Soomin Rho, Sangki Park, Subin Park, Kwangrae Kim, Min-Gwon Song, Ki-Seok Chung. TiMM-ViT: Token-Importance-Aware Token Merging with Multi-Exit Training and an FPGA-based Vision Transformer Accelerator for Image Classification. In Proceedings of the ACM/IEEE International Symposium on Low Power Electronics and Design, ISLPED 2026, Evanston, IL, USA, August 5-7, 2026. ACM, 2026. [doi]
Abstract is missing.