{"slug": "scopd-sparse-context-on-policy-self-distillation-for-efficient-vision-language", "title": "SCOPD: Sparse-Context On-Policy Self-Distillation for Efficient Vision-Language Models", "summary": "Researchers introduced SCOPD (Sparse-Context On-Policy Self-Distillation), a method for efficient vision-language models that addresses the performance degradation caused by training-free token pruning of long visual-token sequences. The approach targets the irreversible loss of task-relevant visual information that occurs under aggressive compression, which makes inference expensive for reasoning VLMs processing images and videos.", "body_md": "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", "url": "https://wpnews.pro/news/scopd-sparse-context-on-policy-self-distillation-for-efficient-vision-language", "canonical_source": "https://aiflash.com/news/128605/", "published_at": "2026-09-29 15:30:13+00:00", "updated_at": "2026-09-29 15:50:03.326339+00:00", "lang": "en", "topics": ["computer-vision", "large-language-models", "machine-learning", "ai-research"], "entities": ["SCOPD"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/scopd-sparse-context-on-policy-self-distillation-for-efficient-vision-language", "markdown": "https://wpnews.pro/news/scopd-sparse-context-on-policy-self-distillation-for-efficient-vision-language.md", "text": "https://wpnews.pro/news/scopd-sparse-context-on-policy-self-distillation-for-efficient-vision-language.txt", "jsonld": "https://wpnews.pro/news/scopd-sparse-context-on-policy-self-distillation-for-efficient-vision-language.jsonld"}}