cs.LG（2025-05-29）

📊 共 7 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (4) 支柱九：具身大模型 (Embodied Foundation Models) (3 🔗1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
1 Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Better 提出知识隔离的VLA模型，加速训练、推理并提升泛化能力 flow matching vision-language-action VLA
2 Differential Information Distribution: A Bayesian Perspective on Direct Preference Optimization 提出差异信息分布以优化直接偏好学习 DPO direct preference optimization reward design
3 Composite Reward Design in PPO-Driven Adaptive Filtering 提出基于PPO的复合奖励自适应滤波框架以解决动态环境中的去噪问题 reinforcement learning PPO reward design
4 Information Structure in Mappings: An Approach to Learning, Representation, and Generalisation 提出一种量化映射结构的方法，用于理解深度学习模型的表征、泛化能力和设计决策的影响。 reinforcement learning large language model

🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)

#题目一句话要点标签🔗⭐
5 From Images to Signals: Are Large Vision Models Useful for Time Series Analysis? 研究大型视觉模型在时间序列分析中的有效性，揭示其在分类任务的优势与预测任务的挑战。 large language model foundation model multimodal
6 Large Language Models for Controllable Multi-property Multi-objective Molecule Optimization 提出C-MuMOInstruct数据集和GeLLMO-Cs模型，解决药物设计中多属性多目标分子优化问题。 large language model ✅
7 Vision Language Models are Biased 揭示视觉语言模型在计数和识别任务中存在的偏差问题 large language model

⬅️ 返回 cs.LG 首页 · 🏠 返回主页