cs.LG（2024-12-24）

📊 共 8 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

#	题目	一句话要点	标签	🔗
1	Diverse and Effective Red Teaming with Auto-generated Rewards and Multi-step Reinforcement Learning	提出基于自动生成奖励和多步强化学习的红队测试方法，提升攻击的多样性和有效性。	reinforcement learning large language model
2	Enhancing Online Continual Learning with Plug-and-Play State Space Model and Class-Conditional Mixture of Discretization	提出S6MOD即插即用模块，提升在线持续学习模型适应性和性能。	state space model distillation
3	Graph Structure Learning for Spatial-Temporal Imputation: Adapting to Node and Feature Scales	提出多尺度图结构学习框架GSLI，用于解决时空数据填补中异构空间关系建模问题	representation learning spatial relationship
4	NoiseHGNN: Synthesized Similarity Graph-Based Neural Network For Noised Heterogeneous Graph Representation Learning	提出NoiseHGNN以解决有噪声的异构图表示学习问题	representation learning	✅
5	U-Mamba-Net: A highly efficient Mamba-based U-net style network for noisy and reverberant speech separation	提出U-Mamba-Net，一种高效的基于Mamba的U型网络，用于噪声和混响语音分离	Mamba
6	Quantum framework for Reinforcement Learning: Integrating Markov decision process, quantum arithmetic, and trajectory search	提出一种量子强化学习框架，利用量子算术和轨迹搜索实现全量子MDP。	reinforcement learning

#	题目	一句话要点	标签	🔗	⭐
7	MixMAS: A Framework for Sampling-Based Mixer Architecture Search for Multimodal Fusion and Learning	MixMAS：一种基于采样的多模态融合架构搜索框架	multimodal
8	Learning Randomized Reductions	Bitween：利用线性回归和神经符号方法自动学习随机自归约	large language model