Lionel Z. Wang — accepted AI-conference papers

2026

AudioTrust: Benchmarking The Multifaceted Trustworthiness of Audio Large Language Models

Kai Li, Can Shen, Yile Liu, Jirui Han, Kelong zheng, Xuechao Zou +28

ICLR 2026poster

The rapid development and widespread adoption of Audio Large Language Models (ALLMs) require a rigorous assessment of their trustworthiness. However, existing evaluation frameworks, primarily designed for text, are not equipped to handle the unique vulnerabilities introduced by audio’s acoustic prop…

Cited by 0 Source ↗code ↗Scholar ↗

2026

DeAR: Fine-Grained VLM Adaptation by Decomposing Attention Head Roles

Yiming Ma, Hongkun Yang, Lionel Z. Wang, Bin Chen, Weizhi Xian, Jianzhi Teng

CVPR 2026

Prompt learning is a dominant paradigm for adapting pre-trained Vision-Language Models (VLMs) to downstream tasks. However, existing methods often rely on a simplistic, layer-centric view, assuming shallow layers capture general features while deep layers handle task-specific knowledge. This assumpt

Cited by 0 Source ↗Scholar ↗