cs.GR（2026-04-07）
📊 共 4 篇论文
🎯 兴趣领域导航
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)
支柱一：机器人控制 (Robot Control) (1)
🔬 支柱三：空间感知与语义 (Perception & Semantics) (2 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | GEMM-GS: Accelerating 3D Gaussian Splatting on Tensor Cores with GEMM-Compatible Blending | 提出GEMM-GS以加速3D高斯点云渲染 | 3D gaussian splatting 3DGS gaussian splatting | ||
| 2 | PhysGaia: A Physics-Aware Benchmark with Multi-Body Interactions for Dynamic Novel View Synthesis | PhysGaia：一个用于动态新视角合成的物理感知多体交互基准 | gaussian splatting splatting scene understanding |
🔬 支柱九：具身大模型 (Embodied Foundation Models) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 3 | SASAV: Self-Directed Agent for Scientific Analysis and Visualization | 提出SASAV：一种用于科学分析和可视化的自驱动智能体，无需人工干预。 | large language model multimodal |
🔬 支柱一：机器人控制 (Robot Control) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 4 | CrowdVLA: Embodied Vision-Language-Action Agents for Context-Aware Crowd Simulation | CrowdVLA：用于上下文感知人群模拟的具身视觉-语言-动作智能体 | locomotion vision-language-action VLA |