cs.AI（2024-12-12）
📊 共 13 篇论文
🎯 兴趣领域导航
支柱九：具身大模型 (Embodied Foundation Models) (7)
支柱二：RL算法与架构 (RL & Architecture) (4)
支柱三：空间感知与语义 (Perception & Semantics) (1)
支柱一：机器人控制 (Robot Control) (1)
🔬 支柱九：具身大模型 (Embodied Foundation Models) (7 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | A Large Sensor Foundation Model Pretrained on Continuous Glucose Monitor Data for Diabetes Management | 提出基于Transformer解码器的CGM-LSM，用于改善糖尿病管理中的血糖预测。 | large language model foundation model | ||
| 2 | Multimodal Sentiment Analysis based on Video and Audio Inputs | 提出多模态情感分析模型以提升视频音频情感识别准确率 | multimodal | ||
| 3 | Enhancing Modality Representation and Alignment for Multimodal Cold-start Active Learning | 提出MMCSAL方法，解决多模态冷启动主动学习中的模态差距和对齐问题 | multimodal | ||
| 4 | Kajal: Extracting Grammar of a Source Code Using Large Language Models | Kajal：利用大语言模型自动提取源代码的语法规则 | large language model | ||
| 5 | Neural Interactive Proofs | 提出神经交互证明框架，用于可信但算力有限的验证者与不可信但强大的证明者之间的交互任务。 | large language model | ||
| 6 | Systematic Analysis of LLM Contributions to Planning: Solver, Verifier, Heuristic | 系统分析LLM在规划问题中的作用：求解器、验证器与启发式函数 | large language model | ||
| 7 | EmbedGenius: Towards Automated Software Development for Generic Embedded IoT Systems | EmbedGenius：面向通用嵌入式物联网系统的全自动软件开发平台 | 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 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 8 | LMAgent: A Large-scale Multimodal Agents Society for Multi-user Simulation | LMAgent：构建大规模多模态智能体社会，用于多用户电商行为仿真 | world model large language model multimodal | ||
| 9 | In-Dataset Trajectory Return Regularization for Offline Preference-based Reinforcement Learning | 提出数据集内轨迹回报正则化(DTR)以解决离线偏好强化学习中的奖励偏差问题 | reinforcement learning offline RL decision transformer | ||
| 10 | Residual Channel Boosts Contrastive Learning for Radio Frequency Fingerprint Identification | 提出基于残差信道增强的对比学习方法，用于解决射频指纹识别中小样本泛化问题 | contrastive learning | ||
| 11 | Quantum-Train-Based Distributed Multi-Agent Reinforcement Learning | 提出量子训练分布式多智能体强化学习以解决可扩展性问题 | reinforcement learning |
🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 12 | Towards Open-Vocabulary Video Semantic Segmentation | 提出OV2VSS，解决视频语义分割中开放词汇场景下的泛化性问题 | open-vocabulary open vocabulary |
🔬 支柱一：机器人控制 (Robot Control) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 13 | Understanding Opportunities and Risks of Synthetic Relationships: Leveraging the Power of Longitudinal Research with Customised AI Tools | 利用定制AI工具的纵向研究，探索合成关系的机遇与风险 | manipulation |