cs.CV（2025-03-10）
📊 共 8 篇论文 | 🔗 1 篇有代码
🎯 兴趣领域导航
支柱二：RL算法与架构 (RL & Architecture) (4 🔗1)
支柱三：空间感知与语义 (Perception & Semantics) (2)
支柱九：具身大模型 (Embodied Foundation Models) (1)
支柱八：物理动画 (Physics-based Animation) (1)
🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | CoT-Drive: Efficient Motion Forecasting for Autonomous Driving with LLMs and Chain-of-Thought Prompting | CoT-Drive：利用LLM和思维链提示提升自动驾驶运动预测效率 | teacher-student distillation scene understanding | ||
| 2 | POp-GS: Next Best View in 3D-Gaussian Splatting with P-Optimality | POp-GS：基于P-最优性的3D高斯溅射下一最佳视角选择 | world model 3D gaussian splatting gaussian splatting | ||
| 3 | AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning | AlphaDrive：通过强化学习和推理释放VLM在自动驾驶中的潜力 | reinforcement learning multimodal | ||
| 4 | A Data-Centric Revisit of Pre-Trained Vision Models for Robot Learning | 提出SlotMIM，提升预训练视觉模型在机器人学习中对非物体中心数据的表征能力 | MAE scene understanding | ✅ |
🔬 支柱三：空间感知与语义 (Perception & Semantics) (2 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 5 | Multi-Modal 3D Mesh Reconstruction from Images and Text | 提出一种语言引导的少样本3D网格重建方法，解决零样本方法依赖预训练3D模型的难题。 | gaussian splatting splatting | ||
| 6 | FunGraph: Functionality Aware 3D Scene Graphs for Language-Prompted Scene Interaction | FunGraph：面向语言提示场景交互的功能感知3D场景图 | affordance |
🔬 支柱九：具身大模型 (Embodied Foundation Models) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 7 | Lightweight Multimodal Artificial Intelligence Framework for Maritime Multi-Scene Recognition | 提出轻量级多模态AI框架，用于提升复杂海事场景识别精度与效率。 | large language model multimodal |
🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 8 | Temporal Overlapping Prediction: A Self-supervised Pre-training Method for LiDAR Moving Object Segmentation | 提出Temporal Overlapping Prediction自监督预训练方法，提升LiDAR点云移动物体分割性能。 | spatiotemporal |