Cover Image

From Inheritance to Saturation: Disentangling the Evolution of Visual Redundancy for Architecture-Aware MLLM Inference Acceleration

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shi, Jiaqi, Li, Yuechan, Zhang, Xulong, Qu, Xiaoyang, Wang, Jianzong
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

CARE: Multi-Task Pretraining for Latent Continuous Action Representation in Robot Control
by: Shi, Jiaqi, et al.
Published: (2026)

MIRRORTALK: Forging Personalized Avatars Via Disentangled Style and Hierarchical Motion Control
by: Lu, Renjie, et al.
Published: (2026)

Vista: Scene-Aware Optimization for Streaming Video Question Answering under Post-Hoc Queries
by: Lu, Haocheng, et al.
Published: (2026)

DIVA: Harnessing the Representation Divergence in Unified Multimodal Models for Mutual Reinforcement
by: Lu, Renjie, et al.
Published: (2026)

ESARM: 3D Emotional Speech-to-Animation via Reward Model from Automatically-Ranked Demonstrations
by: Zhang, Xulong, et al.
Published: (2024)

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy
by: Chen, Aiyue, et al.
Published: (2025)

Exploring Visual Prompting: Robustness Inheritance and Beyond
by: Li, Qi, et al.
Published: (2025)

Visual Position Prompt for MLLM based Visual Grounding
by: Tang, Wei, et al.
Published: (2025)

IPCV: Information-Preserving Compression for MLLM Visual Encoders
by: Chen, Yuan, et al.
Published: (2025)

Raformer: Redundancy-Aware Transformer for Video Wire Inpainting
by: Ji, Zhong, et al.
Published: (2024)

Robust MLLM Unlearning via Visual Knowledge Distillation
by: Wang, Yuhang, et al.
Published: (2025)

Slot-MLLM: Object-Centric Visual Tokenization for Multimodal LLM
by: Chi, Donghwan, et al.
Published: (2025)

SMART: Shot-Aware Multimodal Video Moment Retrieval with Audio-Enhanced MLLM
by: Yu, An, et al.
Published: (2025)

Hard to Read, Easy to Jailbreak: How Visual Degradation Bypasses MLLM Safety Alignment
by: Song, Zhixue, et al.
Published: (2026)

LIME: Less Is More for MLLM Evaluation
by: Zhu, King, et al.
Published: (2024)

Temporal Aware Pruning for Efficient Diffusion-based Video Generation
by: Li, Sheng, et al.
Published: (2026)

VLA-InfoEntropy: A Training-Free Vision-Attention Information Entropy Approach for Vision-Language-Action Models Inference Acceleration and Success
by: Liu, Chuhang, et al.
Published: (2026)

Decouple before Align: Visual Disentanglement Enhances Prompt Tuning
by: Zhang, Fei, et al.
Published: (2025)

AdaptToken: Entropy-based Adaptive Token Selection for MLLM Long Video Understanding
by: Qi, Haozhe, et al.
Published: (2026)

Re-purposing SAM into Efficient Visual Projectors for MLLM-Based Referring Image Segmentation
by: Yang, Xiaobo, et al.
Published: (2025)

Enhancing Instruction-Following Capability of Visual-Language Models by Reducing Image Redundancy
by: Yang, Te, et al.
Published: (2024)

PRENet: A Plane-Fit Redundancy Encoding Point Cloud Sequence Network for Real-Time 3D Action Recognition
by: He, Shenglin, et al.
Published: (2024)

From Intuition to Investigation: A Tool-Augmented Reasoning MLLM Framework for Generalizable Face Anti-Spoofing
by: Zhang, Haoyuan, et al.
Published: (2026)

DTL: Disentangled Transfer Learning for Visual Recognition
by: Fu, Minghao, et al.
Published: (2023)

MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolution
by: Zhu, Chunzheng, et al.
Published: (2026)

ESearch-R1: Learning Cost-Aware MLLM Agents for Interactive Embodied Search via Reinforcement Learning
by: Zhou, Weijie, et al.
Published: (2025)

A Survey on MLLM-based Visually Rich Document Understanding: Methods, Challenges, and Emerging Trends
by: Ding, Yihao, et al.
Published: (2025)

MoQAE: Mixed-Precision Quantization for Long-Context LLM Inference via Mixture of Quantization-Aware Experts
by: Tao, Wei, et al.
Published: (2025)

Bridging the Gap Between Sparsity and Redundancy: A Dual-Decoding Framework with Global Context for Map Inference
by: Shen, Yudong, et al.
Published: (2025)

Robust-R1: Degradation-Aware Reasoning for Robust Visual Understanding
by: Tang, Jiaqi, et al.
Published: (2025)

Ref-Adv: Exploring MLLM Visual Reasoning in Referring Expression Tasks
by: Dong, Qihua, et al.
Published: (2026)

S$^2$-MLLM: Boosting Spatial Reasoning Capability of MLLMs for 3D Visual Grounding with Structural Guidance
by: Xu, Beining, et al.
Published: (2025)

VisTa: Visual-contextual and Text-augmented Zero-shot Object-level OOD Detection
by: Zhang, Bin, et al.
Published: (2025)

AIC MLLM: Autonomous Interactive Correction MLLM for Robust Robotic Manipulation
by: Xiong, Chuyan, et al.
Published: (2024)

Divide-and-Conquer Inference for Large-Scale Visual Recognition with Multimodal Large Language Models
by: Ye, Zhipeng, et al.
Published: (2026)

MDF-MLLM: Deep Fusion Through Cross-Modal Feature Alignment for Contextually Aware Fundoscopic Image Classification
by: Jordan, Jason, et al.
Published: (2025)

AG-VAS: Anchor-Guided Zero-Shot Visual Anomaly Segmentation with Large Multimodal Models
by: Qu, Zhen, et al.
Published: (2026)

Disentangling Visual Transformers: Patch-level Interpretability for Image Classification
by: Jeanneret, Guillaume, et al.
Published: (2025)

Abstractive Visual Understanding of Multi-modal Structured Knowledge: A New Perspective for MLLM Evaluation
by: Zhang, Yichi, et al.
Published: (2025)

What Do Visual Tokens Really Encode? Uncovering Sparsity and Redundancy in Multimodal Large Language Models
by: Fan, Yingqi, et al.
Published: (2026)