collaborators

19 papers

cs.SD2026

VCB Bench: An Evaluation Benchmark for Audio-Grounded Large Language Model Conversational Agents

Jiliang Hu, Wenfu Wang, Zuchao Li +6

Recent advances in large audio language models (LALMs) have greatly enhanced multimodal conversational systems. However, existing benchmarks remain limited -- they are mainly Engli…

cs.SD2026

VoiceTTA: Enhancing Zero-Shot Text-to-Speech via Reinforcement Learning-Based Test-Time Adaptation

Tianxin Xie, Chenxing Li, Dong Yu +1

Recently, zero-shot text-to-speech (TTS) has enabled high-fidelity and expressive speech synthesis, but it often fails to imitate unseen speaking styles from uncommon scenarios (e.…

cs.CL2026

Escape the Language Prior: Mitigating Late-Stage Modality Collapse in Audio Reasoning via Modality-Aware Policy Optimization

Cihan Xiao, Yiwen Shao, Chenxing Li +5

Audio and omni-modal large language models exhibit impressive cross-modal reasoning capabilities. However, applying standard reinforcement learning post-training algorithms to thes…

cs.SD2026

PhyAVBench: A Challenging Audio Physics-Sensitivity Benchmark for Physically Grounded Text-to-Audio-Video Generation

Tianxin Xie, Wentao Lei, Kai Jiang +27

Text-to-audio-video (T2AV) generation is central to applications such as filmmaking and world modeling. However, current models often fail to produce physically plausible sounds. P…

cs.SD2026

Audio-DeepThinker: Progressive Reasoning-Aware Reinforcement Learning for High-Quality Chain-of-Thought Emergence in Audio Language Models

Xiang He, Chenxing Li, Jinting Wang +5

Large Audio-Language Models (LALMs) have made significant progress in audio understanding, yet they primarily operate as perception-and-answer systems without explicit reasoning pr…

cs.CV2026

Frequency-guided Multi-level Reasoning for Scene Graph Generation in Video

Chenxing Li, Yiping Duan, Xiaoming Tao

Video Scene Graph Generation aims to obtain structured semantic representations of objects and their relationships in videos for high-level understanding. However, existing methods…