Skip to content
conftrace_

early exit mechanism

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

model acceleration (2) token-level exit (1) visual language model (1) bert inference (1) token-level early exit (1) inference cost (1) attention map (1) bounding box prediction (1) inference acceleration (1) token pruning (1)

Papers

A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs CVPR 2025 Exploring Efficient and Effective Sequence Learning for Visual Object Tracking IJCAI 2025 Accelerating BERT Inference for Sequence Labeling via Early-Exit ACL 2021