Wenhan Lv — accepted AI-conference papers

2026

Hierarchical Enhancement of Semantic Priors for Disentangled Text-Driven Motion Generation

Wenhan Lv, Shaopan Wang, Xiangyu Wu, Tianchu Hang, Zhongquan Jian, Qingqiang Wu

CVPR 2026

Text-to-motion generation aims to synthesize realistic and semantically aligned 3D human motions from natural language descriptions. Existing diffusion-based methods often rely on isotropic latent priors and shallow cross-modal supervision, which lead to semantic entanglement, limited controllabilit

Cited by 0 Source ↗Scholar ↗

2026

MDF: A Modality-Aware Disentanglement and Fusion Framework for Multimodal Sentiment Analysis

Zhongquan Jian, Wenhan Lv, Yanhao Chen, Guanran Luo, Wentao Qiu, Shaopan Wang +2

AAAI 2026technical

The homogeneity and heterogeneity across modalities are critical factors that influence multimodal fusion. In Multimodal Sentiment Analysis (MSA), the inherent textual information within the audio modality induces cross-modality homogeneity with the text modality. Conversely, the mutual independence

Cited by 0 Source ↗PDF ↗Scholar ↗