Cover Image

2D or 3D: Who Governs Salience in VLA Models? -- Tri-Stage Token Pruning Framework with Modality Salience Awareness

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zheng, Zihao, Tian, Sicheng, Mao, Zhihao, Zhang, Lingyue, Li, Chenyue, Zhang, Ziyun, Gao, Hong, Huang, Yuchen, Xu, Yutong, Luo, Guojie, Chen, Xiang
Format:	Preprint
Published:	2026
Subjects:	Multimedia Computer Vision and Pattern Recognition Robotics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SpikeMba: Multi-Modal Spiking Saliency Mamba for Temporal Video Grounding
by: Li, Wenrui, et al.
Published: (2024)

Images Inpainting Quality Evaluation Using Structural Features and Visual Saliency
by: Shuang Ma, et al.
Published: (2024)

ISMAF: Intrinsic-Social Modality Alignment and Fusion for Multimodal Rumor Detection
by: Yu, Zihao, et al.
Published: (2025)

Using Saliency and Cropping to Improve Video Memorability
by: Mudgal, Vaibhav, et al.
Published: (2023)

SOSControl: Enhancing Human Motion Generation through Saliency-Aware Symbolic Orientation and Timing Control
by: Au, Ho Yin, et al.
Published: (2025)

Adaptive 3D Gaussian Splatting Video Streaming: Visual Saliency-Aware Tiling and Meta-Learning-Based Bitrate Adaptation
by: Gong, Han, et al.
Published: (2025)

Saliency-Aware Diffusion Reconstruction for Effective Invisible Watermark Removal
by: Alam, Inzamamul, et al.
Published: (2025)

Transformer-based Video Saliency Prediction with High Temporal Dimension Decoding
by: Moradi, Morteza, et al.
Published: (2024)

Token-Level Contrastive Learning with Modality-Aware Prompting for Multimodal Intent Recognition
by: Zhou, Qianrui, et al.
Published: (2023)

Viewport Prediction for Volumetric Video Streaming by Exploring Video Saliency and Trajectory Information
by: Li, Jie, et al.
Published: (2023)

TMDC: A Two-Stage Modality Denoising and Complementation Framework for Multimodal Sentiment Analysis with Missing and Noisy Modalities
by: Zhuang, Yan, et al.
Published: (2025)

Robust Mesh Saliency Ground Truth Acquisition in VR via View Cone Sampling and Manifold Diffusion
by: Zheng, Guoquan, et al.
Published: (2026)

Modality-Aware Contrastive and Uncertainty-Regularized Emotion Recognition
by: Zhuang, Yan, et al.
Published: (2026)

Dynamic Interaction-Aware and Causality-Disentangled Framework for Multimodal Sentiment Analysis
by: Dong, Guangyuan, et al.
Published: (2026)

Sphere-GAN: a GAN-based Approach for Saliency Estimation in 360° Videos
by: Wahba, Mahmoud Z. A., et al.
Published: (2025)

Structure-Aware Residual-Center Representation for Self-Supervised Open-Set 3D Cross-Modal Retrieval
by: Xu, Yang, et al.
Published: (2024)

Cross-Modality and Within-Modality Regularization for Audio-Visual DeepFake Detection
by: Zou, Heqing, et al.
Published: (2024)

High-Fidelity 3D Gaussian Human Reconstruction via Region-Aware Initialization and Geometric Priors
by: Liu, Yang, et al.
Published: (2026)

A Survey on Music Generation from Single-Modal, Cross-Modal, and Multi-Modal Perspectives
by: Li, Shuyu, et al.
Published: (2025)

NTIRE 2026 Challenge on Video Saliency Prediction: Methods and Results
by: Moskalenko, Andrey, et al.
Published: (2026)

3MDiT: Unified Tri-Modal Diffusion Transformer for Text-Driven Synchronized Audio-Video Generation
by: Li, Yaoru, et al.
Published: (2025)

AIM 2024 Challenge on Video Saliency Prediction: Methods and Results
by: Moskalenko, Andrey, et al.
Published: (2024)

Augmenting Intra-Modal Understanding in MLLMs for Robust Multimodal Keyphrase Generation
by: Cao, Jiajun, et al.
Published: (2025)

TF-Mamba: Text-enhanced Fusion Mamba with Missing Modalities for Robust Multimodal Sentiment Analysis
by: Li, Xiang, et al.
Published: (2025)

Brain-Grasp: Graph-based Saliency Priors for Improved fMRI-based Visual Brain Decoding
by: Moradi, Mohammad, et al.
Published: (2026)

Diffusion Model-Based Size Variable Virtual Try-On Technology and Evaluation Method
by: Zhang, Shufang, et al.
Published: (2025)

Boosting Omni-Modal Language Models: Staged Post-Training with Visually Debiased Evaluation
by: Liu, Che, et al.
Published: (2026)

Mixture of Disentangled Experts with Missing Modalities for Robust Multimodal Sentiment Analysis
by: Li, Xiang, et al.
Published: (2026)

Saliency-Based diversity and fairness Metric and FaceKeepOriginalAugment: A Novel Approach for Enhancing Fairness and Diversity
by: Kumar, Teerath, et al.
Published: (2024)

UltraSketchLLM: Saliency-Driven Sketching for Ultra-Low Bit LLM Compression
by: Zou, Sunan, et al.
Published: (2025)

AC^2-VLA: Action-Context-Aware Adaptive Computation in Vision-Language-Action Models for Efficient Robotic Manipulation
by: Yu, Wenda, et al.
Published: (2026)

Towards Unified Representation of Multi-Modal Pre-training for 3D Understanding via Differentiable Rendering
by: Fei, Ben, et al.
Published: (2024)

Towards Universal Modal Tracking with Online Dense Temporal Token Learning
by: Zheng, Yaozong, et al.
Published: (2025)

DailyLLM: Context-Aware Activity Log Generation Using Multi-Modal Sensors and LLMs
by: Tian, Ye, et al.
Published: (2025)

Modality-Aware Identity Construction and Counterfactual Structure Learning for ID-Free Multimodal Recommendation
by: Ma, Hongjian, et al.
Published: (2026)

Adaptive 3D Mesh Steganography Based on Feature-Preserving Distortion
by: Zhang, Yushu, et al.
Published: (2022)

ASAP: Advancing Semantic Alignment Promotes Multi-Modal Manipulation Detecting and Grounding
by: Zhang, Zhenxing, et al.
Published: (2024)

Multimodal Emotion Recognition with Large Language Models
by: Zhang, Hongrui, et al.
Published: (2026)

Enhanced Multimodal Hate Video Detection via Channel-wise and Modality-wise Fusion
by: Zhang, Yinghui, et al.
Published: (2025)

Recognizing Everything from All Modalities at Once: Grounded Multimodal Universal Information Extraction
by: Zhang, Meishan, et al.
Published: (2024)