Ruohong Zhang

Exploiting Local and Global Features in Transformer-based Extreme Multi-label Text Classification

2022 · arXiv (Cornell University)

Extreme multi-label text classification (XMTC) is the task of tagging each document with the relevant labels from a very large space of predefined categories. Recently, large pre-trained Transformer models have made significant performance improvements in …

Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward

2025

Ruohong Zhang, Liangke Gui, Zhiqing Sun, Yihao Feng, Keyang Xu, Yuanhan Zhang, Di Fu, Chunyuan Li, Alexander G Hauptmann, Yonatan Bisk, Yiming Yang. Proceedings of the 2025 Conference of the Nations of the Americas Chapter …