cs.AI（2025-03-05）

📊 共 17 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) (11 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱四：生成式动作 (Generative Motion) (1) 支柱五：交互与反应 (Interaction & Reaction) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (11 篇)

#题目一句话要点标签🔗⭐
1 CodeIF-Bench: Evaluating Instruction-Following Capabilities of Large Language Models in Interactive Code Generation CodeIF-Bench：评估大型语言模型在交互式代码生成中的指令遵循能力 large language model instruction following ✅
2 Towards Understanding Multi-Round Large Language Model Reasoning: Approximability, Learnability and Generalizability 从理论层面分析多轮LLM推理：可逼近性、可学习性和泛化性 large language model chain-of-thought
3 COSINT-Agent: A Knowledge-Driven Multimodal Agent for Chinese Open Source Intelligence 提出COSINT-Agent，解决中文开源情报中多模态数据融合与推理难题。 large language model multimodal
4 Multi-Agent Systems Powered by Large Language Models: Applications in Swarm Intelligence 提出基于LLM驱动的多智能体系统，用于模拟和研究群体智能。 large language model ✅
5 Leveraging Large Language Models to Develop Heuristics for Emerging Optimization Problems 提出CEoH框架，利用大语言模型为新兴优化问题自动生成启发式算法。 large language model
6 AttackSeqBench: Benchmarking Large Language Models in Analyzing Attack Sequences within Cyber Threat Intelligence AttackSeqBench：评估大语言模型在网络威胁情报中分析攻击序列的能力 large language model
7 Unified Mind Model: Reimagining Autonomous Agents in the LLM Era 提出统一心智模型UMM，赋能LLM时代自主智能体快速构建 large language model instruction following
8 Human Preferences for Constructive Interactions in Language Model Alignment 利用人类偏好数据，对语言模型进行建设性对话的对齐研究 large language model
9 Parallelized Planning-Acting for Efficient LLM-based Multi-Agent Systems 提出并行化规划-行动框架，提升LLM多智能体系统在动态环境中的效率 large language model
10 LeRAAT: LLM-Enabled Real-Time Aviation Advisory Tool LeRAAT：基于LLM的实时航空咨询工具，提升飞行员决策效率。 large language model
11 OMNISEC: LLM-Driven Provenance-based Intrusion Detection via Retrieval-Augmented Behavior Prompting OMNISEC：基于LLM和溯源图的入侵检测，通过检索增强行为提示提升检测效果 large language model

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

#题目一句话要点标签🔗⭐
12 A Multimodal Framework for Topic Propagation Classification in Social Networks 提出一种多模态框架，用于社交网络中主题传播分类预测。 predictive model multimodal
13 Human Implicit Preference-Based Policy Fine-tuning for Multi-Agent Reinforcement Learning in USV Swarm 提出基于人类隐式偏好的强化学习微调方法，用于无人艇集群多智能体强化学习。 reinforcement learning RLHF large language model
14 Market-based Architectures in RL and Beyond 提出基于商品分解状态空间的市场机制强化学习算法，提升专业化和并行性 reinforcement learning large language model

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
15 RGB-Thermal Infrared Fusion for Robust Depth Estimation in Complex Environments 提出RTFusion模型，通过RGB-热红外融合提升复杂环境下的深度估计鲁棒性。 depth estimation multimodal

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
16 Impact of Level 2/3 Automated Driving Technology on Road Work Zone Safety 研究L2/L3自动驾驶车辆在道路施工区对交通安全的影响 penetration

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#题目一句话要点标签🔗⭐
17 From Infants to AI: Incorporating Infant-like Learning in Models Boosts Efficiency and Generalization in Learning Social Prediction Tasks 融合婴儿认知先验知识提升AI社交预测任务效率与泛化性 human-object interaction

⬅️ 返回 cs.AI 首页 · 🏠 返回主页