cs.LG（2025-04-13）

📊 共 9 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

#	题目	一句话要点	标签	🔗
1	DUMP: Automated Distribution-Level Curriculum Learning for RL-based LLM Post-training	提出DUMP框架以解决RL基础LLM后训练中的数据分布调度问题	reinforcement learning curriculum learning large language model	✅
2	GenEDA: Towards Generative Netlist Functional Reasoning via Cross-Modal Circuit Encoder-Decoder Alignment	GenEDA：通过跨模态电路编码器-解码器对齐实现生成式网表功能推理	representation learning large language model foundation model
3	Causal integration of chemical structures improves representations of microscopy images for morphological profiling	MICON：利用化学结构因果整合，提升细胞形态学图谱的表征学习	representation learning contrastive learning multimodal
4	Adaptive Insurance Reserving with CVaR-Constrained Reinforcement Learning under Macroeconomic Regimes	提出基于CVaR约束强化学习的自适应保险准备金方法，应对宏观经济环境变化。	reinforcement learning PPO
5	Can LLMs Revolutionize the Design of Explainable and Efficient TinyML Models?	利用LLM驱动的神经架构搜索设计高效可解释的TinyML模型	distillation large language model

#	题目	一句话要点	标签
6	Integrating Large Language Models for Automated Structural Analysis	提出集成LLM的自动化结构分析框架，解决工程结构分析效率问题。	large language model
7	Federated Learning with Layer Skipping: Efficient Training of Large Language Models for Healthcare NLP	提出层跳跃联邦学习，高效训练医疗NLP大语言模型	large language model
8	Ordinary Least Squares as an Attention Mechanism	将普通最小二乘法(OLS)重构为一种受限的注意力机制，为理解注意力机制提供新视角。	large language model
9	Quantization Error Propagation: Revisiting Layer-Wise Post-Training Quantization	提出量化误差传播（QEP）框架，提升低比特量化下LLM的层间量化精度。	large language model