cs.LG（2024-02-17）

📊 共 11 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

#	题目	一句话要点	标签	🔗
1	Knowledge Distillation Based on Transformed Teacher Matching	提出转化教师匹配的知识蒸馏方法以提升学生模型泛化能力	distillation	✅
2	Aligning Large Language Models by On-Policy Self-Judgment	提出SELF-JUDGE框架以高效对齐大型语言模型与人类偏好	policy learning large language model instruction following
3	Deep Reinforcement Learning Based Toolpath Generation for Thermal Uniformity in Laser Powder Bed Fusion Process	提出基于深度强化学习的工具路径生成以解决激光粉末床熔融过程中的热不均匀问题	reinforcement learning deep reinforcement learning DRL
4	SINR-Aware Deep Reinforcement Learning for Distributed Dynamic Channel Allocation in Cognitive Interference Networks	提出CARLTON以解决认知干扰网络中的动态信道分配问题	reinforcement learning deep reinforcement learning
5	Multi Task Inverse Reinforcement Learning for Common Sense Reward	提出多任务逆强化学习以解决常识奖励问题	reinforcement learning inverse reinforcement learning
6	Debiased Offline Representation Learning for Fast Online Adaptation in Non-stationary Dynamics	提出DORA以解决非平稳动态下的离线表示学习问题	reinforcement learning representation learning
7	Reinforcement learning to maximise wind turbine energy generation	提出强化学习策略以最大化风力发电效率	reinforcement learning

#	题目	一句话要点	标签	🔗
8	TuneTables: Context Optimization for Scalable Prior-Data Fitted Networks	提出TuneTables以优化大规模先验数据拟合网络的上下文	large language model	✅
9	ZeroG: Investigating Cross-dataset Zero-shot Transferability in Graphs	提出ZeroG框架以解决图数据的跨数据集零-shot迁移问题	large language model foundation model zero-shot transfer	✅
10	Mirror Gradient: Towards Robust Multimodal Recommender Systems via Exploring Flat Local Minima	提出Mirror Gradient以增强多模态推荐系统的鲁棒性	multimodal	✅
11	Turn Waste into Worth: Rectifying Top-$k$ Router of MoE	提出Rectify-Router以解决MoE模型中的冗余计算问题	large language model