Cover Image

Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jung, Chaeyoung, Rho, Kyeongha, Chung, Joon Son
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

MoLT: Mixture of Layer-Wise Tokens for Efficient Audio-Visual Learning
by: Rho, Kyeongha, et al.
Published: (2025)

AVCD: Mitigating Hallucinations in Audio-Visual Large Language Models through Contrastive Decoding
by: Jung, Chaeyoung, et al.
Published: (2025)

Fork-Merge Decoding: Enhancing Multimodal Understanding in Audio-Visual Large Language Models
by: Jung, Chaeyoung, et al.
Published: (2025)

From Faces to Voices: Learning Hierarchical Representations for High-quality Video-to-Speech
by: Kim, Ji-Hoon, et al.
Published: (2025)

Index-Preserving Lightweight Token Pruning for Efficient Document Understanding in Vision-Language Models
by: Son, Jaemin, et al.
Published: (2025)

On the Nature of Attention Sink that Shapes Decoding Strategy in Omni-LLMs
by: Yoo, Suho, et al.
Published: (2026)

Rotation-Aligned Key Channel Pruning for Efficient Vision-Language Model Inference
by: Kang, Beomseok, et al.
Published: (2026)

OmniNFT: Modality-wise Omni Diffusion Reinforcement for Joint Audio-Video Generation
by: Zhang, Guohui, et al.
Published: (2026)

AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning
by: Zhong, Yiwu, et al.
Published: (2024)

LAVCap: LLM-based Audio-Visual Captioning using Optimal Transport
by: Rho, Kyeongha, et al.
Published: (2025)

IWP: Token Pruning as Implicit Weight Pruning in Large Vision Language Models
by: Lee, Dong-Jae, et al.
Published: (2026)

EgoPrune: Efficient Token Pruning for Egomotion Video Reasoning in Embodied Agent
by: Li, Jiaao, et al.
Published: (2025)

TransPrune: Token Transition Pruning for Efficient Large Vision-Language Model
by: Li, Ao, et al.
Published: (2025)

ContextDrag: Precise Drag-Based Image Editing via Context-Preserving Token Injection and Position-Aligned Attention
by: He, Huiguo, et al.
Published: (2025)

TokenTrim: Inference-Time Token Pruning for Autoregressive Long Video Generation
by: Shaulov, Ariel, et al.
Published: (2026)

What Kind of Visual Tokens Do We Need? Training-free Visual Token Pruning for Multi-modal Large Language Models from the Perspective of Graph
by: Jiang, Yutao, et al.
Published: (2025)

OccamToken: Efficient VLM Inference with Training-Free and Budget-Adaptive Token Pruning
by: Li, Geng, et al.
Published: (2026)

Sharp Eyes and Memory for VideoLLMs: Information-Aware Visual Token Pruning for Efficient and Reliable VideoLLM Reasoning
by: Qin, Jialong, et al.
Published: (2025)

SpecVLM: Enhancing Speculative Decoding of Video LLMs via Verifier-Guided Token Pruning
by: Ji, Yicheng, et al.
Published: (2025)

Preserve or Modify? Context-Aware Evaluation for Balancing Preservation and Modification in Text-Guided Image Editing
by: Kim, Yoonjeon, et al.
Published: (2024)

ST-Prune: Training-Free Spatio-Temporal Token Pruning for Vision-Language Models in Autonomous Driving
by: Sha, Lin, et al.
Published: (2026)

Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning
by: Chien, Tzu-Chun, et al.
Published: (2025)

IDPruner: Harmonizing Importance and Diversity in Visual Token Pruning for MLLMs
by: Tan, Yifan, et al.
Published: (2026)

Object-Centric Vision Token Pruning for Vision Language Models
by: Li, Guangyuan, et al.
Published: (2025)

Video Diffusion Models Excel at Tracking Similar-Looking Objects Without Supervision
by: Zhang, Chenshuang, et al.
Published: (2025)

Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs
by: Hyun, Jeongseok, et al.
Published: (2025)

SNP: Structured Neuron-level Pruning to Preserve Attention Scores
by: Shim, Kyunghwan, et al.
Published: (2024)

KeepOriginalAugment: Single Image-based Better Information-Preserving Data Augmentation Approach
by: Kumar, Teerath, et al.
Published: (2024)

Audio-Omni: Extending Multi-modal Understanding to Versatile Audio Generation and Editing
by: Tian, Zeyue, et al.
Published: (2026)

Spatio-Temporal Token Pruning for Efficient High-Resolution GUI Agents
by: Xu, Zhou, et al.
Published: (2026)

Token Pruning using a Lightweight Background Aware Vision Transformer
by: Sah, Sudhakar, et al.
Published: (2024)

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs
by: Zhang, Qizhe, et al.
Published: (2025)

Probing Cross-modal Information Hubs in Audio-Visual LLMs
by: Jung, Jihoo, et al.
Published: (2026)

QAPruner: Quantization-Aware Vision Token Pruning for Multimodal Large Language Models
by: Wang, Xinhao, et al.
Published: (2026)

Energy-Driven Adaptive Visual Token Pruning for Efficient Vision-Language Models
by: He, Jialuo, et al.
Published: (2026)

RASA: Replace Anyone, Say Anything -- A Training-Free Framework for Audio-Driven and Universal Portrait Video Editing
by: Pan, Tianrui, et al.
Published: (2025)

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

Where Do Tokens Go? Understanding Pruning Behaviors in STEP at High Resolutions
by: Szczepanski, Michal, et al.
Published: (2025)

Balanced Token Pruning: Accelerating Vision Language Models Beyond Local Optimization
by: Li, Kaiyuan, et al.
Published: (2025)

ZSPAPrune: Zero-Shot Prompt-Aware Token Pruning for Vision-Language Models
by: Zhang, Pu, et al.
Published: (2025)