Skip to content
conftrace_

token reduction

77 papers

Explore in graph

Also known as

TR

Co-occurring keywords · papers mentioning both

model compression (21) large language model (16) efficient computing (15) vision transformer (14) vision-language model (12) multimodal large language model (9) computational efficiency (9) video understanding (8) multimodal learning (8) inference efficiency (7)

Papers

A-ViT: Adaptive Tokens for Efficient Vision Transformer CVPR 2022 IA-RED$^2$: Interpretability-Aware Redundancy Reduction for Vision Transformers NeurIPS 2021