cs.LG（2024-12-25）

📊 共 6 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

#	题目	一句话要点	标签	🔗
1	Constraint-Adaptive Policy Switching for Offline Safe Reinforcement Learning	提出约束自适应策略切换(CAPS)框架，解决离线安全强化学习中约束变化适应问题	reinforcement learning offline RL	✅
2	Elucidating Flow Matching ODE Dynamics with Respect to Data Geometries and Denoisers	理论分析流匹配ODE动态，揭示数据几何与去噪器作用机制	flow matching
3	Effective and Lightweight Representation Learning for Link Sign Prediction in Signed Bipartite Graphs	提出ELISE：一种高效轻量级的符号二部图链接符号预测方法	representation learning
4	Optimistic Critic Reconstruction and Constrained Fine-Tuning for General Offline-to-Online RL	提出乐观Critic重构与约束微调方法，实现通用离线到在线强化学习	reinforcement learning offline RL

#	题目	一句话要点	标签	🔗	⭐
5	Renaissance of Literate Programming in the Era of LLMs: Enhancing LLM-Based Code Generation in Large-Scale Projects	提出互操作性文学编程(ILP)以提升LLM在大型项目中的代码生成能力	large language model
6	Torque-Aware Momentum	提出扭矩感知动量优化器(TAM)，解决传统动量优化器在大梯度下的震荡问题。	large language model