Zheqi Dai
4 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper addresses the modality gap between text and speech in spoken dialogue models by redesigning speech tokens to increase semantic density and efficiency.
A novel Token2Wav architecture is proposed to improve the efficiency of LLM-based TTS and multimodal systems.
This paper introduces Audio-Dependency Filtering (ADF) pipeline for Audio-Dependent Question Answering (ADQA) task in DCASE~2026, achieving top overall and sub-10B accuracy.
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.
Papers
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.