Yuanyuan Pu — accepted AI-conference papers

2026

Blocking the Leakage: Manifold-Aware Gradient Projection for Long-Horizon Test-Time Adaptation

Haoyu Xiong, Chengchao Wang, ZhongQiang Wang, Huang He, Qiuxia Yang, Zhengpeng Zhao +1

ICML 2026poster

Test-Time Adaptation (TTA) empowers pre-trained models to adapt online to distribution shifts during inference, but such online updates often become unstable in long-horizon deployments. Prevailing approaches attribute this failure to error accumulation from noisy pseudo-labels, relying on heuristic…

Cited by 0 Source ↗Scholar ↗

2024

Multimodal Sentiment Analysis Based on 3D Stereoscopic Attention

Jian Huang, Yuanyuan Pu, Dongming Zhou, Hang Shi, Zhengpeng Zhao, Dan Xu +1

ICASSP 2024accepted

In the multimodal (text, audio, and visual) sentiment analysis, the current methods generally consider the bi-modal sentiment interaction, resulting in inadequate mining and fusion of relations between modalities. In this paper, we propose the concept of multimodal 3D (3-Dimensional) stereoscopic at…

Cited by 0 Source ↗Scholar ↗