cs.LG(2025-10-15)

📊 共 6 篇论文

🎯 兴趣领域导航

支柱二:RL算法与架构 (RL & Architecture) (3) 支柱四:生成式动作 (Generative Motion) (1) 支柱一:机器人控制 (Robot Control) (1) 支柱九:具身大模型 (Embodied Foundation Models) (1)

🔬 支柱二:RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗
1 NeuroRVQ: Multi-Scale EEG Tokenization for Generative Large Brainwave Models 提出NeuroRVQ以解决EEG信号重建精度不足问题 representation learning foundation model multimodal
2 Simplicial Embeddings Improve Sample Efficiency in Actor-Critic Agents 提出基于单纯复形嵌入的强化学习方法,提升Actor-Critic算法的样本效率。 reinforcement learning deep reinforcement learning PPO
3 A New Perspective on Transformers in Online Reinforcement Learning for Continuous Control 探索Transformer在在线强化学习连续控制中的应用 reinforcement learning

🔬 支柱四:生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗
4 On the Reasoning Abilities of Masked Diffusion Language Models 研究表明Masked Diffusion模型在特定推理问题上优于自回归语言模型。 MDM chain-of-thought

🔬 支柱一:机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗
5 Data-driven learning of feedback maps for explicit robust predictive control: an approximation theoretic view 提出一种数据驱动的鲁棒预测控制反馈映射学习算法,保证递归可行性。 MPC model predictive control

🔬 支柱九:具身大模型 (Embodied Foundation Models) (1 篇)

#题目一句话要点标签🔗
6 Neural Triangular Transport Maps: A New Approach Towards Sampling in Lattice QCD 提出稀疏三角运输图以解决格点量子色动力学采样问题 multimodal

⬅️ 返回 cs.LG 首页 · 🏠 返回主页