作者位次 #3/4ICLR 2026Poster· Applications / Time Series
Latent-to-Data Cascaded Diffusion Models for Unconditional Time Series Generation
Lifeng Shen · Kai Syun Hou · Weiyu Chen · James Kwok
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Lifeng Shen · Kai Syun Hou · Weiyu Chen · James Kwok
Yuyan Zhou · Weiyu Chen · James Kwok
Diffusion-based Large Language Models (dLLMs) are emerging as a powerful alternative to traditional autoregressive models. These models learn to generate text by iteratively denoising masked sequences. In this work, we identify a critical problem in dLLMs: the model’s attention is wastefully expe...