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

Ziyang Cheng

2 indexed papers

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

Publications per year

2
26

Top categories

NLP×1AI×1

Frequent co-authors

Yanfeng Wang2×
Yu Wang2×
Heyang Liu1×
Jiayi Huang1×
Wenyang Xiao1×
Ronghua Wu1×

Research Timeline

2026
Agentic Active Omni-Modal Perception for Multi-Hop Audio-Visual Reasoning

The paper introduces MOV-Bench, a challenging benchmark for multi-hop audio-visual reasoning, and proposes AOP-Agent, an agentic framework that significantly improves open-source Omni-LLMs' ability to perform active cross-modal perception.

LaSR: Context-Aware Speech Recognition via Latent Reasoning

The paper proposes LaSR, a context-aware training paradigm that uses latent reasoning to significantly improve speech recognition, especially for specialized terminology, without adding latency.

Highlighted terms show continued research focus across papers

Papers

cs.CLRecentMay 30, 2026

LaSR: Context-Aware Speech Recognition via Latent Reasoning

Heyang Liu, Ziyang Cheng, Jiayi Huang, Wenyang Xiao +4 more

The paper proposes LaSR, a context-aware training paradigm that uses latent reasoning to significantly improve speech recognition, especially for specialized terminology, without adding latency.

View →
cs.AIRecentMay 27, 2026

Agentic Active Omni-Modal Perception for Multi-Hop Audio-Visual Reasoning

Ke Xu, Yuhao Wang, Ziyang Cheng, Hongcheng Liu +2 more

The paper introduces MOV-Bench, a challenging benchmark for multi-hop audio-visual reasoning, and proposes AOP-Agent, an agentic framework that significantly improves open-source Omni-LLMs' ability to…

View →