cs.LG（2025-07-01）

📊 共 4 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

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

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

#题目一句话要点标签🔗⭐
1 Audio-3DVG: Unified Audio -- Point Cloud Fusion for 3D Visual Grounding 提出Audio-3DVG框架，融合音频与点云信息，提升3D视觉定位性能 representation learning visual grounding
2 Residual Reward Models for Preference-based Reinforcement Learning 提出残差奖励模型以解决偏好强化学习收敛慢的问题 reinforcement learning policy learning inverse reinforcement learning ✅
3 Data-Driven Exploration for a Class of Continuous-Time Indefinite Linear--Quadratic Reinforcement Learning Problems 提出自适应探索机制以解决连续时间LQ强化学习问题 reinforcement learning

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

#题目一句话要点标签🔗⭐
4 MoNE: Replacing Redundant Experts with Lightweight Novices for Structured Pruning of MoE 提出MoNE以解决MoE模型冗余专家带来的内存开销问题 large language model ✅

⬅️ 返回 cs.LG 首页 · 🏠 返回主页