cs.LG（2025-06-01）
📊 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) (2 🔗1)
支柱七：动作重定向 (Motion Retargeting) (1)
🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Action Dependency Graphs for Globally Optimal Coordinated Reinforcement Learning | 提出基于动作依赖图的全局最优协同强化学习方法 | reinforcement learning | ||
| 2 | Closing the Gap between TD Learning and Supervised Learning with $Q$-Conditioned Maximization | 提出GCReinSL，通过Q值条件最大化弥合TD学习与监督学习在离线强化学习中的差距 | reinforcement learning offline RL offline reinforcement learning | ||
| 3 | Generalized Linear Markov Decision Process | 提出广义线性MDP框架，解决传统线性MDP在非线性奖励场景下的局限性 | reinforcement learning offline RL | ||
| 4 | Accelerated Learning with Linear Temporal Logic using Differentiable Simulation | 提出结合可微仿真与线性时序逻辑的学习方法以解决稀疏奖励问题 | reinforcement learning differentiable simulation |
🔬 支柱九：具身大模型 (Embodied Foundation Models) (2 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 5 | Uni-LoRA: One Vector is All You Need | Uni-LoRA：提出一种单向量LoRA统一框架，实现极致参数高效的LLM微调。 | large language model | ✅ | |
| 6 | SafeSteer: Interpretable Safety Steering with Refusal-Evasion in LLMs | SafeSteer：利用类别特定steering vectors在LLM中实现可解释的安全引导与拒绝规避 | large language model |
🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 7 | Beyond Attention: Learning Spatio-Temporal Dynamics with Emergent Interpretable Topologies | 提出InterGAT模型，通过可解释拓扑学习提升时空预测性能与效率。 | spatial relationship |