文章预览
LG - 机器学习 CV - 计算机视觉 CL - 计算与语言 1、[LG] Few-Shot Task Learning through Inverse Generative Modeling 2、[LG] Unlearning in- vs. out-of-distribution data in LLMs under gradient-based method 3、[CL] BitNet a4.8:4-bit Activations for 1-bit LLMs 4、[LG] Bio-xLSTM:Generative modeling, representation and in-context learning of biological and chemical sequences 5、[CL] The Semantic Hub Hypothesis:Language Models Share Semantic Representations Across Languages and Modalities 摘要:基于逆生成建模的少样本任务学习、基于梯度法的大语言模型分布内与分布外数据遗忘学习、1bit大语言模型的4bit激活、生物和化学序列的生成建模表示和上下文学习、语言模型跨语言和模态共享语义表示 1、[LG] Few-Shot Task Learning through Inverse Generative Modeling A Netanyahu, Y Du, A Bronars, J Pari... [MIT] 基于逆生成建模的少样本任务学习 要点: 基于逆向生成模型的小样本任务
………………………………