Language Models Will Change The Way Children Think About Technology And Impact Every Interaction Paradigm 大型语言模型将变革儿童认知技术的方式并影响所有交互模式 large language model
5 Exploring the Potential for Large Language Models to Demonstrate Rational Probabilistic Beliefs 揭示大型语言模型在理性概率信念表达上的不足 large language model
6 Evolution of Optimization Algorithms for Global Placement via Large Language Models 提出基于大语言模型的优化算法演化框架以解决全局布局问题 large language model
7 Large Language Models for Validating Network Protocol Parsers PARVAL：利用大语言模型验证网络协议解析器的正确性 large language model
8 Do Prompt Patterns Affect Code Quality? A First Empirical Assessment of ChatGPT-Generated Code 评估提示模式对ChatGPT生成代码质量的影响：一项初步实证研究 large language model chain-of-thought
9 CPR: Leveraging LLMs for Topic and Phrase Suggestion to Facilitate Comprehensive Product Reviews CPR：利用LLM进行主题和短语推荐，促进全面的产品评论生成。 large language model
10 System of Agentic AI for the Discovery of Metal-Organic Frameworks 提出Agentic AI系统MOFGen，加速金属有机框架材料的发现与合成。 large language model
11 Flowco: Rethinking Data Analysis in the Age of LLMs Flowco：面向LLM时代，重新思考数据分析流程与人机协作 large language model
12 SCRAG: Social Computing-Based Retrieval Augmented Generation for Community Response Forecasting in Social Media Environments SCRAG：基于社会计算的检索增强生成框架，用于预测社交媒体环境中的社区反应 large language model
13 OpenDeception: Benchmarking and Investigating AI Deceptive Behaviors via Open-ended Interaction Simulation 提出OpenDeception框架以评估AI欺骗行为的风险 large language model
14 Going Whole Hog: A Philosophical Defense of AI Cognition 论证大型语言模型具备完整认知能力，挑战AI哲学传统方法 large language model
15 RAG Without the Lag: Interactive Debugging for Retrieval-Augmented Generation Pipelines RAGGY：用于检索增强生成流水线的交互式调试工具 large language model
16 High-Throughput LLM inference on Heterogeneous Clusters 提出异构集群上的高吞吐量LLM推理服务系统，优化部署配置和请求调度。 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
17 CodeVisionary: An Agent-based Framework for Evaluating Large Language Models in Code Generation 提出CodeVisionary，一个基于Agent的框架，用于评估大语言模型在代码生成方面的能力。 distillation large language model ✅
18 Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model? 研究表明：基于可验证奖励的强化学习未能显著提升LLM的推理能力 reinforcement learning distillation large language model
19 SwitchMT: An Adaptive Context Switching Methodology for Scalable Multi-Task Learning in Intelligent Autonomous Agents SwitchMT：一种自适应上下文切换方法，用于智能自主代理中可扩展的多任务学习 reinforcement learning generalist agent
20 Think Deep, Think Fast: Investigating Efficiency of Verifier-free Inference-time-scaling Methods 研究无验证器推理时缩放方法在LLM推理和非推理模型上的效率 reinforcement learning large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
21 Exploring Multimodal Prompt for Visualization Authoring with Large Language Models VisPilot：探索多模态提示，提升大语言模型在可视化创作中的能力 manipulation large language model multimodal

⬅️ 返回 cs.AI 首页 · 🏠 返回主页