cs.CV（2023-12-12）
📊 共 5 篇论文 | 🔗 1 篇有代码
🎯 兴趣领域导航
支柱九：具身大模型 (Embodied Foundation Models) (2 🔗1)
支柱三：空间感知与语义 (Perception & Semantics) (2)
支柱二：RL算法与架构 (RL & Architecture) (1)
🔬 支柱九：具身大模型 (Embodied Foundation Models) (2 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | LMDrive: Closed-Loop End-to-End Driving with Large Language Models | LMDrive：提出基于大语言模型的端到端闭环自动驾驶框架，实现语言引导的自主驾驶。 | large language model instruction following | ✅ | |
| 2 | Interfacing Foundation Models' Embeddings | 提出FIND：统一接口对齐多模态基础模型嵌入，实现跨任务理解 | foundation model |
🔬 支柱三：空间感知与语义 (Perception & Semantics) (2 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 3 | CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor | 提出基于CLIP的循环分割框架，无需训练即可分割海量视觉概念 | open-vocabulary open vocabulary | ||
| 4 | Attacking the Loop: Adversarial Attacks on Graph-based Loop Closure Detection | 提出Adversarial-LCD，针对图结构回环检测的黑盒对抗攻击框架 | visual SLAM |
🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 5 | Cross-modal Contrastive Learning with Asymmetric Co-attention Network for Video Moment Retrieval | 提出基于非对称协同注意力网络的跨模态对比学习方法，用于视频片段检索。 | representation learning contrastive learning |