cs.AI(2025-01-08)
📊 共 3 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 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection | InfiGUIAgent:具备原生推理和反思能力的多模态通用GUI智能体 | large language model multimodal | ✅ | |
| 2 | From Conceptual Data Models to Multimodal Representation | 提出一种从概念数据模型到多模态表示的框架,用于视听数据分析与重用。 | multimodal |
🔬 支柱二:RL算法与架构 (RL & Architecture) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 3 | Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought | 提出Meta-CoT框架,提升LLM的System 2推理能力,使其更接近人类思维 | reinforcement learning chain-of-thought |