Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tao, Keda, Shao, Kele, Yu, Bohan, Wang, Weiqiang, liu, Jian, Wang, Huan
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Active Perception Agent for Omnimodal Audio-Video Understanding
by: Tao, Keda, et al.
Published: (2025)

StreamingTOM: Streaming Token Compression for Efficient Video Understanding
by: Chen, Xueyi, et al.
Published: (2025)

HoliTom: Holistic Token Merging for Fast Video Large Language Models
by: Shao, Kele, et al.
Published: (2025)

LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMs
by: Tao, Keda, et al.
Published: (2026)

DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models
by: Tao, Keda, et al.
Published: (2024)

A Survey of Token Compression for Efficient Multimodal Large Language Models
by: Shao, Kele, et al.
Published: (2025)

DASH: Dynamic Audio-Driven Semantic Chunking for Efficient Omnimodal Token Compression
by: Li, Bingzhou, et al.
Published: (2026)

ZipVL: Efficient Large Vision-Language Models with Dynamic Token Sparsification
by: He, Yefei, et al.
Published: (2024)

StreamingAssistant: Efficient Visual Token Pruning for Accelerating Online Video Understanding
by: Jin, Xinqi, et al.
Published: (2025)

Omni-o3: Deep Nested Omnimodal Deduction for Deliberative Audio-Visual Reasoning
by: Zhang, Zhicheng, et al.
Published: (2026)

OmniSelect: Dynamic Modality-Aware Token Compression for Efficient Omni-modal Large Language Models
by: Yang, Morunliu, et al.
Published: (2026)

Revisiting MLLM Token Technology through the Lens of Classical Visual Coding
by: Liu, Jinming, et al.
Published: (2025)

Investigating and Enhancing Vision-Audio Capability in Omnimodal Large Language Models
by: Hu, Rui, et al.
Published: (2025)

Omni-Persona: Systematic Benchmarking and Improving Omnimodal Personalization
by: Oh, Yeongtak, et al.
Published: (2026)

Plug-and-Play 1.x-Bit KV Cache Quantization for Video Large Language Models
by: Tao, Keda, et al.
Published: (2025)

EarlyTom: Early Token Compression Completes Fast Video Understanding
by: Wang, Hesong, et al.
Published: (2026)

TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs
by: Zhang, Kejia, et al.
Published: (2025)

Is Oracle Pruning the True Oracle?
by: Feng, Sicheng, et al.
Published: (2024)

ForensicZip: More Tokens are Better but Not Necessary in Forensic Vision-Language Models
by: Lai, Yingxin, et al.
Published: (2026)

LLaVA-Zip: Adaptive Visual Token Compression with Intrinsic Image Information
by: Wang, Ke, et al.
Published: (2024)

Towards Omnimodal Expressions and Reasoning in Referring Audio-Visual Segmentation
by: Ying, Kaining, et al.
Published: (2025)

Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration
by: Zhong, Hao, et al.
Published: (2025)

OmniZip: Learning a Unified and Lightweight Lossless Compressor for Multi-Modal Data
by: Zhao, Yan, et al.
Published: (2026)

Poison as Cure: Visual Noise for Mitigating Object Hallucinations in LVMs
by: Zhang, Kejia, et al.
Published: (2025)

Language-Guided Token Compression with Reinforcement Learning in Large Vision-Language Models
by: Cao, Sihan, et al.
Published: (2026)

A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models
by: Zeng, Quan-Sheng, et al.
Published: (2025)

Uni-MoE-2.0-Omni: Scaling Language-Centric Omnimodal Large Model with Advanced MoE, Training and Data
by: Li, Yunxin, et al.
Published: (2025)

Overcoming False Illusions in Real-World Face Restoration with Multi-Modal Guided Diffusion Model
by: Tao, Keda, et al.
Published: (2024)

OpenOmni: Advancing Open-Source Omnimodal Large Language Models with Progressive Multimodal Alignment and Real-Time Self-Aware Emotional Speech Synthesis
by: Luo, Run, et al.
Published: (2025)

OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation
by: Wang, Junke, et al.
Published: (2024)

TokenCarve: Information-Preserving Visual Token Compression in Multimodal Large Language Models
by: Tan, Xudong, et al.
Published: (2025)

Scaling Language-Centric Omnimodal Representation Learning
by: Xiao, Chenghao, et al.
Published: (2025)

HybridToken-VLM: Hybrid Token Compression for Vision-Language Models
by: Zhang, Jusheng, et al.
Published: (2025)

Dynamic-VLM: Simple Dynamic Visual Token Compression for VideoLLM
by: Wang, Han, et al.
Published: (2024)

Vision-centric Token Compression in Large Language Model
by: Xing, Ling, et al.
Published: (2025)

Dynamic Token Compression for Efficient Video Understanding through Reinforcement Learning
by: Wang, Shida, et al.
Published: (2026)

OmniVLM: A Token-Compressed, Sub-Billion-Parameter Vision-Language Model for Efficient On-Device Inference
by: Chen, Wei, et al.
Published: (2024)

Boosting Audio-visual Zero-shot Learning with Large Language Models
by: Chen, Haoxing, et al.
Published: (2023)

PhotoArtAgent: Intelligent Photo Retouching with Language Model-Based Artist Agents
by: Chen, Haoyu, et al.
Published: (2025)

ROVER: Benchmarking Reciprocal Cross-Modal Reasoning for Omnimodal Generation
by: Liang, Yongyuan, et al.
Published: (2025)