cs.AI（2025-03-06）

📊 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 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (4) 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	Training-free Adjustable Polynomial Graph Filtering for Ultra-fast Multimodal Recommendation	提出一种免训练的可调多项式图滤波方法，用于超快速多模态推荐。	multimodal
2	Benchmarking Reasoning Robustness in Large Language Models	揭示大语言模型推理鲁棒性困境，提出Math-RoB基准进行全面评估	large language model
3	Activation Space Interventions Can Be Transferred Between Large Language Models	提出激活空间干预迁移方法，实现大语言模型间的安全对齐。	large language model
4	AgentSafe: Safeguarding Large Language Model-based Multi-agent Systems via Hierarchical Data Management	AgentSafe：通过分层数据管理保障大语言模型多智能体系统安全	large language model
5	KidneyTalk-open: No-code Deployment of a Private Large Language Model with Medical Documentation-Enhanced Knowledge Database for Kidney Disease	KidneyTalk-open：无代码部署医学文档增强知识库的肾病私有大语言模型	large language model
6	Dynamic Benchmarking of Reasoning Capabilities in Code Large Language Models Under Data Contamination	提出 ool动态基准测试方法，评估代码大语言模型在数据污染下的推理能力	large language model
7	Multi-modal Summarization in Model-Based Engineering: Automotive Software Development Case Study	探索多模态大语言模型在基于模型的工程中UML/EMF图理解与摘要能力	large language model multimodal
8	MathMistake Checker: A Comprehensive Demonstration for Step-by-Step Math Problem Mistake Finding by Prompt-Guided LLMs	提出MathMistake Checker，利用提示引导的大语言模型自动检测数学解题步骤中的错误。	large language model chain-of-thought
9	LLMs' Reshaping of People, Processes, Products, and Society in Software Development: A Comprehensive Exploration with Early Adopters	通过早期采用者访谈，揭示LLM在软件开发中对人员、流程、产品和社会的影响	large language model
10	Quantifying the Relevance of Youth Research Cited in the US Policy Documents	利用自然语言处理量化美国政策文件中引用的青年研究的相关性	large language model
11	LLM Applications: Current Paradigms and the Next Frontier	综述LLM应用范式，提出分层架构以应对碎片化、安全和扩展性挑战	large language model
12	ToolFuzz -- Automated Agent Tool Testing	ToolFuzz：自动化测试Agent工具文档，提升LLM Agent可靠性	large language model
13	Wider or Deeper? Scaling LLM Inference-Time Compute with Adaptive Branching Tree Search	提出自适应分支蒙特卡洛树搜索(AB-MCTS)，提升LLM推理时计算效率与复杂任务性能。	large language model	✅
14	Malware Detection at the Edge with Lightweight LLMs: A Performance Evaluation	提出轻量级LLM边缘恶意软件检测方案，解决资源受限环境下的检测难题	large language model
15	Mapping AI Benchmark Data to Quantitative Risk Estimates Through Expert Elicitation	通过专家评估将AI基准数据映射到定量风险估计	large language model
16	How Do Hackathons Foster Creativity? Towards AI Collaborative Evaluation of Creativity at Scale	提出基于大规模黑客松项目的AI协同创造力评估方法，促进黑客松创意产出。	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	SED2AM: Solving Multi-Trip Time-Dependent Vehicle Routing Problem using Deep Reinforcement Learning	提出SED2AM，利用深度强化学习解决带最大工作时间约束的多车次时变车辆路径问题	reinforcement learning deep reinforcement learning DRL
18	SOLAR: Scalable Optimization of Large-scale Architecture for Reasoning	SOLAR框架通过动态优化推理拓扑结构，提升大语言模型在复杂推理任务上的性能。	curriculum learning large language model chain-of-thought
19	Multi-Agent Inverse Q-Learning from Demonstrations	提出MAMQL，通过边缘化Q学习从演示中进行多智能体逆强化学习。	reinforcement learning deep reinforcement learning inverse reinforcement learning
20	Semantic Retrieval Augmented Contrastive Learning for Sequential Recommendation	提出语义检索增强对比学习（SRA-CL）用于提升序列推荐模型性能	contrastive learning

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
21	InterChat: Enhancing Generative Visual Analytics using Multimodal Interactions	InterChat：利用多模态交互增强生成式可视化分析	manipulation large language model multimodal

⬅️ 返回 cs.AI 首页 · 🏠 返回主页