cs.AI（2025-03-18）

📊 共 15 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (8) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗2) 支柱一：机器人控制 (Robot Control) (2) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (8 篇)

#题目一句话要点标签🔗⭐
1 Assessing Large Language Models for Automated Feedback Generation in Learning Programming Problem Solving 评估大型语言模型在编程问题解决中自动生成反馈的性能 large language model
2 EIAD: Explainable Industrial Anomaly Detection Via Multi-Modal Large Language Models 提出EIAD，通过多模态大语言模型实现可解释的工业异常检测 large language model
3 Inference-Time Intervention in Large Language Models for Reliable Requirement Verification 提出基于干预的大语言模型，用于可靠的需求验证，提升MBSE效率。 large language model
4 RAGO: Systematic Performance Optimization for Retrieval-Augmented Generation Serving RAGO：面向检索增强生成服务的系统性性能优化框架 large language model
5 Engineering Scientific Assistants using Interactive Structured Induction of Programs 提出iStrucInd，利用交互式结构化归纳编程加速科学助手软件的构建。 large language model
6 Gricean Norms as a Basis for Effective Collaboration 提出基于Gricean规范的LLM智能体Lamoids，提升人机协作中处理歧义指令的能力。 large language model
7 Beyond Single Pass, Looping Through Time: KG-IRAG with Iterative Knowledge Retrieval 提出KG-IRAG框架，通过迭代知识检索增强LLM在时序推理任务中的性能 large language model
8 Can LLMs Enable Verification in Mainstream Programming? 探索LLM在主流编程中实现代码验证的能力，提升软件可靠性 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🔗⭐
9 Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning Cosmos-Reason1：通过物理常识到具身推理，实现物理AI系统决策 reinforcement learning large language model multimodal ✅
10 Core-Periphery Principle Guided State Space Model for Functional Connectome Classification 提出CP-SSM模型，用于提升功能连接组分类性能并降低计算复杂度。 Mamba SSM state space model
11 Pauli Network Circuit Synthesis with Reinforcement Learning 提出基于强化学习的Pauli网络电路重构方法，显著降低量子门数量。 reinforcement learning
12 Inferring Events from Time Series using Language Models 首个研究：利用大型语言模型从时间序列数据中推断事件 distillation large language model ✅

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
13 HA-VLN 2.0: An Open Benchmark and Leaderboard for Human-Aware Navigation in Discrete and Continuous Environments with Dynamic Multi-Human Interactions HA-VLN 2.0：提出一个用于动态多智能体交互环境中人机协同导航的开放基准和排行榜 sim-to-real VLN
14 VARP: Reinforcement Learning from Vision-Language Model Feedback with Agent Regularized Preferences VARP：利用视觉-语言模型反馈和智能体正则化偏好进行强化学习，提升机器人控制性能。 locomotion reinforcement learning

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
15 Automatic MILP Model Construction for Multi-Robot Task Allocation and Scheduling Based on Large Language Models 提出基于本地LLM的MILP自动建模框架，解决多机器人任务分配与调度问题 spatiotemporal large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页