TriVLLo: Tri-View Dynamic Architecture and Unified Cross-Modal Representation for Efficient Fine-Grained Vision–Language Understanding
| Title: | TriVLLo: Tri-View Dynamic Architecture and Unified Cross-Modal Representation for Efficient Fine-Grained Vision–Language Understanding |
|---|---|
| Authors: | Kou, L.; Fan, W.; Huang, X.; Lin, B.; Yang, B.; Zhang, J.; Lin, Y.; Wang, M. |
| Source: | IEEE Transactions on Reliability IEEE Trans. Rel. Reliability, IEEE Transactions on. 75:1281-1290 2026 |
| Database: | IEEE Xplore Digital Library |