G$^2$TR: Generation-Guided Visual Token Reduction for Separate-Encoder Unified Multimodal Models

• URL: http://arxiv.org/abs/2605.12309v2
• Date: Fri, 15 May 2026 11:58:28 GMT
• Title: G$^2$TR: Generation-Guided Visual Token Reduction for Separate-Encoder Unified Multimodal Models
• Abstract summary: We propose a generation-guided visual token reduction framework for separate-encoder Unified multimodal models.<n>G$2$TR estimates token importance from consistency with VAE latent, performs balanced token selection, and merges redundant tokens into retained representatives.<n>Experiments show that G$2$TR substantially reduces visual tokens and prefill computation by 1.94x while maintaining both reasoning accuracy and editing quality.
• Score: 33.010296874246215
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The development of separate-encoder Unified multimodal models (UMMs) comes with a rapidly growing inference cost due to dense visual token processing. In this paper, we focus on understanding-side visual token reduction for improving the efficiency of separate-encoder UMMs. While this topic has been widely studied for MLLMs, existing methods typically rely on attention scores, text-image similarity and so on, implicitly assuming that the final objective is discriminative reasoning. This assumption does not hold for UMMs, where understanding-side visual tokens must also preserve the model's capabilities for editing images. We propose G$^2$TR, a generation-guided visual token reduction framework for separate-encoder UMMs. Our key insight is that the generation branch provides a task-agnostic signal for identifying understanding-side visual tokens that are not only semantically relevant but also important for latent-space image reconstruction and generation. G$^2$TR estimates token importance from consistency with VAE latent, performs balanced token selection, and merges redundant tokens into retained representatives to reduce information loss. The method is training-free, plug-and-play, and applied only after the understanding encoding stage, making it compatible with existing UMM inference pipelines. Experiments on image understanding and editing benchmarks show that G$^2$TR substantially reduces visual tokens and prefill computation by 1.94x while maintaining both reasoning accuracy and editing quality, outperforming baselines on almost all benchmarks. Code is at: https://github.com/lijunxian111/G2TR.

