Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Jiajun Xu

Jiajun Xu

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

ML×1NLP×1AI×1Multimedia×1Sound×1

Frequent co-authors

Yijie Jin1×
Yuxuan Liu1×
Chenkai Xu1×
Yi Tu1×
Jiajun Li1×
Dandan Tu1×

Research Timeline

2026
MTAVG-Bench 2.0: Diagnosing Failure Modes of Cinematic Expressiveness in Multi-Talker Audio-Video Generation

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.

Multi-Block Diffusion Language Models

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.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.CLEmpiricalRecentJun 28, 2026

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 (…

View →
cs.AIcs.MMcs.SDRecent
May 27, 2026

MTAVG-Bench 2.0: Diagnosing Failure Modes of Cinematic Expressiveness in Multi-Talker Audio-Video Generation

Haitian Li, Yanghao Zhou, Heyan Huang, Liangji Chen +14 more

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 model…

View →