ETC: Extreme Token Compression via Task-aware Visual Information Distillation in VLMs

• URL: http://arxiv.org/abs/2606.00543v1
• Date: Sat, 30 May 2026 05:28:43 GMT
• Title: ETC: Extreme Token Compression via Task-aware Visual Information Distillation in VLMs
• Abstract summary: High-resolution images produce a large number of visual tokens, resulting in high computational costs and KV-cache overhead during inference.<n>We propose an Extreme Token Compression framework that minimizes task loss when reducing the number of input tokens.<n>ETC remains effective even under single-token compression, substantially reducing KV-cache overhead while retaining strong task performance.
• Score: 34.659605252016036
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In Vision-Language Models (VLMs), high-resolution images produce a large number of visual tokens, resulting in high computational costs and KV-cache overhead during inference. To address this problem, we propose an Extreme Token Compression (ETC) framework that minimizes task loss when reducing the number of input tokens based on the principle of variational information distillation. Specifically, from an information-theoretic perspective, we show that minimizing task loss requires the compact representation to preserve the instruction-aware sufficient statistic of the task-relevant visual information for prediction. In practice, ETC leverages text-to-image cross-attention to weight the original visual features to approximate the latent instruction-aware predictive statistic. Moreover, ETC introduces a variational information distillation, enabling the compact representation to preserve the essential information to recover this predictive statistic. Experiments on LLaVA-1.5-7B and Qwen3-VL-2B show that ETC remains effective even under single-token compression, substantially reducing KV-cache overhead while retaining strong task performance.

Related papers

• VisCo: Leveraging Large Language Models as Intrinsic Encoders for Visual Token Compression [52.23010472235226]
  Vision-language models (VLMs) process large numbers of visual tokens, resulting in substantial inference and overhead latency.<n>We propose VisCo, a training-efficient self-compression framework that reuses the pretrained VLM itself as an intrinsic compressor.
  arXiv  Detail & Related papers  (2026-07-14T13:21:36Z)
• VEN-VL: A Visual Ensemble MoE Framework for Effective and Efficient Multi-Modal Understanding [50.904820090651974]
  VEN-VL is a visual ensemble MoE framework for effective and efficient perception.<n>We first enrich the information capacity by unifying the visual representations of different perspectives.<n>We then progressively compact it with adaptive routers in specialized visual experts to enhance the information density.
  arXiv  Detail & Related papers  (2026-05-25T15:28:48Z)
• VISion On Request: Enhanced VLLM efficiency with sparse, dynamically selected, vision-language interactions [51.41587958253802]
  We introduce VISion On Request (VISOR), a method that reduces inference cost without discarding visual information.<n>VISOR improves efficiency by sparsifying the interaction between image and text tokens.<n>Experiments show that VISOR drastically reduces computational cost while matching or exceeding state-of-the-art results.
  arXiv  Detail & Related papers  (2026-03-24T17:58:17Z)
• Less Is More -- Until It Breaks: Security Pitfalls of Vision Token Compression in Large Vision-Language Models [69.84867664371826]
  We show that visual token compression substantially degrades the robustness of Large Vision-Language Models (LVLMs)<n>Small and imperceptible perturbations can significantly alter token importance ranking, leading the compression mechanism to mistakenly discard task-critical information.<n>We propose a Compression-Aware Attack to systematically study and exploit this vulnerability.
  arXiv  Detail & Related papers  (2026-01-17T13:02:41Z)
• Compressor-VLA: Instruction-Guided Visual Token Compression for Efficient Robotic Manipulation [8.316354570715491]
  Vision-Language-Action (VLA) models have emerged as a powerful paradigm in Embodied AI.<n>We propose a novel hybrid instruction-conditioned token compression framework designed for efficient, task-oriented compression of visual information.<n>We show that our approach achieves a competitive success rate on the LIBERO benchmark while reducing FLOPs by 59% and the visual token count by over 3x compared to its baseline.
  arXiv  Detail & Related papers  (2025-11-24T10:06:41Z)
• Variation-aware Vision Token Dropping for Faster Large Vision-Language Models [24.952668143243542]
  Large vision-language models (LVLMs) have demonstrated remarkable capabilities in multimodal understanding tasks.<n> Token compression offers a direct solution by reducing the number of tokens to be processed, thereby improving computational efficiency.<n>We propose Variation-aware Vision Token Dropping (textiti.e., textbfV$2$Drop), which progressively removes visual tokens with minimal variation during LVLM inference.
  arXiv  Detail & Related papers  (2025-09-01T15:28:44Z)
• Efficient LLaMA-3.2-Vision by Trimming Cross-attended Visual Features [24.33252753245426]
  We exploit the sparse nature in cross-attention maps to selectively prune redundant visual features.<n>Our model can reduce inference latency and memory usage while achieving benchmark parity.
  arXiv  Detail & Related papers  (2025-04-01T09:10:32Z)
• TopV: Compatible Token Pruning with Inference Time Optimization for Fast and Low-Memory Multimodal Vision Language Model [56.43860351559185]
  We introduce textbfTopV, a compatible textbfTOken textbfPruning with inference Time Optimization for fast and low-memory textbfVLM.<n>Our framework incorporates a visual-aware cost function to measure the importance of each source visual token, enabling effective pruning of low-importance tokens.
  arXiv  Detail & Related papers  (2025-03-24T01:47:26Z)
• 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)
• Efficient Large Multi-modal Models via Visual Context Compression [23.966237939194514]
  We present the study on the analysis of redundancy concerning visual tokens and efficient training within large language models. Our initial experiments show that eliminating up to 70% of visual tokens at the testing stage by simply average pooling only leads to a minimal 3% reduction in visual question answering accuracy. We introduce Visual Context on the GQA benchmark, which reduces the number of visual tokens to enhance training and inference efficiency without sacrificing performance.
  arXiv  Detail & Related papers  (2024-06-28T17:57:14Z)
• 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)
• Disentangled Representation Learning with Transmitted Information Bottleneck [57.22757813140418]
  We present textbfDisTIB (textbfTransmitted textbfInformation textbfBottleneck for textbfDisd representation learning), a novel objective that navigates the balance between information compression and preservation.
  arXiv  Detail & Related papers  (2023-11-03T03:18:40Z)

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.