cs.LG(2025-03-16)

📊 共 4 篇论文

🎯 兴趣领域导航

支柱二:RL算法与架构 (RL & Architecture) (2) 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) (2 篇)

#题目一句话要点标签🔗
1 One Goal, Many Challenges: Robust Preference Optimization Amid Content-Aware and Multi-Source Noise 提出CNRPO框架,解决大语言模型偏好优化中内容相关和多源噪声问题。 preference learning large language model
2 RL-TIME: Reinforcement Learning-based Task Replication in Multicore Embedded Systems 提出RL-TIME,一种基于强化学习的多核嵌入式系统任务复制方法,优化功耗和实时性。 reinforcement learning

🔬 支柱一:机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗
3 Ensemble Kalman-Bucy filtering for nonlinear model predictive control 提出基于Ensemble Kalman-Bucy滤波的非线性模型预测控制方法,解决部分观测动态系统的最优控制问题。 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🔗
4 MoECollab: Democratizing LLM Development Through Collaborative Mixture of Experts MoECollab:通过协作式混合专家模型 democratize 大语言模型开发 large language model

⬅️ 返回 cs.LG 首页 · 🏠 返回主页