文章预览
LG - 机器学习 CV - 计算机视觉 CL - 计算与语言 AS - 音频与语音 1、[LG] AI-Assisted Generation of Difficult Math Questions 2、[CL] Matryoshka-Adaptor:Unsupervised and Supervised Tuning for Smaller Embedding Dimensions 3、[LG] Relaxed Equivariant Graph Neural Networks 4、[LG] A Method for Fast Autonomy Transfer in Reinforcement Learning 5、[AS] Futga:Towards Fine-grained Music Understanding through Temporally-enhanced Generative Augmentation 摘要:人工智能辅助生成困难的数学问题、用于较低维度嵌入的无监督和监督微调、松弛等变图神经网络 、一种快速自主迁移的强化学习方法、通过时间增强的生成式增强实现细粒度音乐理解 1、[LG] AI-Assisted Generation of Difficult Math Questions V Shah, D Yu, K Lyu, S Park… [Mila & Princeton University] 人工智能辅助生成困难的数学问题 要点: 提出一个框架,通过结合大规模语言模型(LLM)和人类专业知识来生成新的、
………………………………