4 papers
Aligning Multimodal Sequential Recommendations via Robust Direct Preference Optimization with Sparse MoE
Hejin Huang, Jusheng Zhang, Kaitong Cai +2
Preference-based alignment objectives have been widely adopted, from RLHF-style pairwise learning in large language models to emerging applications in recommender systems. Yet, exi…
HandX: Scaling Bimanual Motion and Interaction Generation
Zimu Zhang, Yucheng Zhang, Xiyan Xu +8
Synthesizing human motion has advanced rapidly, yet realistic hand motion and bimanual interaction remain underexplored. Whole-body models often miss the fine-grained cues that dri…
FatigueFormer: Static-Temporal Feature Fusion for Robust sEMG-Based Muscle Fatigue Recognition
Tong Zhang, Hong Guo, Shuangzhou Yan +3
We present FatigueFormer, a semi-end-to-end framework that deliberately combines saliency-guided feature separation with deep temporal modeling to learn interpretable and generaliz…
Aesthetic Assessment of Chinese Handwritings Based on Vision Language Models
Chen Zheng, Yuxuan Lai, Haoyang Lu +3
The handwriting of Chinese characters is a fundamental aspect of learning the Chinese language. Previous automated assessment methods often framed scoring as a regression problem.…