TOPS: First-Principles Visual Token Pruning via Constructing Token Optimal Preservation Sets for Efficient MLLM Inference

• URL: http://arxiv.org/abs/2606.27161v1
• Date: Thu, 25 Jun 2026 15:29:37 GMT
• Title: TOPS: First-Principles Visual Token Pruning via Constructing Token Optimal Preservation Sets for Efficient MLLM Inference
• Abstract summary: Multimodal large language models (MLLMs) have achieved strong multimodal reasoning capabilities, but their efficiency is limited by the large number of visual tokens.<n>Visual token pruning offers a natural solution, yet existing methods are imperfect.<n>We propose TOPS, a training-free and model-agnostic pruning module that can be applied to various MLLMs.
• Score: 54.41143483594129
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal large language models (MLLMs) have achieved strong multimodal reasoning capabilities, but their efficiency is limited by the large number of visual tokens, which introduces substantial computational overhead. Visual token pruning offers a natural solution, yet existing methods are imperfect: attention-based criteria tend to retain redundant tokens, while diversity-based criteria are often agnostic to user instructions. Even methods that combine multiple criteria still lack a principled formulation of the intrinsic objective of token pruning. In this paper, we revisit visual token pruning from a first-principles perspective and formulate it as constructing Token Optimal Preservation Sets. Through a top-down information-theoretic analysis, we identify three fundamental principles for effective token selection: Task Relevance, Information Coverage, and Semantic Diversity. Based on these principles, we propose TOPS, a training-free and model-agnostic pruning module that can be applied to various MLLMs. Extensive experiments on 7 MLLM backbones and 14 benchmarks demonstrate that TOPS outperforms prior methods under diverse pruning settings. Notably, on LLaVA-NeXT, TOPS removes 77.8% of visual tokens while preserving 100.0% and 100.6% performance on its 7B and 13B models, respectively, suggesting that pruning redundant visual tokens can sometimes mitigate hallucination and inspire future lightweight MLLM design.

