cs.AI（2025-04-28）

📊 共 24 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) (18 🔗1) 支柱一：机器人控制 (Robot Control) (3) 支柱二：RL算法与架构 (RL & Architecture) (3)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (18 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Fitness Landscape of Large Language Model-Assisted Automated Algorithm Search	图分析揭示大语言模型辅助算法搜索的复杂适应度景观	large language model multimodal
2	AutoP2C: An LLM-Based Agent Framework for Code Repository Generation from Multimodal Content in Academic Papers	AutoP2C：一个基于LLM Agent框架，用于从学术论文多模态内容生成代码仓库	large language model multimodal	✅
3	GVPO: Group Variance Policy Optimization for Large Language Model Post-Training	GVPO：面向大语言模型后训练的组方差策略优化，提升训练稳定性和灵活性	large language model
4	mrCAD: Multimodal Refinement of Computer-aided Designs	提出mrCAD数据集，用于多模态指令驱动的计算机辅助设计迭代优化研究。	multimodal
5	AGATE: Stealthy Black-box Watermarking for Multimodal Model Copyright Protection	提出AGATE：一种隐蔽的黑盒水印框架，用于多模态模型版权保护	multimodal
6	CodeBC: A More Secure Large Language Model for Smart Contract Code Generation in Blockchain	提出CodeBC，用于区块链智能合约代码安全生成，无需人工标注漏洞位置。	large language model
7	Towards Large Language Models for Lunar Mission Planning and In Situ Resource Utilization	利用大语言模型进行月球任务规划和原位资源利用的数据提取	large language model
8	Towards AI-Driven Policing: Interdisciplinary Knowledge Discovery from Police Body-Worn Camera Footage	提出跨学科框架以分析警用随身摄像头视频	large language model multimodal
9	What's Pulling the Strings? Evaluating Integrity and Attribution in AI Training and Inference through Concept Shift	ConceptLens：通过概念漂移评估AI训练和推理中的完整性和归因问题	multimodal
10	Can Differentially Private Fine-tuning LLMs Protect Against Privacy Attacks?	研究差分隐私微调LLM抵抗隐私攻击的有效性与代价	large language model
11	Understanding and supporting how developers prompt for LLM-powered code editing in practice	通过分析开发者提示行为，提出AutoPrompter以提升LLM代码编辑的准确性	large language model
12	BLADE: Benchmark suite for LLM-driven Automated Design and Evolution of iterative optimisation heuristics	BLADE：用于LLM驱动的迭代优化启发式算法自动设计与演化的基准测试套件	large language model
13	Towards Automated Scoping of AI for Social Good Projects	提出问题范围界定代理（PSA），利用LLM自动生成AI社会公益项目提案。	large language model
14	Leveraging LLM to Strengthen ML-Based Cross-Site Scripting Detection	利用LLM增强基于机器学习的跨站脚本攻击检测能力	large language model
15	Pediatric Asthma Detection with Googles HeAR Model: An AI-Driven Respiratory Sound Classifier	利用谷歌HeAR模型，AI驱动的呼吸音分类器用于儿童哮喘早期检测	foundation model
16	Reconstructing Context: Evaluating Advanced Chunking Strategies for Retrieval-Augmented Generation	针对RAG中上下文碎片问题，对比分析晚期分块与上下文检索策略的优劣	large language model
17	Llama-3.1-FoundationAI-SecurityLLM-Base-8B Technical Report	提出Foundation-Sec-8B：基于Llama 3.1的增强型网络安全大语言模型	large language model
18	ResearchCodeAgent: An LLM Multi-Agent System for Automated Codification of Research Methodologies	ResearchCodeAgent：利用LLM多智能体系统自动生成机器学习研究方法代码	large language model

🔬 支柱一：机器人控制 (Robot Control) (3 篇)

#	题目	一句话要点	标签	🔗	⭐
19	Prefill-level Jailbreak: A Black-Box Risk Analysis of Large Language Models	提出预填充攻击方法，揭示大语言模型新的安全漏洞	manipulation large language model
20	Mitigating Societal Cognitive Overload in the Age of AI: Challenges and Directions	应对AI时代社会认知超载：挑战与方向	manipulation
21	A Real-Time Gesture-Based Control Framework	提出一种基于手势的实时控制框架，用于动态调整音频和音乐。	manipulation

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#	题目	一句话要点	标签	🔗	⭐
22	From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review	全面综述LLM推理到自主AI Agent的演进：基准、框架与应用	reinforcement learning large language model multimodal
23	Agentic Reasoning and Tool Integration for LLMs via Reinforcement Learning	ARTIST：通过强化学习实现LLM的Agentic推理和工具集成	reinforcement learning large language model
24	Automated decision-making for dynamic task assignment at scale	提出基于图结构和定制奖励函数的DRL决策支持系统，解决大规模动态任务分配问题。	reinforcement learning deep reinforcement learning DRL

⬅️ 返回 cs.AI 首页 · 🏠 返回主页