Imagen de Portada

EchoingPixels: Cross-Modal Adaptive Token Reduction for Efficient Audio-Visual LLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Gong, Chao, Wang, Depeng, Wei, Zhipeng, Guo, Ya, Zhu, Huijia, Chen, Jingjing
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Rethinking Visual Token Reduction in LVLMs Under Cross-Modal Misalignment
por: Xu, Rui, et al.
Publicado: (2025)

PixelPrune: Pixel-Level Adaptive Visual Token Reduction via Predictive Coding
por: Wang, Nan, et al.
Publicado: (2026)

VCE: Safe Autoregressive Image Generation via Visual Contrast Exploitation
por: Han, Feng, et al.
Publicado: (2025)

LINK: Adaptive Modality Interaction for Audio-Visual Video Parsing
por: Wang, Langyu, et al.
Publicado: (2024)

Reliable and Efficient Concept Erasure of Text-to-Image Diffusion Models
por: Gong, Chao, et al.
Publicado: (2024)

Dense Audio-Visual Event Localization under Cross-Modal Consistency and Multi-Temporal Granularity Collaboration
por: Zhou, Ziheng, et al.
Publicado: (2024)

Mettle: Meta-Token Learning for Memory-Efficient Audio-Visual Adaptation
por: Zhou, Jinxing, et al.
Publicado: (2025)

ImageAttributionBench: How Far Are We from Generalizable Attribution?
por: Mou, Tingshu, et al.
Publicado: (2026)

EchoingECG: An Electrocardiogram Cross-Modal Model for Echocardiogram Tasks
por: Gao, Yuan, et al.
Publicado: (2025)

From Pixels to Tokens: Byte-Pair Encoding on Quantized Visual Modalities
por: Zhang, Wanpeng, et al.
Publicado: (2024)

SimToken: A Simple Baseline for Referring Audio-Visual Segmentation
por: Jin, Dian, et al.
Publicado: (2025)

Teacher-Guided Pseudo Supervision and Cross-Modal Alignment for Audio-Visual Video Parsing
por: Chen, Yaru, et al.
Publicado: (2025)

VisionSelector: End-to-End Learnable Visual Token Compression for Efficient Multimodal LLMs
por: Zhu, Jiaying, et al.
Publicado: (2025)

From Waveforms to Pixels: A Survey on Audio-Visual Segmentation
por: Li, Jia, et al.
Publicado: (2025)

Learning Visual Affordance from Audio
por: Lu, Lidong, et al.
Publicado: (2025)

PRIMED: Adaptive Modality Suppression for Referring Audio-Visual Segmentation via Biased Competition
por: He, Yuchen, et al.
Publicado: (2026)

AVHBench: A Cross-Modal Hallucination Benchmark for Audio-Visual Large Language Models
por: Sung-Bin, Kim, et al.
Publicado: (2024)

Adaptive Identification of Blurred Regions for Accurate Image Deblurring
por: Gao, Hu, et al.
Publicado: (2025)

AlignVSR: Audio-Visual Cross-Modal Alignment for Visual Speech Recognition
por: Liu, Zehua, et al.
Publicado: (2024)

A Systematic Study of Cross-Modal Typographic Attacks on Audio-Visual Reasoning
por: Chen, Tianle, et al.
Publicado: (2026)

Unsupervised Audio-Visual Segmentation with Modality Alignment
por: Bhosale, Swapnil, et al.
Publicado: (2024)

EchoInk-R1: Exploring Audio-Visual Reasoning in Multimodal LLMs via Reinforcement Learning
por: Xing, Zhenghao, et al.
Publicado: (2025)

Spatial and Frequency Domain Adaptive Fusion Network for Image Deblurring
por: Gao, Hu, et al.
Publicado: (2025)

EEPNet-V2: Patch-to-Pixel Solution for Efficient Cross-Modal Registration between LiDAR Point Cloud and Camera Image
por: Yue, Yuanchao, et al.
Publicado: (2025)

Residual Cross-Modal Fusion Networks for Audio-Visual Navigation
por: Wang, Yi, et al.
Publicado: (2026)

Cross-Modal Binary Attention: An Energy-Efficient Fusion Framework for Audio-Visual Learning
por: Saleh, Mohamed, et al.
Publicado: (2026)

AQuaUI: Visual Token Reduction for GUI Agents with Adaptive Quadtrees
por: Li, Yuankai, et al.
Publicado: (2026)

DuMo: Dual Encoder Modulation Network for Precise Concept Erasure
por: Han, Feng, et al.
Publicado: (2025)

EVATok: Adaptive Length Video Tokenization for Efficient Visual Autoregressive Generation
por: Xiong, Tianwei, et al.
Publicado: (2026)

WinTok: A Win-Win Hybrid Tokenizer via Decomposing Visual Understanding and Generation with Transferable Tokens
por: Guo, Yiwei, et al.
Publicado: (2026)

UniFlow: A Unified Pixel Flow Tokenizer for Visual Understanding and Generation
por: Yue, Zhengrong, et al.
Publicado: (2025)

Towards Flexible, Scalable, and Adaptive Multi-Modal Conditioned Face Synthesis
por: Ren, Jingjing, et al.
Publicado: (2023)

EchoPrune: Interpreting Redundancy as Temporal Echoes for Efficient VideoLLMs
por: Li, Jiameng, et al.
Publicado: (2026)

Improving Visual Token Reduction via Rectifying Distortions for Efficient Multimodal LLM Inference
por: Cho, Hyeonwoo, et al.
Publicado: (2026)

Enhancing Audio-Visual Spiking Neural Networks through Semantic-Alignment and Cross-Modal Residual Learning
por: He, Xiang, et al.
Publicado: (2025)

HAVT-IVD: Heterogeneity-Aware Cross-Modal Network for Audio-Visual Surveillance: Idling Vehicles Detection With Multichannel Audio and Multiscale Visual Cues
por: Li, Xiwen, et al.
Publicado: (2025)

Towards Open-Vocabulary Audio-Visual Event Localization
por: Zhou, Jinxing, et al.
Publicado: (2024)

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

Memory Efficient Matting with Adaptive Token Routing
por: Lin, Yiheng, et al.
Publicado: (2024)

FocusLLaVA: A Coarse-to-Fine Approach for Efficient and Effective Visual Token Compression
por: Zhu, Yuke, et al.
Publicado: (2024)