# SCOPD: Sparse-Context On-Policy Self-Distillation for Efficient Vision-Language Models > Source: > Published: 2026-09-29 15:30:13+00:00 Reasoning vision-language models (VLMs) process images and videos as long sequences of visual tokens, making inference expensive. Training-free token pruning reduces this cost, but aggressive compression can sharply degrade performance, often attributed to irreversible loss of task-relevant visual i