Cover Image

EvoPrune: Early-Stage Visual Token Pruning for Efficient MLLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Yuhao, Shan, Bin, Ye, Xin, Chen, Cheng
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence I.2.10; I.2.6
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Efficient Image Pre-Training with Siamese Cropped Masked Autoencoders
by: Eymaël, Alexandre, et al.
Published: (2024)

ReLKD: Inter-Class Relation Learning with Knowledge Distillation for Generalized Category Discovery
by: Zhou, Fang, et al.
Published: (2025)

Mitigating Catastrophic Forgetting in the Incremental Learning of Medical Images
by: Yavari, Sara, et al.
Published: (2025)

Data Organization Matters in Multimodal Instruction Tuning: A Controlled Study of Capability Trade-offs
by: Tang, Guowei
Published: (2026)

RDPO: Real Data Preference Optimization for Physics Consistency Video Generation
by: Qian, Wenxu, et al.
Published: (2025)

Adaptive Self-Training for Object Detection
by: Vandeghen, Renaud, et al.
Published: (2022)

Pointing-Based Object Recognition
by: Hajdúch, Lukáš, et al.
Published: (2026)

Engineering an Efficient Object Tracker for Non-Linear Motion
by: Adžemović, Momir, et al.
Published: (2024)

Alternating Gradient Flow Utility: A Unified Metric for Structural Pruning and Dynamic Routing in Deep Networks
by: Qian, Tianhao, et al.
Published: (2026)

EduFlow: Advancing MLLMs' Problem-Solving Proficiency through Multi-Stage, Multi-Perspective Critique
by: Zhu, Chenglin, et al.
Published: (2025)

Contrastive pretraining for semantic segmentation is robust to noisy positive pairs
by: Gerard, Sebastian, et al.
Published: (2022)

Perceptual Flow Network for Visually Grounded Reasoning
by: Li, Yangfu, et al.
Published: (2026)

Selection, Not Fusion: Radar-Modulated State Space Models for Radar-Camera Depth Estimation
by: Hou, Zhangcheng, et al.
Published: (2026)

Once-For-All: A Train-Once and Select-Anytime Framework for Multimodal Instruction Tuning
by: Dong, Mingkang, et al.
Published: (2026)

Exposing Blindspots: Cultural Bias Evaluation in Generative Image Models
by: Seo, Huichan, et al.
Published: (2025)

Smooth regularization for efficient video recognition
by: Goldman, Gil, et al.
Published: (2025)

Neuromorphic Monocular Depth Estimation with Uncertainty Modeling
by: Bergkvist, Viktor, et al.
Published: (2026)

Decoupling Vision and Language: Codebook Anchored Visual Adaptation
by: Wu, Jason, et al.
Published: (2026)

CoT4AD: A Vision-Language-Action Model with Explicit Chain-of-Thought Reasoning for Autonomous Driving
by: Wang, Zhaohui, et al.
Published: (2025)

Conditional Compatibility Learning for Context-Dependent Anomaly Detection
by: Mishra, Shashank, et al.
Published: (2026)

Invariant Representation via Decoupling Style and Spurious Features from Images
by: Li, Ruimeng, et al.
Published: (2023)

Real-Time Flying Object Detection with YOLOv8
by: Reis, Dillon, et al.
Published: (2023)

Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design
by: Alabdulmohsin, Ibrahim, et al.
Published: (2023)

VA-$π$: Variational Policy Alignment for Pixel-Aware Autoregressive Generation
by: Liao, Xinyao, et al.
Published: (2025)

ESCAPE: Energy-based Selective Adaptive Correction for Out-of-distribution 3D Human Pose Estimation
by: Bidulka, Luke, et al.
Published: (2024)

Learning to Seek Evidence: A Verifiable Reasoning Agent with Causal Faithfulness Analysis
by: Huang, Yuhang, et al.
Published: (2025)

Conscious Gaze: Adaptive Attention Mechanisms for Hallucination Mitigation in Vision-Language Models
by: Bu, Weijue, et al.
Published: (2025)

Auto-Annotation Quality Prediction for Semi-Supervised Learning with Ensembles
by: Simon, Dror, et al.
Published: (2019)

FrescoDiffusion: 4K Image-to-Video with Prior-Regularized Tiled Diffusion
by: Caselles-Dupré, Hugo, et al.
Published: (2026)

Training a Student Expert via Semi-Supervised Foundation Model Distillation
by: Taghavi, Pardis, et al.
Published: (2026)

eStonefish-Scenes: A Sim-to-Real Validated and Robot-Centric Event-based Optical Flow Dataset for Underwater Vehicles
by: Mansour, Jad, et al.
Published: (2025)

eCARLA-scenes: A synthetically generated dataset for event-based optical flow prediction
by: Mansour, Jad, et al.
Published: (2024)

An Active Inference Model of Covert and Overt Visual Attention
by: Mišić, Tin, et al.
Published: (2025)

FlightScope: An Experimental Comparative Review of Aircraft Detection Algorithms in Satellite Imagery
by: Ghazouali, Safouane El, et al.
Published: (2024)

VITA: Zero-Shot Value Functions via Test-Time Adaptation of Vision-Language Models
by: Ziakas, Christos, et al.
Published: (2025)

CrossVLA: Cross-Paradigm Post-Training and Inference Optimization for Vision-Language-Action Models
by: Liu, Zhi
Published: (2026)

Aligning by Misaligning: Boundary-aware Curriculum Learning for Multimodal Alignment
by: Ye, Hua, et al.
Published: (2025)

Physics-R1: An Audited Olympiad Corpus and Recipe for Visual Physics Reasoning
by: Yang, Shan
Published: (2026)

Beyond Segmentation: Structurally Informed Facade Parsing from Imperfect Images
by: Janicki, Maciej, et al.
Published: (2026)

Analyzing Quality, Bias, and Performance in Text-to-Image Generative Models
by: Masrourisaadat, Nila, et al.
Published: (2024)