cs.CV（2023-11-12）
📊 共 7 篇论文 | 🔗 3 篇有代码
🎯 兴趣领域导航
支柱九：具身大模型 (Embodied Foundation Models) (3 🔗2)
支柱二：RL算法与架构 (RL & Architecture) (2)
支柱三：空间感知与语义 (Perception & Semantics) (1)
支柱四：生成式动作 (Generative Motion) (1 🔗1)
🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | InfMLLM: A Unified Framework for Visual-Language Tasks | 提出InfMLLM框架以解决视觉语言任务的挑战 | large language model multimodal instruction following | ✅ | |
| 2 | DialMAT: Dialogue-Enabled Transformer with Moment-Based Adversarial Training | 提出DialMAT以解决DialFRED任务中的对话式指令跟随问题 | embodied AI foundation model instruction following | ||
| 3 | Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models | 提出Q-Instruct以提升多模态基础模型的低级视觉能力 | foundation model | ✅ |
🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 4 | Contrastive Learning of View-Invariant Representations for Facial Expressions Recognition | 提出ViewFX框架以解决非正面视角下的面部表情识别问题 | contrastive learning | ||
| 5 | CL-Flow:Strengthening the Normalizing Flows by Contrastive Learning for Better Anomaly Detection | 提出CL-Flow以解决无监督异常检测中样本稀缺问题 | contrastive learning |
🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 6 | Two Stream Scene Understanding on Graph Embedding | 提出双流网络架构以增强场景理解能力 | scene understanding semantic map |
🔬 支柱四：生成式动作 (Generative Motion) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 7 | ChatAnything: Facetime Chat with LLM-Enhanced Personas | 提出ChatAnything以解决生成类人角色的多样性问题 | motion generation | ✅ |