cs.AI（2025-03-31）

📊 共 22 篇论文

🎯 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) 支柱一：机器人控制 (Robot Control) (2)

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

#题目一句话要点标签🔗⭐
1 Orchestrate Multimodal Data with Batch Post-Balancing to Accelerate Multimodal Large Language Model Training OrchMLLM框架通过批量后平衡加速多模态大语言模型训练 large language model multimodal
2 GazeLLM: Multimodal LLMs incorporating Human Visual Attention GazeLLM：融合人类视觉注意力的多模态LLM，高效处理第一人称视频 large language model multimodal
3 WebMap -- Large Language Model-assisted Semantic Link Induction in the Web WebMap：提出一种基于大语言模型的Web语义链接归纳方法，以增强网络研究能力。 large language model
4 Large Language Models in Numberland: A Quick Test of Their Numerical Reasoning Abilities 提出Numberland基准测试，评估大语言模型在数值推理上的能力。 large language model
5 $\textit{Agents Under Siege}$: Breaking Pragmatic Multi-Agent LLM Systems with Optimized Prompt Attacks 提出针对多智能体LLM系统的优化提示攻击，突破分布式安全机制。 large language model
6 PIM-LLM: A High-Throughput Hybrid PIM Architecture for 1-bit LLMs PIM-LLM：一种用于1比特LLM的高吞吐混合PIM架构 large language model
7 LLMs for Explainable AI: A Comprehensive Survey 综述：利用大型语言模型提升可解释性人工智能 large language model
8 Assessing Code Understanding in LLMs 评估LLM在代码理解中对语义保持变换的鲁棒性 large language model
9 Grounding Agent Reasoning in Image Schemas: A Neurosymbolic Approach to Embodied Cognition 提出基于图像图式的神经符号方法，增强具身智能体推理能力 embodied AI
10 Towards Scientific Intelligence: A Survey of LLM-based Scientific Agents 综述：基于LLM的科学智能体，加速科学发现与研究自动化 large language model
11 Pay More Attention to the Robustness of Prompt for Instruction Data Mining 提出基于Prompt鲁棒性的指令数据挖掘框架，提升指令调优效果 instruction following
12 Rubric Is All You Need: Enhancing LLM-based Code Evaluation With Question-Specific Rubrics 提出基于问题特定评分标准的LLM代码评估方法，提升教育场景下的逻辑评估效果。 large language model
13 DebFlow: Automating Agent Creation via Agent Debate DebFlow：通过智能体辩论自动创建Agent工作流，提升推理能力并降低资源消耗。 large language model
14 InteractiveSurvey: An LLM-based Personalized and Interactive Survey Paper Generation System InteractiveSurvey：提出一种基于LLM的个性化交互式综述论文生成系统 large language model
15 Human aversion? Do AI Agents Judge Identity More Harshly Than Performance 揭示AI对人类判断的偏见：AI系统低估人类输入，存在“反算法厌恶”现象 large language model
16 GIScience in the Era of Artificial Intelligence: A Research Agenda Towards Autonomous GIS 提出自主GIS框架，利用大语言模型驱动地理信息系统实现自动化空间分析。 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 Exploration and Adaptation in Non-Stationary Tasks with Diffusion Policies 提出基于扩散策略的强化学习方法，解决非平稳视觉任务中的探索与适应问题 PPO diffusion policy
18 Graph Neural Network-Based Predictive Modeling for Robotic Plaster Printing 提出基于图神经网络的预测模型，用于机器人抹灰喷涂的表面预测。 predictive model
19 Rack Position Optimization in Large-Scale Heterogeneous Data Centers 提出基于DRL的两层优化框架，解决大规模异构数据中心机架位置优化问题 reinforcement learning deep reinforcement learning DRL
20 Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems 综述性研究：探索具身智能Agent的进展、挑战及未来发展方向 world model large language model

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
21 Detecting Malicious AI Agents Through Simulated Interactions 通过模拟交互检测恶意AI助手的操纵行为 manipulation
22 Text2Schema: Filling the Gap in Designing Database Table Structures based on Natural Language 提出SchemaAgent框架，解决从自然语言文本直接生成数据库表结构的问题。 manipulation

⬅️ 返回 cs.AI 首页 · 🏠 返回主页