cs.AI（2026-02-20）

📊 共 11 篇论文

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (5) 支柱九：具身大模型 (Embodied Foundation Models) (4) 支柱一：机器人控制 (Robot Control) (1) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
1 Diffusing to Coordinate: Efficient Online Multi-Agent Diffusion Policies 提出OMAD框架，利用扩散策略解决在线多智能体强化学习中的探索与协调难题。 reinforcement learning diffusion policy multimodal
2 Hierarchical Reward Design from Language: Enhancing Alignment of Agent Behavior with Human Specifications 提出HRDL与L2HR，通过语言指导分层强化学习智能体行为对齐人类规范 reinforcement learning reward design
3 Mean-Field Reinforcement Learning without Synchrony 提出基于人口分布的均场强化学习以解决异步问题 reinforcement learning
4 1D-Bench: A Benchmark for Iterative UI Code Generation with Visual Feedback in Real-World 提出1D-Bench基准，用于评估真实电商场景下基于视觉反馈的迭代UI代码生成 reinforcement learning multimodal
5 MeanVoiceFlow: One-step Nonparallel Voice Conversion with Mean Flows 提出MeanVoiceFlow，一种基于平均流的单步非平行语音转换模型。 flow matching distillation

🔬 支柱九：具身大模型 (Embodied Foundation Models) (4 篇)

#题目一句话要点标签🔗⭐
6 Context-Aware Mapping of 2D Drawing Annotations to 3D CAD Features Using LLM-Assisted Reasoning for Manufacturing Automation 提出一种基于LLM辅助推理的上下文感知映射方法，用于2D图纸标注到3D CAD特征的映射，以促进制造自动化。 large language model multimodal
7 RPU -- A Reasoning Processing Unit RPU：面向推理应用的片上系统架构，解决大模型推理的访存瓶颈 large language model
8 Neurosymbolic Language Reasoning as Satisfiability Modulo Theory 提出Logitext，通过SMT求解器融合LLM与符号推理，提升自然语言理解能力 large language model
9 Aurora: Neuro-Symbolic AI Driven Advising Agent Aurora：神经符号AI驱动的智能选课顾问，解决高校咨询瓶颈。 large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
10 Cross-Embodiment Offline Reinforcement Learning for Heterogeneous Robot Datasets 提出基于离线强化学习的跨具身机器人数据集预训练方法，解决异构机器人数据利用问题。 locomotion reinforcement learning offline RL

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
11 Can AI Lower the Barrier to Cybersecurity? A Human-Centered Mixed-Methods Study of Novice CTF Learning 利用AI降低网络安全门槛：以人为本的新手CTF学习混合方法研究 penetration

⬅️ 返回 cs.AI 首页 · 🏠 返回主页