Jiajun Xu
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces MTAVG-Bench 2.0, a new benchmark designed to diagnose high-level failure modes of cinematic expressiveness in multi-talker audio-video generation, showing that even advanced models struggle with complex scene-level failures.
This paper proposes Multi-Block Diffusion Language Models (MBD-LMs) for text generation, which are obtained by post-training Block Diffusion Language Models (BD-LMs) with Multi-block Teacher Forcing (MultiTF). MBD-LMs improve inter-block parallelism and wall-clock acceleration.
Papers
Multi-Block Diffusion Language Models
Yijie Jin, Jiajun Xu, Yuxuan Liu, Chenkai Xu +7 more
This paper proposes Multi-Block Diffusion Language Models (MBD-LMs) for text generation, which are obtained by post-training Block Diffusion Language Models (BD-LMs) with Multi-block Teacher Forcing (…