Out of Sight, Still in Mind: Token Compression for Omni-LLMs

• URL: http://arxiv.org/abs/2607.21179v1
• Date: Thu, 23 Jul 2026 11:09:24 GMT
• Title: Out of Sight, Still in Mind: Token Compression for Omni-LLMs
• Abstract summary: We propose ReMo, a framework that compresses visual tokens by redistributing their information across modalities.<n>On Qwen2.5- Omni at two model scales, ReMo removes 54% of the input tokens with no loss in accuracy.
• Score: 34.925891815982865
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The goal of this paper is to reduce the input token cost of Omni-modal large language models (Omni-LLMs) at inference time. Omni-LLMs reason jointly over audio, video and text, but the cost of the three streams is highly unbalanced: visual tokens account for the vast majority of the input, and are highly redundant. In this paper, we propose ReMo, a training-free framework that compresses visual tokens by redistributing their information across modalities: a visual token is kept only if its information appears nowhere else. ReMo achieves this in two ways: (i) it aligns audio and video in a common embedding space, and removes visual tokens already explained by the audio or by other visual tokens; and (ii) it replaces object-level visual tokens with compact text proxies, short descriptions of each object and its location, conveying the same content in far fewer tokens. On Qwen2.5-Omni at two model scales, ReMo removes 54% of the input tokens with no loss in accuracy. Indeed, it slightly exceeds the full-token model, reaching 101.2% and 101.3% of its average accuracy over five audio-visual benchmarks.

Related papers

• Omni-Prune: Query-Aware Unified Token Pruning for Efficient Omnimodal Large Language Models [18.902147033940434]
  Omni-Prune is a training-free, query-aware audio-visual token pruning framework.<n>It removes redundancy from both modalities while keeping task-relevant cross-modal evidence.<n>It delivers up to 3.25x prefill speedup and 1.3x memory reduction while retaining over 99% of full-model performance.
  arXiv  Detail & Related papers  (2026-07-26T03:51:39Z)
• OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models [23.801162485653478]
  We propose a training-free token compression framework that uses the query as a shared semantic anchor while estimating relevance separately for audio and video.<n>Across four audio-video benchmarks and two Qwen2.5- Omni model scales, OmniScope achieves the best average accuracy across all compression settings.<n>These results suggest a simple design principle for OmniLLM inference: share the query across modalities, but not the salience estimates.
  arXiv  Detail & Related papers  (2026-07-25T13:16:04Z)
• OmniFocus: Query-Guided Modality-Balanced Token Compression for Omni-Modal Large Language Models [72.34361439042634]
  We propose a training-free query-guided token compression method for OmniLLMs that performs independent importance estimation for video and audio.<n>Experiments on the Qwen2.5- Omni model family across four audio-visual benchmarks show that OmniFocus maintains strong compressed performance at low token retention ratios.
  arXiv  Detail & Related papers  (2026-07-03T07:41:00Z)
• Audio-Visual Exchange-Aware Token Pruning for Efficient Audio-Visual Captioning [30.40330199901482]
  We propose a AVEX-Prune, an RL-based audio-visual dynamic token pruning method.<n> AVEX-Prune preserves full-token quality at a 40% retention ratio on both VILA 1.5-8B and VideoLLaMA 2.
  arXiv  Detail & Related papers  (2026-06-09T08:04:06Z)
• Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs [38.874953063372416]
  We propose ContextGuard as an inference-time token pruning framework.<n> ContextGuard predicts coarse visual semantics from audio and prunes video tokens.<n>It achieves full-token-level performance on five of six benchmarks while pruning 55% of input tokens.
  arXiv  Detail & Related papers  (2026-05-12T06:35:29Z)
• ElasticTok: Adaptive Tokenization for Image and Video [109.75935878130582]
  We introduce ElasticTok, a method that conditions on prior frames to adaptively encode a frame into a variable number of tokens.<n>During inference, ElasticTok can dynamically allocate tokens when needed.<n>Our evaluations on images and video demonstrate the effectiveness of our approach in efficient token usage.
  arXiv  Detail & Related papers  (2024-10-10T20:54:15Z)
• SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference [45.11612407862277]
  In vision-language models (VLMs), visual tokens usually bear a significant amount of computational overhead despite sparsity of information in them when compared to text tokens.<n>We propose a text-guided training-free token optimization mechanism dubbed SparseVLM that eliminates the need of extra parameters or fine-tuning costs.
  arXiv  Detail & Related papers  (2024-10-06T09:18:04Z)
• Matryoshka Query Transformer for Large Vision-Language Models [103.84600181927884]
  We introduce the Matryoshka Query Transformer (MQT), capable of encoding an image into m visual tokens during inference. We train a single model once, and flexibly and drastically reduce the number of inference-time visual tokens. Our model, MQT-LLAVA, matches LLaVA-1.5 performance across 11 benchmarks using a maximum of 256 tokens instead of LLaVA's fixed 576.
  arXiv  Detail & Related papers  (2024-05-29T17:39:42Z)
• How can objects help action recognition? [74.29564964727813]
  We investigate how we can use knowledge of objects to design better video models. First, we propose an object-guided token sampling strategy that enables us to retain a small fraction of the input tokens. Second, we propose an object-aware attention module that enriches our feature representation with object information.
  arXiv  Detail & Related papers  (2023-06-20T17:56:16Z)
• DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification [134.9393799043401]
  We propose a dynamic token sparsification framework to prune redundant tokens based on the input. By hierarchically pruning 66% of the input tokens, our method greatly reduces 31%37% FLOPs and improves the throughput by over 40%. DynamicViT models can achieve very competitive complexity/accuracy trade-offs compared to state-of-the-art CNNs and vision transformers on ImageNet.
  arXiv  Detail & Related papers  (2021-06-03T17:57:41Z)

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.