Esoteric Language Models: A Family of Any-Order Diffusion LLMs 文章

ArXiv CS.CL2026-06-01NEWSen作者: Subham Sekhar Sahoo, Zhihan Yang, Yash Akhauri, Johnna Liu, Deepansha Singh, Zhoujun Cheng, Zhengzhong Liu, Eric Xing, John Thickstun, Arash Vahdat
查看原文 →
关系图谱

Esoteric Language Models: A Family of Any-Order Diffusion LLMs · 相关技术

相关技术

Any-Order autoregressive modelsautoregressive modelscausal attentionKV cachingmasked diffusion modelsdiffusion-based language models