cs.LG（2025-12-10）
📊 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) (3 🔗1)
支柱一：机器人控制 (Robot Control) (1)
支柱二：RL算法与架构 (RL & Architecture) (1)
🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | D3G: Diverse Demographic Data Generation Increases Zero-Shot Image Classification Accuracy within Multimodal Models | D3G：通过多样化人口数据生成提升多模态模型零样本图像分类精度 | multimodal | ||
| 2 | SIP-BMM: Constructing Capability-Efficiency Pareto Set of LLMs via Bayesian Model Merging with Structural Importance Prior | SIP-BMM：通过结构重要性先验的贝叶斯模型合并构建LLM的能力-效率帕累托集 | large language model | ✅ | |
| 3 | Encoder-Free Knowledge-Graph Reasoning with LLMs via Hyperdimensional Path Retrieval | PathHD：利用超维路径检索，实现无编码器的LLM知识图谱推理 | large language model |
🔬 支柱一：机器人控制 (Robot Control) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 4 | Closing the Train-Test Gap in World Models for Gradient-Based Planning | 提出数据合成方法，弥合World Model中基于梯度规划的训练-测试差距 | manipulation MPC model predictive control |
🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 5 | LLaDA2.0: Scaling Up Diffusion Language Models to 100B | LLaDA2.0：通过扩散语言模型扩展至1000亿参数，实现高效部署。 | DPO large language model |