{"slug": "who-speaks-for-the-pruned-visual-token-pruning-as-coverage-optimization", "title": "Who Speaks for the Pruned? Visual Token Pruning as Coverage Optimization", "summary": "Researchers propose CoverPruner, a training-free visual token pruner for vision-language models (VLMs) that frames pruning as Representational Coverage Maximization (RCM), ensuring each removed token is represented by a surviving original token. In tests across multiple VLM architectures and compression rates, CoverPruner achieves the best average accuracy among compared methods, with largest gains under aggressive compression.", "body_md": "arXiv:2609.03158v1 Announce Type: new\nAbstract: Visual token pruning reduces the inference cost of vision-language models (VLMs), but most methods only ask which tokens to keep. This retained-token view can keep redundant high-scoring tokens while leaving discarded evidence without a close representative. We propose CoverPruner, a training-free pruner that asks the complementary demand-side question: after a token is removed, which surviving original token represents it for the target VLM? CoverPruner formulates pruning as Representational Coverage Maximization (RCM), covering the full projected visual-token set with query-weighted demand. It instantiates RCM with projector-space coverage and a lightweight first-layer attention probe. Across multiple VLM architectures and compression rates, CoverPruner achieves the best average accuracy among all compared methods, with the largest gains usually appearing under aggressive compression.", "url": "https://wpnews.pro/news/who-speaks-for-the-pruned-visual-token-pruning-as-coverage-optimization", "canonical_source": "https://arxiv.org/abs/2609.03158", "published_at": "2026-09-04 04:00:00+00:00", "updated_at": "2026-09-04 04:24:32.774814+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "computer-vision", "ai-research"], "entities": ["CoverPruner", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/who-speaks-for-the-pruned-visual-token-pruning-as-coverage-optimization", "markdown": "https://wpnews.pro/news/who-speaks-for-the-pruned-visual-token-pruning-as-coverage-optimization.md", "text": "https://wpnews.pro/news/who-speaks-for-the-pruned-visual-token-pruning-as-coverage-optimization.txt", "jsonld": "https://wpnews.pro/news/who-speaks-for-the-pruned-visual-token-pruning-as-coverage-optimization.jsonld"}}