Structured Redundancy Modeling for Efficient Visual Token Pruning in High-Resolution MLLMs

• URL: http://arxiv.org/abs/2607.23046v1
• Date: Sat, 25 Jul 2026 05:08:22 GMT
• Title: Structured Redundancy Modeling for Efficient Visual Token Pruning in High-Resolution MLLMs
• Abstract summary: We propose a structural reformulation of visual token pruning that embeds redundancy control directly into the scoring space.<n>We show that our approach maintains stable selection costs, reducing the token selection process by up to 110 ms, from 112.4 ms to just 2.5 ms at 512 tokens in Qwen2.5-VL.
• Score: 9.080169376642433
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent high-resolution Multimodal Large Language Models (MLLMs) generate thousands of visual tokens per input, leading to a visual token explosion that introduces severe latency bottlenecks. While token pruning mitigates this issue, state-of-the-art subset-optimization methods typically rely on iterative subset construction to jointly capture visual diversity and instruction relevance. As visual token counts scale, this sequential dependency introduces significant selection overhead, severely limiting the translation of theoretical FLOPs reductions into actual wall-clock speedups. To address this limitation, we propose Single-Forward Pruner (SFPruner), a structural reformulation of visual token pruning that embeds redundancy control directly into the scoring space, bypassing the need for iterative combinatorial optimization. Our non-iterative framework achieves redundancy-aware importance selection in a single forward pass through two complementary mechanisms. First, to attenuate redundancy at the covariance level, we introduce a semantics-guided ridge leverage scheme. By integrating instruction relevance and visual saliency, this mechanism suppresses dominant covariance directions and mitigates representation bias. Second, ranking-based directional masking resolves residual overlap through asymmetric similarity competition, where higher-scoring tokens explicitly suppress redundant lower-scoring alternatives via parallel tensor operations. Extensive evaluations demonstrate that our approach maintains stable selection costs, reducing the token selection process by up to 110 ms, from 112.4 ms to just 2.5 ms at 512 tokens in Qwen2.5-VL. This structural efficiency successfully translates theoretical token reductions into tangible inference speedups while preserving highly competitive performance against state-of-the-art techniques under aggressive compression.

Related papers

• Accelerating Hierarchical Sparse Predictive Coding with Hybrid Amortized Inference [0.0]
  We show that a shallow LISTA-style initializer plus short corrective recurrence improves over pure amortization while remaining much faster than long iterative inference.<n>Results show that a shallow LISTA-style initializer plus short corrective recurrence improves over pure amortization while remaining much faster than long iterative inference.
  arXiv  Detail & Related papers  (2026-06-26T07:38:55Z)
• Adaptive Tokenisation Via Temporal Redundancy Masking And Latent Inpainting [18.71433885255431]
  Adaptive video tokenisation seeks to dynamically allocate token budgets based on the underlying visual complexity of a sequence.<n>We show that the latent space of a frozen continuous video tokeniser inherently encodes temporal redundancy that can be exploited directly.<n>We introduce a parameter-free adaptive token allocation mechanism that applies a fixed threshold to per-position temporal-L1 differences.
  arXiv  Detail & Related papers  (2026-06-04T13:31:12Z)
• Where to Refine, When to Stop: Rethinking Redundancy via Latent Discrepancy for Efficient Visual Autoregressive Generation [50.139984798361375]
  We propose a training-free framework that removes redundancy via latent discrepancy.<n> LD-Pruning substantially reduces inference while maintaining high generation quality, achieving up to 2.35x speedup on Infinity-8B.
  arXiv  Detail & Related papers  (2026-05-29T19:34:39Z)
• Rethinking Token Reduction for Diffusion Models via Output-Similarity-Awareness [2.5966966127729454]
  Diffusion Transformers (DiTs) achieve superior image generation quality but suffer from quadratic computational complexity relative to token count.<n>We propose DiTo, a novel TR paradigm that shifts the focus toward output-centric token reduction.<n>Experiments demonstrate that DiTo consistently outperforms existing TR methods with 1.6-3.9 dB higher PSNR at comparable speedups.
  arXiv  Detail & Related papers  (2026-05-21T05:18:42Z)
• Efficient-LVSM: Faster, Cheaper, and Better Large View Synthesis Model via Decoupled Co-Refinement Attention [105.11288339285154]
  Efficient-LVSM is a dual-stream architecture that applies intra-view self-attention for input views and self-then-cross attention for target views.<n>It achieves 29.86 dB PSNR on RealEstate10K with 2 input views, surpassing LVSM by 0.2 dB, with 2x faster training convergence and 4.4x faster inference speed.
  arXiv  Detail & Related papers  (2026-02-06T08:11:58Z)
• Training-free Context-adaptive Attention for Efficient Long Context Modeling [57.703159205740185]
  Training-free Context-adaptive Attention (TCA-Attention) is a training-free sparse attention mechanism that selectively attends to only the informative tokens for efficient long-context inference.<n>TCA-Attention achieves a 2.8$times$ speedup and reduces KV cache by 61% at 128K context length while maintaining performance comparable to full attention.
  arXiv  Detail & Related papers  (2025-12-10T01:54:57Z)
• Repulsor: Accelerating Generative Modeling with a Contrastive Memory Bank [65.00301565190824]
  mname is a plug-and-play training framework that requires no external encoders.<n>mname achieves a state-of-the-art FID of textbf2.40 within 400k steps, significantly outperforming comparable methods.
  arXiv  Detail & Related papers  (2025-12-09T14:39:26Z)
• PT$^2$-LLM: Post-Training Ternarization for Large Language Models [52.4629647715623]
  Large Language Models (LLMs) have shown impressive capabilities across diverse tasks, but their large memory and compute demands hinder deployment.<n>We propose PT$2$-LLM, a post-training ternarization framework tailored for LLMs.<n>At its core is an Asymmetric Ternary Quantizer equipped with a two-stage refinement pipeline.
  arXiv  Detail & Related papers  (2025-09-27T03:01:48Z)
• MPQ-DMv2: Flexible Residual Mixed Precision Quantization for Low-Bit Diffusion Models with Temporal Distillation [74.34220141721231]
  We present MPQ-DMv2, an improved textbfMixed textbfPrecision textbfQuantization framework for extremely low-bit textbfDiffusion textbfModels.
  arXiv  Detail & Related papers  (2025-07-06T08:16:50Z)
• PAR: Prompt-Aware Token Reduction Method for Efficient Large Multimodal Models [32.33892531885448]
  Multimodal large language models (MLLMs) demonstrate strong performance across visual tasks.<n>But their efficiency is hindered by significant computational and memory demands from processing long contexts in multimodal inputs.<n>We introduce PAR (Prompt-Aware Token Reduction), a novel and plug-and-play approach that reduces visual tokens efficiently without compromising model performance.
  arXiv  Detail & Related papers  (2024-10-09T07:13:22Z)
• TPC-ViT: Token Propagation Controller for Efficient Vision Transformer [6.341420717393898]
  Vision transformers (ViTs) have achieved promising results on a variety of Computer Vision tasks. Previous approaches that employ gradual token reduction to address this challenge assume that token redundancy in one layer implies redundancy in all the following layers. We propose a novel token propagation controller (TPC) that incorporates two different token-distributions.
  arXiv  Detail & Related papers  (2024-01-03T00:10:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.