cs.CV（2025-05-22）
📊 共 4 篇论文 | 🔗 2 篇有代码
🎯 兴趣领域导航
🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | DriveMoE: Mixture-of-Experts for Vision-Language-Action Model in End-to-End Autonomous Driving | DriveMoE：基于混合专家模型的端到端自动驾驶视觉-语言-动作模型 | embodied AI vision-language-action VLA | ||
| 2 | Image Quality Assessment for Embodied AI | 提出Embodied-IQA数据集与评估体系，用于评估具身智能在真实场景下的图像质量。 | embodied AI vision-language-action | ✅ | |
| 3 | Extremely Simple Multimodal Outlier Synthesis for Out-of-Distribution Detection and Segmentation | 提出Feature Mixing方法，用于多模态OOD检测与分割，加速10-370倍。 | multimodal | ✅ |
🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 4 | CoMo: Learning Continuous Latent Motion from Internet Videos for Scalable Robot Learning | CoMo：从互联网视频学习连续潜在运动，用于可扩展的机器人学习 | cross-embodiment |