Beyond Selection: Token Parameterization for Extreme Visual Token Compression

2026-09-28

AI Summary

This study addresses the degradation of spatial localization caused by visual token pruning and the high computational overhead of resamplers under extreme compression. To this end, we propose Braco, a lightweight encoder that decouples compressibility from learnability objectives. Braco introduces a four-step parameterized encoding pipeline incorporating orthogonal reparameterization, input-agnostic basis coordinate embedding, and spatial residual token pooling, achieving efficient visual compression through basis transform truncation and coordinate reassembly. Experimental results demonstrate that Braco preserves 95.2% localization accuracy at a 64× compression ratio while reducing FLOPs by over 84% and improving inference speed by 36%, thereby establishing an effective balance between extreme compression and model performance.

Abstract

Visual-token compression is effective for improving the efficiency of vision-language models, but under extreme compression budgets, token pruning can break visual grounding while learned resamplers increase parameter count, attention cost, and training complexity. We revisit compression through a token parameterization lens, separating (i) basis transformation and structured truncation (retained subspace/compressibility) from (ii) coordinate organization (optimization and cross-modal alignment). This view yields two coupled objectives, compressibility and learnability, which we formalize as unified functionals. Guided by these objectives, we design Braco, a lightweight four-step coder that combines transform-basis truncation, input-independent basis-coordinate embeddings, budget-dependent orthogonal re-parameterization, and learned spatial residual tokens from lightweight pooling. Experiments show that Braco forms the favorable empirical accuracy-efficiency frontier under $23\times$--$64\times$ compression and remains competitive at $144\times$, reaching 95.2% accuracy while reducing prefill FLOPs by 84.2%--86.7% relative to the uncompressed upper bound. Against prior methods, Braco matches or improves accuracy while achieving up to approximately 36% end-to-end speedup and using $16.6\times$/$78.8\times$ lower compressor latency/FLOPs.

Problem

• Visual token compression
• Vision-language models
• Extreme compression
• Token pruning
• Learned resamplers

Innovation

• Visual Token Compression
• Token Parameterization
• Orthogonal Re-parameterization
• Vision-Language Models
• Braco