OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models

• URL: http://arxiv.org/abs/2511.14582v1
• Date: Tue, 18 Nov 2025 15:22:32 GMT
• Title: OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models
• Abstract summary: We present a training-free, audio-visual token-compression framework that optimize multimodal token representation and inference.<n>Specifically, OmniZip first identifies salient audio tokens, then computes an audio retention score for each time group to capture information.<n>For each time window, OmniZip compresses the video tokens using an interleaved-temporal scheme.
• Score: 21.542205813984243
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Omnimodal large language models (OmniLLMs) have attracted increasing research attention of late towards unified audio-video understanding, wherein processing audio-video token sequences creates a significant computational bottleneck, however. Existing token compression methods have yet to accommodate this emerging need of jointly compressing multimodal tokens. To bridge this gap, we present OmniZip, a training-free, audio-guided audio-visual token-compression framework that optimizes multimodal token representation and accelerates inference. Specifically, OmniZip first identifies salient audio tokens, then computes an audio retention score for each time group to capture information density, thereby dynamically guiding video token pruning and preserving cues from audio anchors enhanced by cross-modal similarity. For each time window, OmniZip compresses the video tokens using an interleaved spatio-temporal scheme. Extensive empirical results demonstrate the merits of OmniZip - it achieves 3.42X inference speedup and 1.4X memory reduction over other top-performing counterparts, while maintaining performance with no training.

