YongXiang Hua

According to our database, YongXiang Hua authored at least 5 papers between 2025 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2026

Dynamic Token Compression for Efficient Video Understanding through Reinforcement Learning.

Shida Wang, YongXiang Hua, Zhou Tao, Haoyu Cao, Linli Xu

CoRR, March, 2026

Multimodal Table Understanding with Difficulty-aware Reinforcement Learning.

Chaohu Liu, Haoyu Cao, YongXiang Hua, Linli Xu

Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025

DiG: Differential Grounding for Enhancing Fine-Grained Perception in Multimodal Large Language Model.

Zhou Tao, Shida Wang, YongXiang Hua, Haoyu Cao, Linli Xu

CoRR, December, 2025

Input Domain Aware MoE: Decoupling Routing Decisions from Task Optimization in Mixture of Experts.

YongXiang Hua, Haoyu Cao, Zhou Tao, Bocheng Li, Zihao Wu, Chaohu Liu, Linli Xu

Proceedings of the 33rd ACM International Conference on Multimedia, 2025

Dynamic Prefix as Instructor for Incremental Named Entity Recognition: A Unified Seq2Seq Generation Framework.

Zihao Wu, YongXiang Hua, Yongxin Zhu, Fang Zhang, Linli Xu

Proceedings of the Findings of the Association for Computational Linguistics, 2025