Related papers

• An AI4AI Framework for Visual Token Pruning [30.316781118289043]
  We build an AI4AI framework for visual-token pruning.<n>AutoPrune is a training-free framework for visual-token pruning policy design.
  arXiv  Detail & Related papers  (2026-08-07T13:07:40Z)
• LAST: The Last Query Token Guides Visual Token Pruning for Edge-Cloud Collaborative MLLM Inference [63.932718076408584]
  LAST is a training-free framework for query-dependent visual token pruning in edge-cloud collaborative MLLM inference.<n>It preserves 95.4% of the full-token accuracy while retaining only 12.5% of the visual tokens, with low edge-side selection overhead and reduced cloud-side computation.
  arXiv  Detail & Related papers  (2026-07-30T09:59:25Z)
• Moving Beyond Diversity: Visual Token Pruning as Subspace Reconstruction for Efficient VLMs [7.371189496638082]
  We introduce SPARE, a subspace reconstruction method that reformulates token pruning as a column subset selection problem.<n>We show that SPARE consistently achieves state-of-the-art performance, with strong gains on tasks.
  arXiv  Detail & Related papers  (2026-06-17T04:45:10Z)
• QAPruner: Quantization-Aware Vision Token Pruning for Multimodal Large Language Models [18.353831760548267]
  Multimodal Large Language Models (MLLMs) have shown strong reasoning ability, but their high computational and memory costs hinder deployment in resource-constrained settings.<n>While Post-Training Quantization (PTQ) and vision token pruning are standard compression techniques, they are usually treated as independent optimizations.<n>In this paper, we show that these two techniques are strongly coupled: naively applying semantic-based token pruning to PTQ-optimized MLLMs can discard activation outliers that are important for numerical stability and thus worsen quantization errors in low-bit regimes.<n>We propose a quantization-aware vision token pruning framework
  arXiv  Detail & Related papers  (2026-04-03T07:32:07Z)
• Bridging Perception and Reasoning: Token Reweighting for RLVR in Multimodal LLMs [51.60575965819268]
  We propose a plug-and-play Token-Reweighting (ToR) strategy that explicitly models this interdependence.<n>ToR delivers consistent performance gains across multiple multi-modal reasoning benchmarks.
  arXiv  Detail & Related papers  (2026-03-26T06:25:27Z)
• IDPruner: Harmonizing Importance and Diversity in Visual Token Pruning for MLLMs [11.254129271889035]
  Visual token pruning has emerged as a critical technique for accelerating MLLM inference.<n>IDPruner achieves state-of-the-art performance and superior generalization across diverse architectures and tasks.
  arXiv  Detail & Related papers  (2026-02-10T11:20:24Z)
• SCOPE: Saliency-Coverage Oriented Token Pruning for Efficient Multimodel LLMs [59.415473779171315]
  We propose a novel visual token pruning strategy called textbfSaliency-textbfCoverage textbfOriented token textbfPruning for textbfEfficient MLLMs.
  arXiv  Detail & Related papers  (2025-10-28T09:29:37Z)
• ZSPAPrune: Zero-Shot Prompt-Aware Token Pruning for Vision-Language Models [7.7352936204066]
  We propose a novel, zero-shot method to model visual token pruning as a balance between task relevance and information diversity.<n>Our method achieves performance that matches or surpasses the state-of-the-art with only minimal accuracy loss.<n>These gains are accompanied by significant reductions in GPU memory footprint and inference latency.
  arXiv  Detail & Related papers  (2025-10-20T06:18:47Z)
• FrugalPrompt: Reducing Contextual Overhead in Large Language Models via Token Attribution [3.4666771782038652]
  Large language models (LLMs) owe much of their stellar performance to expansive input contexts, yet such verbosity inflates monetary costs, carbon footprint, and inference-time latency.<n>We introduce FrugalPrompt, a novel prompt compression framework for LLMs, which retains only the most semantically significant tokens.<n>We evaluate the approach across four NLP tasks: Sentiment Analysis, Commonsense QA, Summarization, and Mathematical Reasoning.
  arXiv  Detail & Related papers  (2025-10-18T10:22:13Z)
• VFlowOpt: A Token Pruning Framework for LMMs with Visual Information Flow-Guided Optimization [70.98122339799218]
  Large Multimodal Models (LMMs) excel in visual-language tasks by leveraging numerous visual tokens for fine-grained visual information.<n>Previous research aimed at reducing visual tokens during inference typically leverages importance maps derived from attention scores among vision-only tokens or vision-language tokens to prune tokens across one or multiple pruning stages.<n>We propose VFlowOpt, a token pruning framework that introduces an importance map derivation process and a progressive pruning module with a recycling mechanism.<n> Experiments demonstrate that VFlowOpt can prune 90% of visual tokens while maintaining comparable performance, leading to an 89% reduction in KV-Cache memory and 3.8
  arXiv  Detail & Related papers  (2025-08-07T09:47:21Z)
• The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models [69.798277882245]
  We introduce Unsupervised Prefix Fine-Tuning (UPFT) to enhance large language models' reasoning efficiency.<n>UPFT removes the need for labeled data or exhaustive sampling.<n> Experiments show that UPFT matches the performance of supervised methods.
  arXiv  Detail & Related papers  (2025-03-04T18:56:03Z)
• Enhancing Item Tokenization for Generative Recommendation through Self-Improvement [67.94240423434944]
  Generative recommendation systems are driven by large language models (LLMs)<n>Current item tokenization methods include using text descriptions, numerical strings, or sequences of discrete tokens.<n>We propose a self-improving item tokenization method that allows the LLM to refine its own item tokenizations during training process.
  arXiv  Detail & Related papers  (2024-12-22T21:56:15Z)
• Inference Optimal VLMs Need Fewer Visual Tokens and More Parameters [54.01228554126122]
  Vision Language Models (VLMs) have demonstrated strong capabilities across various visual understanding and reasoning tasks.<n>To reduce inference costs, one can either downsize the Large Language Models (LLMs) or reduce the number of input tokens needed to represent the image.<n>We take the first steps toward designing token compression algorithms tailored for high-compression settings.
  arXiv  Detail & Related papers  (2024-11-05T18:54:21Z)

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.