conftrace_

dynamic token pruning

3 papers

Explore in graph

Also known as

DTP

Co-occurring keywords · papers mentioning both

model compression (2) token sparsification (1) vision-language transformer (1) small language model (1) model efficiency (1) attention masking (1) dynamic computation (1) multimodal alignment (1) inference acceleration (1) token pruning (1)

Papers

MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer CVPR 2024 Length-Adaptive Distillation: Customizing Small Language Model for Dynamic Token Pruning EMNLP 2023 DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification NeurIPS 2021