STAR-Pro: Stage-Wise Token Adaptive Reduction with Progressive Refinement for Efficient Large Vision-Language Models

arXiv:2609.05916 · cs.CV, cs.AI · Submitted 2026-09-05 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-09-05

Updated: 2026-09-05

Comments: 26 pages, 7 figures

Code: https://github.com/EasonAI-5589/starpro

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Pruning — 6× in this paper · explained in 4 episodes
• Vision-language models — 2× in this paper · explained in 2 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Computational overhead — 1× in this paper · explained in 2 episodes
• Two-Stage Framework — 1× in this paper · explained in 2 episodes

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models