Tutorials
Just Respect the Semantics: Image-Token Compression via Pre-LLM Semantic Variable-Resolution Tokenization and In-LLM Relevance Pruning
arXiv:2610.18690v1 Announce Type: new Abstract: Image-token compression must reduce computation without hurting the semantics. We introduce Varest, guided by semantic fungibility: tokens within a cohe
arXiv:2610.18690v1 Announce Type: new Abstract: Image-token compression must reduce computation without hurting the semantics. We introduce Varest, guided by semantic fungibility: tokens within a coherent semantic region can be summarized coarsely, while object boundaries and literal text require finer distinctions. Object and text localizers guide variable-resolution merging, preserving spatial coverage and finer detail at boundaries and text. Learned [REL] registers then prune visual tokens after early decoder processing. Training across budgets enables one checkpoint per backbone. Across three backbones and 13 benchmarks, Varest outperforms 15 baselines in mean performance retention at every evaluated budget, retaining 86.10-92.33% of full-token performance with only 5.56% of the original layer-averaged image-token count.
Related
- Learnable Token Sparsification for Efficient Gigapixel Whole Slide Image Reasoning
- Structured State-Space Regularization for Compact and Generation-Friendly Image Tokenization
- DiffPrune: differentiable information throttling for token pruning in vision-language models
Source: arXiv cs.CV | 2026-10-14