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

Yu Bai

2 indexed papers

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

Publications per year

2
26

Top categories

Crypto×1ML×1Software Eng.×1AI×1Multimedia×1Sound×1

Frequent co-authors

Bin Duan1×
Zeyu Bai1×
Guowei Yang1×
Haitian Li1×
Yanghao Zhou1×
Heyan Huang1×

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.

Toward a Generalized Defense Across Sparse, Continuous, and Structured Parameter Attacks

The paper introduces ParDef, a generalized defense mechanism that effectively mitigates various types of parameter attacks on deep neural networks while maintaining high performance.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.LGcs.SERecentJun 3, 2026

Toward a Generalized Defense Across Sparse, Continuous, and Structured Parameter Attacks

Bin Duan, Zeyu Bai, Guowei Yang

The paper introduces ParDef, a generalized defense mechanism that effectively mitigates various types of parameter attacks on deep neural networks while maintaining high performance.

View →
cs.AIcs.MMcs.SDRecentMay 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 →