cs.LG（2025-10-09）

📊 共 7 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

#	题目	一句话要点	标签	🔗
1	Better Together: Leveraging Unpaired Multimodal Data for Stronger Unimodal Models	提出UML，利用非配对多模态数据增强单模态模型表示学习	representation learning multimodal
2	MMM: Quantum-Chemical Molecular Representation Learning for Combinatorial Drug Recommendation	MMM：利用量子化学分子表示学习进行组合药物推荐，提升DDI预测。	representation learning multimodal
3	Reinforcement Learning-Driven Edge Management for Reliable Multi-view 3D Reconstruction	提出基于强化学习的边缘管理框架，提升多视角3D重建在动态环境下的可靠性。	reinforcement learning
4	Reinforcing Diffusion Models by Direct Group Preference Optimization	提出直接群体偏好优化(DGPO)，加速并提升扩散模型的强化学习训练。	reinforcement learning large language model	✅
5	Dual-granularity Sinkhorn Distillation for Enhanced Learning from Long-tailed Noisy Data	提出双粒度Sinkhorn蒸馏(D-SINK)框架，提升长尾噪声数据下的模型学习能力。	distillation

#	题目	一句话要点	标签	🔗	⭐
6	DEAS: DEtached value learning with Action Sequence for Scalable Offline RL	DEAS：利用动作序列和解耦价值学习实现可扩展的离线强化学习	manipulation reinforcement learning offline RL
7	Zero-Shot Policy Transfer in Reinforcement Learning using Buckingham's Pi Theorem	利用白金汉π定理实现强化学习中的零样本策略迁移	sim-to-real reinforcement learning zero-shot transfer