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

Qize Yang

2 indexed papers

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

Publications per year

2
26

Top categories

Audio and Speech Processing×1AI×1Image and Video Processing×1Vision×1NLP×1Sound×1

Frequent co-authors

Yunfei Chu2×
Jin Xu2×
Haolin He1×
Qi Chen1×
Wen Huang1×
Yuan Feng1×

Research Timeline

2026
Native Active Perception as Reasoning for Omni-Modal Understanding

The paper proposes OmniAgent, a native omni-modal agent that formulates video understanding as a POMDP-based iterative Observation-Thought-Action cycle, enabling active perception and improving performance with increasing reasoning turns.

OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue

The paper presents OmniVChat-Studio, a multi-agent data engine for synthesizing audio-visual dialogues, and OmniVChat-RL, a reinforcement learning reward design for evaluating omni models.

Highlighted terms show continued research focus across papers

Papers

eess.AScs.AIeess.IVEmpiricalRecentSep 18, 2026

OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue

Haolin He, Yunfei Chu, Qi Chen, Wen Huang +14 more

The paper presents OmniVChat-Studio, a multi-agent data engine for synthesizing audio-visual dialogues, and OmniVChat-RL, a reinforcement learning reward design for evaluating omni models.

View →
cs.CVcs.CLcs.SDEmpirical
Recent
Jun 17, 2026

Native Active Perception as Reasoning for Omni-Modal Understanding

Zhenghao Xing, Ruiyang Xu, Yuxuan Wang, Jinzheng He +7 more

The paper proposes OmniAgent, a native omni-modal agent that formulates video understanding as a POMDP-based iterative Observation-Thought-Action cycle, enabling active perception and improving perfor…

View →