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

arXiv: https://arxiv.org/abs/2511.14582 · HTML: https://mlsanity.com/paper/2511.14582/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Placed in Audio and omni-modal token compression, one of 12 directions in Efficient LLM inference and serving.
- Builds on 66 of its 76 references that are in the map.
- First posted on arXiv 18 Nov 2025.

## Placed in

- Efficient LLM inference and serving / [Audio and omni-modal token compression](https://mlsanity.com/inference/audio-and-omni-modal-token-compression/)

## Builds on (most cited first, 30 of 66)

- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis](https://mlsanity.com/paper/2405.21075/) (2024)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot](https://mlsanity.com/paper/2301.00774/) (2023)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [VideoChat: Chat-Centric Video Understanding](https://mlsanity.com/paper/2305.06355/) (2023)
- [A Simple and Effective Pruning Approach for Large Language Models](https://mlsanity.com/paper/2306.11695/) (2023)
- [Qwen2.5-Omni Technical Report](https://mlsanity.com/paper/2503.20215/) (2025)
- [An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models](https://mlsanity.com/paper/2403.06764/) (2024)
- [VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding](https://mlsanity.com/paper/2501.13106/) (2025)
- [Qwen3-Omni Technical Report](https://mlsanity.com/paper/2509.17765/) (2025)
- [SpinQuant: LLM quantization with learned rotations](https://mlsanity.com/paper/2405.16406/) (2024)
- [Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning](https://mlsanity.com/paper/2310.06694/) (2023)
- [LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models](https://mlsanity.com/paper/2403.15388/) (2024)
- [Kimi-VL Technical Report](https://mlsanity.com/paper/2504.07491/) (2025)
- [LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding](https://mlsanity.com/paper/2410.17434/) (2024)
- [LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models](https://mlsanity.com/paper/2407.12772/) (2024)
- [VisionZip: Longer is Better but Not Necessary in Vision Language Models](https://mlsanity.com/paper/2412.04467/) (2024)
- [PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction](https://mlsanity.com/paper/2410.17247/) (2024)

## Built on by (most cited first, 22 of 22)

- [OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models](https://mlsanity.com/paper/2602.04804/) (2026)
- [LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMs](https://mlsanity.com/paper/2603.19217/) (2026)
- [Active Perception Agent for Omnimodal Audio-Video Understanding](https://mlsanity.com/paper/2512.23646/) (2025)
- [DASH: Dynamic Audio-Driven Semantic Chunking for Efficient Omnimodal Token Compression](https://mlsanity.com/paper/2603.15685/) (2026)
- [Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs](https://mlsanity.com/paper/2605.11605/) (2026)
- [OmniRefine: Alignment-Aware Cooperative Compression for Efficient Omnimodal Large Language Models](https://mlsanity.com/paper/2605.12056/) (2026)
- [AVOC: Enhancing Hour-Level Audio-Video Understanding in Omni-Modal LLMs via Retrieval-Inspired Token Compression](https://mlsanity.com/paper/2606.24286/) (2026)
- [OmniPack: Unified Token Compression for Efficient Omni-modal Large Language Models](https://mlsanity.com/paper/2608.03812/) (2026)
- [V-CAST: Video Curvature-Aware Spatio-Temporal Pruning for Efficient Video Large Language Models](https://mlsanity.com/paper/2603.27650/) (2026)
- [dMoE: dLLMs with Learnable Block Experts](https://mlsanity.com/paper/2605.30876/) (2026)
- [OmniFocus: Query-Guided Modality-Balanced Token Compression for Omni-Modal Large Language Models](https://mlsanity.com/paper/2607.03050/) (2026)
- [Chain of Modality: From Static Fusion to Dynamic Orchestration in Omni-MLLMs](https://mlsanity.com/paper/2604.14520/) (2026)
- [EchoPrune: Interpreting Redundancy as Temporal Echoes for Efficient VideoLLMs](https://mlsanity.com/paper/2605.10050/) (2026)
- [From Senses to Decisions: The Information Flow of Auditory and Visual Perception in Multimodal LLMs](https://mlsanity.com/paper/2606.10147/) (2026)
- [OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models](https://mlsanity.com/paper/2607.23193/) (2026)
- [OmniDelta: Skill-Driven Budget Allocation for Token Compression in OmniLLMs](https://mlsanity.com/paper/2607.25669/) (2026)
- [Allocation Before Ranking: Decoupled Token Compression for OmniLLMs](https://mlsanity.com/paper/2608.01665/) (2026)
- [Why Is Video Still So Expensive? A Survey of Inference-Efficiency Mechanisms in Video and Audiovisual LLMs](https://mlsanity.com/paper/2609.10355/) (2026)
- [OmniKVQuant: KV Cache Quantization for Omni-LLMs](https://mlsanity.com/paper/2609.11582/) (2026)
- [Video-HolmesV2: Can MLLMs Reason with Spatio-Temporal Audio-Visual Evidence in Long Videos?](https://mlsanity.com/paper/2609.17248/) (2026)
- [OmniRoute: Mapping Temporal Semantic Evidence to Audio-Visual Token Budgets for Efficient Omnimodal Large Language Models](https://mlsanity.com/paper/2609.37052/) (2026)
- [LEAP: Learned Block-wise Evidence Retrieval for Long Audio-Video Perception](https://mlsanity.com/paper/2609.39938/) (2026)

## Abstract (arXiv)

Omnimodal large language models (OmniLLMs) have attracted increasing research attention of late towards unified audio-video understanding. However, the high computational cost of processing longer joint audio-video token sequences has become a key bottleneck. Existing token compression methods have not addressed the emerging need to jointly compress 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 model 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 results demonstrate the merits of OmniZip: it achieves a 3.42X inference speedup and a 1.4X memory reduction over other top-performing counterparts, while maintaining the performance of OmniLLMs without training.