cs.AI（2026-02-18）

📊 共 14 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (10) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (10 篇)

#题目一句话要点标签🔗⭐
1 Automated Histopathology Report Generation via Pyramidal Feature Extraction and the UNI Foundation Model 提出基于金字塔特征提取和UNI基础模型的自动组织病理学报告生成方法 foundation model
2 Leveraging Large Language Models for Causal Discovery: a Constraint-based, Argumentation-driven Approach 提出基于大语言模型的因果发现方法，结合约束推理和论证驱动，提升因果关系推断准确性。 large language model
3 Human-AI Collaboration in Large Language Model-Integrated Building Energy Management Systems: The Role of User Domain Knowledge and AI Literacy 研究用户领域知识和AI素养对LLM集成建筑能源管理系统人机协作的影响 large language model
4 Framework of Thoughts: A Foundation Framework for Dynamic and Optimized Reasoning based on Chains, Trees, and Graphs 提出Framework of Thoughts以解决动态推理结构适应性不足问题 large language model chain-of-thought
5 SPARC: Scenario Planning and Reasoning for Automated C Unit Test Generation SPARC：基于场景规划与推理的自动化C单元测试生成框架 large language model
6 Retrieval Augmented Generation of Literature-derived Polymer Knowledge: The Example of a Biodegradable Polymer Expert System 提出两种检索增强生成（RAG）方法，用于从聚合物文献中提取知识，构建可信赖的生物降解聚合物专家系统。 large language model
7 FlowPrefill: Decoupling Preemption from Prefill Scheduling Granularity to Mitigate Head-of-Line Blocking in LLM Serving FlowPrefill：解耦抢占与预填充调度粒度，缓解LLM服务中的队头阻塞 large language model
8 Creating a digital poet 通过工作坊式Prompt工程，塑造大型语言模型为数字诗人，并成功出版诗集。 large language model
9 Toward Scalable Verifiable Reward: Proxy State-Based Evaluation for Multi-turn Tool-Calling LLM Agents 提出基于代理状态评估的可扩展可验证奖励框架，用于多轮工具调用LLM Agent。 large language model
10 Retrieval Collapses When AI Pollutes the Web 揭示AI污染Web内容导致检索崩溃的风险，并分析其传播机制 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
11 Edge Learning via Federated Split Decision Transformers for Metaverse Resource Allocation 提出联邦拆分决策Transformer（FSDT）以优化元宇宙资源分配，提升异构环境下的用户体验。 reinforcement learning offline RL decision transformer
12 Causally-Guided Automated Feature Engineering with Multi-Agent Reinforcement Learning CAFE：利用因果引导的多智能体强化学习实现自动化特征工程，提升泛化性和效率。 reinforcement learning reward shaping

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
13 Color-based Emotion Representation for Speech Emotion Recognition 提出基于色彩属性的情感表征方法，用于提升语音情感识别的性能与可解释性。 motion representation

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
14 Learning Personalized Agents from Human Feedback 提出PAHF框架，通过人机交互在线学习个性化Agent，解决用户偏好动态变化问题 manipulation

⬅️ 返回 cs.AI 首页 · 🏠 返回主页