Related papers

• Omni2LoRA: Coherence-Preserving Parametric Memory for Efficient Omni Language Models [65.49950267695267]
  We introduce Omni2LoRA, a framework for efficient parametric memory compression via coherence-preserving context distillation.<n>By converting multimodal memory into a fixed-budget, reusable parameter state, our method drives answer-time multimodal-token load to zero.
  arXiv  Detail & Related papers  (2026-08-10T07:49:10Z)
• Deferred Audio Pruning with Local Audio-Visual Dynamics for Omni-LLMs [13.179456385239481]
  A-Pack is a framework that defers audio pruning until query-conditioned multimodal interactions emerge.<n>A-Pack achieves the strongest average performance among the evaluated prior methods.<n>It reduces prefill FLOPs by up to 78% and improving decoding throughput by up to 2.21x.
  arXiv  Detail & Related papers  (2026-08-09T16:18:41Z)
• VLZip: Unified Visual and Textual Compression for Interleaved Long-Context Modeling [81.92510561363197]
  We introduce VLZip, a framework that unifies visual and textual compression for high-fidelity reasoning within a pure Transformer.<n>We also introduce LongVLBench, a new benchmark derived from video narratives that demands holistic, narrative-level reasoning.
  arXiv  Detail & Related papers  (2026-08-09T10:31:03Z)
• VoxZip: Semantic-Anchored Temporal KV Cache Compression for Long-Context Audio Inference [53.883871460875234]
  VoxZip is a semantic-anchored KV cache compression framework.<n>First stage uses automatic speech recognition (ASR) transcriptions as explicit semantic anchors to temporally align, compress, and fuse audio tokens.<n>Second stage employs a dynamic filtering strategy based on temporally decayed accumulated attention to evict non-essential tokens.
  arXiv  Detail & Related papers  (2026-08-09T08:17:18Z)
• 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)
• 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)
• OmniSelect: Dynamic Modality-Aware Token Compression for Efficient Omni-modal Large Language Models [49.34557936004057]
  We propose a training-free, modality-adaptive token pruning framework that dynamically selects appropriate compression strategies for multimodal inputs.<n>Our method achieves efficient multimodal token reduction while maintaining strong performance, without requiring any additional training.
  arXiv  Detail & Related papers  (2026-05-18T08:33:52Z)
• OmniRefine: Alignment-Aware Cooperative Compression for Efficient Omnimodal Large Language Models [14.355322423471018]
  We propose a training-free two-stage framework for efficient audio-visual token compression in Omni-LLMs.<n>First, Correspondence-Preserving Chunk Refinement refines native chunk boundaries into cross-modally aligned compression units.<n>Second, Modality-Aware Cooperative Compression jointly compresses video and audio tokens within each refined unit to reduce redundancy while preserving critical evidence.
  arXiv  Detail & Related papers  (2026-05-12T12:42:44Z)
• DASH: Dynamic Audio-Driven Semantic Chunking for Efficient Omnimodal Token Compression [5.201210378318278]
  We propose Dynamic Audio-driven Semantic cHunking (DASH) to align token compression with semantic structure.<n>DASH treats audio embeddings as a semantic anchor and detects boundary candidates via cosine-similarity discontinuities.<n> experiments on AVUT, VideoMME, and WorldSense demonstrate that DASH maintains superior accuracy while achieving higher compression ratios compared to prior methods.
  arXiv  Detail & Related papers  (2026-03-15T15:22:06Z)
• OmniZip: Learning a Unified and Lightweight Lossless Compressor for Multi-Modal Data [20.09409492679677]
  Lossless compression is essential for efficient data storage and transmission.<n>We propose textbf OmniZip, a unified and lightweight compressor for multi-modal data.<n>Built on a lightweight backbone, OmniZip incorporates three key components to enable efficient multi-modal compression.
  arXiv  Detail & Related papers  (2026-02-25T13:51:08Z)
• OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models [42.615226139135174]
  We propose OmniSIFT, a token compression framework tailored for Omni-LLMs.<n>The entire framework is optimized end-to-end via a differentiable straight-through estimator.<n>With merely 25% of the original token context, OmniSIFT consistently outperforms all compression baselines and even surpasses the performance of the full-token model on several tasks.
  arXiv  Detail & Related papers  (2026-02-04T17:51:05Z)
• EchoingPixels: Cross-Modal Adaptive Token Reduction for Efficient Audio-Visual LLMs [28.295585578439212]
  EchoingPixels is a framework inspired by the coexistence and interaction of visuals and sound in real-world scenes.<n>It reduces tokens from an entire combined pool of audio-visual tokens rather than using fixed budgets per modality.<n>It achieves performance comparable to strong baselines using only 5-20% of the original tokens, with a 2-3x speedup and memory reduction.
  arXiv  Detail & Related papers  (2025-12-11T06:18:58Z)
• FLoC: Facility Location-Based Efficient Visual Token Compression for Long Video Understanding [55.700832127331324]
  FLoC is an efficient visual token compression framework based on the facility location function.<n>Our method achieves remarkable efficiency gains by swiftly selecting a compact subset of tokens.<n>Our approach is training-free, model-agnostic, and query-agnostic, providing a versatile solution.
  arXiv  Detail & Related papers  (2025-10-31T17:29:39Z)
• VisionSelector: End-to-End Learnable Visual Token Compression for Efficient Multimodal LLMs [82.72388893596555]
  Multimodal Large Language Models (MLLMs) encounter significant computational and memory bottlenecks.<n>Previous token compression techniques are often constrained by rules that risk discarding critical information.<n>We reformulate token compression as a lightweight plug-and-play framework that reformulates token compression into an end-to-end learnable decision process.
  arXiv  Detail & Related papers  (2025-10-18T17:54:18Z)
• VibeVoice Technical Report [90.14596405668135]
  VibeVoice is a model designed to synthesize long-form speech with multiple speakers.<n>We introduce a novel continuous speech tokenizer that, when compared to the popular Encodec model, improves data compression by 80 times.
  arXiv  Detail & Related papers  (2025-08-26T17:09:12Z)
• LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs [23.801172170798132]
  LLaVA-Scissor is a training-free token compression strategy designed for multimodal large language models.<n>We propose to leverage the Semantic Connected Components ( SCC) approach to ensure comprehensive semantic coverage.<n>We conduct extensive evaluations of the token compression capabilities of LLaVA-Scissor across diverse video understanding benchmarks.
  arXiv  Detail & Related papers  (2025-06-27T02:29:58Z)
• VQToken: Neural Discrete Token Representation Learning for Extreme Token Reduction in Video Large Language Models [35.38573641029626]
  We introduce the novel task of Extreme Short Token Reduction, which aims to represent entire videos using a minimal set of discrete tokens.<n>On the Extreme Short Token Reduction task, our VQToken compresses sequences to just 0.07 percent of their original length while incurring only a 0.66 percent drop in accuracy on the NextQA-MC benchmark.
  arXiv  Detail & Related papers  (2025-03-21T09:46:31Z)
• Vision-centric Token Compression in Large Language Model [51.92055188780033]
  Vision Centric Token Compression (Vist) is a slow-fast compression framework that mirrors human reading.<n>On eleven in-context learning benchmarks, Vist achieves the same accuracy with 2.3 times fewer tokens, cutting FLOPs by 16% and memory by 50%.
  arXiv  Detail & Related papers  (2025-02-02T13:10:06Z)
• Whisper-GPT: A Hybrid Representation Audio Large Language Model [1.2328446298523066]
  A generative large language model (LLM) for speech and music that allows us to work with continuous audio representations and discrete tokens simultaneously as part of a single architecture.<n>We show how our architecture improves the perplexity and negative log-likelihood scores for the next token prediction compared to a token-based LLM for speech and music.
  arXiv  Detail & Related papers  (2024-12-16T05:03:48Z)
• PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models [64.9366388601049]
  Visual token compression is leveraged to reduce the considerable token length of visual inputs.<n>We introduce a unified token compression strategy called Progressive Visual Token Compression.<n>Our model achieves state-of-the-art performance across various video understanding benchmarks.
  arXiv  Detail & Related papers  (2024-12-12T18:59:40Z)
• DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models [28.379533608574814]
  We present DyCoke, a training-free token compression method to optimize token representation and accelerate video large language models.<n>DyCoke incorporates a plug-and-play temporal compression module to minimize temporal redundancy by merging redundant tokens across frames.<n>It ensures high-quality inference by dynamically retaining the critical tokens at each decoding step.
  arXiv  Detail & Related papers  (2024-11-22T15:55:19Z)
• Mirasol3B: A Multimodal Autoregressive model for time-aligned and contextual modalities [67.89368528234394]
  One of the main challenges of multimodal learning is the need to combine heterogeneous modalities. Video and audio are obtained at much higher rates than text and are roughly aligned in time. Our approach achieves the state-of-the-art on well established multimodal benchmarks, outperforming much larger models.
  arXiv  Detail & Related papers  (2023-11-09T19:15:12Z)

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.