Related papers

• Where Does Generative Difficulty Reside? An Empirical Study of Target Representations [62.54876287800644]
  The target representation defines the distribution an image generator must learn, yet it is often treated as an interchangeable interface.<n>We study raw pixels, SD-VAE latents and DINOv2 as well as MAE representation-autoencoder features within a unified masked autoregressive rectified-flow model.<n>Our results show that compression, reconstruction fidelity, token dimensionality, and visible semantic clustering do not individually predict generative behavior.
  arXiv  Detail & Related papers  (2026-08-01T12:32:31Z)
• TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models [6.132992639292891]
  Vision-Language Models (VLMs) have demonstrated impressive capabilities across different tasks, but their computational cost is dominated by the large number of visual tokens fed to the model.<n>We introduce TORINO, a plug-and-play framework for adaptive visual token reduction in VLMs that requires no fine-tuning of the underlying model.
  arXiv  Detail & Related papers  (2026-07-06T01:43:09Z)
• ERA: Entropy-Guided Visual Token Pruning with Rectified Attention for Efficient MLLMs [77.57757084153083]
  We propose ERA, an Entropy-guided visual token pruning framework with Rectified Attention for efficient MLLMs.<n> ERA comprises three crucial components: Dual-view Entropy Pruning (DEP), Bias-aware Token Recycling (BTR), and Logit-preserving Attention Rectification (LAR)
  arXiv  Detail & Related papers  (2026-06-30T17:20:29Z)
• Beyond Scalar Distances: Semantic Attribute Gradients from Frozen MLLMs for Visual Embeddings [9.571136962907888]
  Vision encoders for retrieval are typically trained with class-label supervision.<n>A multimodal large language model (MLLM) can articulate those attributes and use them to predict whether the images share a class.<n>We propose textbfSAGA, a framework that turns this language-grounded, attribute-aware perception into a training signal for the encoder itself.
  arXiv  Detail & Related papers  (2026-06-13T05:50:40Z)
• [CLS] is Not Enough: Multi-Label Recognition via Patch-Level Inference and Adaptive Aggregation [20.637119409165418]
  PIAA formulates prediction as Patch-level Inference followed by Adaptive Aggregation.<n>We introduce an adaptive aggregation module that consolidates patch-level scores into the final multi-label prediction.<n>Experiments show that our method achieves strong improvements with minimal extra computation.
  arXiv  Detail & Related papers  (2026-05-25T13:19:12Z)
• RCP: Representation Consistency Pruner for Mitigating Distribution Shift in Large Vision-Language Models [24.3914653184824]
  Large Vision-Language Models (LVLMs) suffer from prohibitive inference costs due to the massive number of visual tokens processed by the language decoder.<n>Existing pruning methods often lead to significant performance degradation because the irreversible removal of visual tokens causes a distribution shift in the hidden states that deviates from the pre-trained full-token regime.<n>We propose Consistency Representation Pruner, which integrates cumulative visual token pruning with a delayed repair mechanism.
  arXiv  Detail & Related papers  (2026-04-04T13:31:45Z)
• Cheers: Decoupling Patch Details from Semantic Representations Enables Unified Multimodal Comprehension and Generation [66.53544128707817]
  Cheers is a unified multimodal model that decouples patch-level details from semantic representations.<n> Cheers matches or surpasses advanced UMMs in both visual understanding and generation.
  arXiv  Detail & Related papers  (2026-03-13T08:55:27Z)
• ConsensusDrop: Fusing Visual and Cross-Modal Saliency for Efficient Vision Language Models [4.273730624882391]
  Vision-Language Models (VLMs) are expensive because the LLM processes hundreds of largely redundant visual tokens.<n>We show that neither signal alone is sufficient: fusing them consistently improves performance compared to unimodal visual token selection (ranking)<n>We propose textbfConsensusDrop, a training-free framework that derives a emphconsensus ranking by reconciling vision encoder saliency with query-aware cross-attention.
  arXiv  Detail & Related papers  (2026-02-01T00:28:55Z)
• 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)
• Rethinking Visual Token Reduction in LVLMs under Cross-modal Misalignment [38.04426918886084]
  Vision-Language Models (LVLMs) encode visual inputs as dense sequences of patch-level tokens to capture fine-grained semantics.<n>Previous efforts have explored visual token reduction either prior to or within the large language models (LLMs)<n>We introduce VisionDrop, a training-free, visual-only pruning framework that selects informative visual tokens based on intra-modal (visual-to-visual) attention.
  arXiv  Detail & Related papers  (2025-06-27T14:55:40Z)
• ToDRE: Visual Token Pruning via Diversity and Task Awareness for Efficient Large Vision-Language Models [59.47738955960352]
  ToDRE is a two-stage and training-free token compression framework.<n>It achieves superior performance by pruning tokens based on token Diversity and token-task RElevance.
  arXiv  Detail & Related papers  (2025-05-24T15:47:49Z)
• QuoTA: Query-oriented Token Assignment via CoT Query Decouple for Long Video Comprehension [86.0749609778104]
  We propose QuoTA, an ante-hoc training-free modular that extends existing large video-language models.<n>QuoTA strategically allocates frame-level importance scores based on query relevance.<n>We decouple the query through Chain-of-Thoughts reasoning to facilitate more precise LVLM-based frame importance scoring.
  arXiv  Detail & Related papers  (2025-03-11T17:59:57Z)
• UniTok: A Unified Tokenizer for Visual Generation and Understanding [63.23796622553615]
  Visual generative and understanding models typically rely on distinct tokenizers to process images.<n>We introduce UniTok, a unified tokenizer featuring a novel multi-codebook quantization mechanism.<n>In terms of final performance, UniTok sets a new record of 0.38 rFID and 78.6% zero-shot accuracy on ImageNet.
  arXiv  Detail & Related papers  (2025-02-27T17:47:01Z)
• RedundancyLens: Revealing and Exploiting Visual Token Processing Redundancy for Efficient Decoder-Only MLLMs [38.34856927170692]
  We propose a training-free framework for analyzing trained Multimodal Large Language Model (MLLM)<n>It consists of Probe-Activated Dynamic FFN and Hollow Attention, which enable adjustable reductions in computations for visual tokens.<n>Experiments demonstrate substantial, structured, and clustered redundancy unique to decoder-only MLLMs.
  arXiv  Detail & Related papers  (2025-01-31T11:09:16Z)
• Reasoning to Attend: Try to Understand How <SEG> Token Works [44.33848900059659]
  We show that the $texttSEG>$ token contributes to semantic similarity within image-text pairs.<n>We present READ, which facilitates LMMs' resilient $textbfREA$soning capability of where to atten$textbfD$ under the guidance of highly activated points.
  arXiv  Detail & Related papers  (2024-12-23T17:44:05Z)
• Efficient Multi-modal Large Language Models via Visual Token Grouping [55.482198808206284]
  High-resolution images and videos pose a barrier to their broader adoption.<n> compressing vision tokens in MLLMs has emerged as a promising approach to reduce inference costs.<n>We introduce VisToG, a novel grouping mechanism that leverages the capabilities of pre-trained vision encoders to group similar image segments.
  arXiv  Detail & Related papers  (2024-11-26T09:36:02Z)
• 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)
• LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models [35.88374542519597]
  Large Multimodal Models (LMMs) have shown significant visual reasoning capabilities by connecting a visual encoder and a large language model. Recent LMMs incorporate more complex visual inputs, such as high-resolution images and videos, which further increases the number of visual tokens significantly. We propose PruMerge, a novel adaptive visual token reduction strategy that significantly reduces the number of visual tokens without compromising the performance of LMMs.
  arXiv  Detail & Related papers  (2024-03-22T17:59:52Z)

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.