Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Zhen-Hao Xie

Zhen-Hao Xie

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

Vision×1ML×1NLP×1

Frequent co-authors

Yu-Cheng Shi2×
Jun-Tao Tang2×
Da-Wei Zhou2×

Research Timeline

2026
ProtoAda: Prototype-Guided Adaptive Adapter Expansion and Geometric Consolidation for Multimodal Continual Instruction Tuning

ProtoAda introduces a prototype-guided, format-aware adaptive tuning framework to improve multimodal continual instruction tuning by ensuring task assignment and parameter updates respect heterogeneous output structures.

CRAM: Centroid-Routing and Adaptive MoE for Multimodal Continual Instruction Tuning

CRAM proposes a novel framework for Multimodal Continual Instruction Tuning that balances task isolation and parameter efficiency by using centroid-guided routing and adaptive MoE to prevent catastrophic forgetting.

Highlighted terms show continued research focus across papers

Papers

cs.CVcs.LGRecentJun 1, 2026

ProtoAda: Prototype-Guided Adaptive Adapter Expansion and Geometric Consolidation for Multimodal Continual Instruction Tuning

Yu-Cheng Shi, Zhen-Hao Xie, Jun-Tao Tang, Da-Wei Zhou

ProtoAda introduces a prototype-guided, format-aware adaptive tuning framework to improve multimodal continual instruction tuning by ensuring task assignment and parameter updates respect heterogeneou…

View →
cs.CLRecentJun 1, 2026

CRAM: Centroid-Routing and Adaptive MoE for Multimodal Continual Instruction Tuning

Jun-Tao Tang, Zhen-Hao Xie, Yu-Cheng Shi, Da-Wei Zhou

CRAM proposes a novel framework for Multimodal Continual Instruction Tuning that balances task isolation and parameter efficiency by using centroid-guided routing and adaptive MoE to prevent catastrop…

View →