Image de couverture de livre

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Liu, Yi, Xu, Xiao, Xu, Zeyu, Zhang, Meng, Li, Yibo, Chen, Haoyu, Zhang, Junkang, Wang, Qiang, Sun, Jifa, Lin, Siling, Cheng, Shengxun, Zhang, Lingshu, Wang, Kang
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

E-VRAG: Enhancing Long Video Understanding with Resource-Efficient Retrieval Augmented Generation
par: Xu, Zeyu, et autres
Publié: (2025)

Vision-EKIPL: External Knowledge-Infused Policy Learning for Visual Reasoning
par: Wang, Chaoyang, et autres
Publié: (2025)

Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders
par: Zhang, Boqiang, et autres
Publié: (2026)

VL-Cogito: Progressive Curriculum Reinforcement Learning for Advanced Multimodal Reasoning
par: Yuan, Ruifeng, et autres
Publié: (2025)

OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning
par: Liu, Yanqing, et autres
Publié: (2025)

JW-VL: A Vision-Language Model for Solar Physics
par: Shao, Mingfu, et autres
Publié: (2026)

OpenVision 3: A Family of Unified Visual Encoder for Both Understanding and Generation
par: Zhang, Letian, et autres
Publié: (2026)

Recall: Empowering Multimodal Embedding for Edge Devices
par: Cai, Dongqi, et autres
Publié: (2024)

Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception
par: Wang, Junyang, et autres
Publié: (2024)

DeepSeek-VL: Towards Real-World Vision-Language Understanding
par: Lu, Haoyu, et autres
Publié: (2024)

VL-Explore: Zero-shot Vision-Language Exploration and Target Discovery by Mobile Robots
par: Zhang, Yuxuan, et autres
Publié: (2025)

A Cross-Hierarchical Difference Feature Fusion Network Based on Multiscale Encoder-Decoder for Hyperspectral Change Detection
par: Sheng, Mingshuai, et autres
Publié: (2025)

CoME-VL: Scaling Complementary Multi-Encoder Vision-Language Learning
par: Deria, Ankan, et autres
Publié: (2026)

EdgeMoE: Empowering Sparse Large Language Models on Mobile Devices
par: Yi, Rongjie, et autres
Publié: (2023)

Florence-VL: Enhancing Vision-Language Models with Generative Vision Encoder and Depth-Breadth Fusion
par: Chen, Jiuhai, et autres
Publié: (2024)

AgriGPT-VL: Agricultural Vision-Language Understanding Suite
par: Yang, Bo, et autres
Publié: (2025)

HyperVL: An Efficient and Dynamic Multimodal Large Language Model for Edge Devices
par: HyperAI Team, et autres
Publié: (2025)

Towards Lightweight Graph Neural Network Search with Curriculum Graph Sparsification
par: Xie, Beini, et autres
Publié: (2024)

VL-GenRM: Enhancing Vision-Language Verification via Vision Experts and Iterative Training
par: Zhang, Jipeng, et autres
Publié: (2025)

ReDas: A Lightweight Architecture for Supporting Fine-Grained Reshaping and Multiple Dataflows on Systolic Array
par: Han, Meng, et autres
Publié: (2023)

MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices
par: Chu, Xiangxiang, et autres
Publié: (2023)

Image Recognition with Online Lightweight Vision Transformer: A Survey
par: Zhang, Zherui, et autres
Publié: (2025)

MobileMamba: Lightweight Multi-Receptive Visual Mamba Network
par: He, Haoyang, et autres
Publié: (2024)

MobileIE: An Extremely Lightweight and Effective ConvNet for Real-Time Image Enhancement on Mobile Devices
par: Yan, Hailong, et autres
Publié: (2025)

TinyChemVL: Advancing Chemical Vision-Language Models via Efficient Visual Token Reduction and Complex Reaction Tasks
par: Zhao, Xuanle, et autres
Publié: (2025)

Transformers in Pseudo-Random Number Generation: A Dual Perspective on Theory and Practice
par: Li, Ran, et autres
Publié: (2025)

VL-DPO: Vision-Language-Guided Finetuning for Preference-Aligned Autonomous Driving
par: Xu, Zhefan, et autres
Publié: (2026)

A Novel ViDAR Device With Visual Inertial Encoder Odometry and Reinforcement Learning-Based Active SLAM Method
par: Xin, Zhanhua, et autres
Publié: (2025)

Youtu-VL: Unleashing Visual Potential via Unified Vision-Language Supervision
par: Wei, Zhixiang, et autres
Publié: (2026)

VideoCap-R1: Enhancing MLLMs for Video Captioning via Structured Thinking
par: Meng, Desen, et autres
Publié: (2025)

ImageRef-VL: Enabling Contextual Image Referencing in Vision-Language Models
par: Yi, Jingwei, et autres
Publié: (2025)

Explicit Semantic-Base-Empowered Communications for 6G Mobile Networks
par: Wang, Fengyu, et autres
Publié: (2024)

Multiple Information Prompt Learning for Cloth-Changing Person Re-Identification
par: Wei, Shengxun, et autres
Publié: (2024)

Qianfan-VL: Domain-Enhanced Universal Vision-Language Models
par: Dong, Daxiang, et autres
Publié: (2025)

InternVL-X: Advancing and Accelerating InternVL Series with Efficient Visual Token Compression
par: Lu, Dongchen, et autres
Publié: (2025)

Code2Worlds: Empowering Coding LLMs for 4D World Generation
par: Zhang, Yi, et autres
Publié: (2026)

Re-Parameterization of Lightweight Transformer for On-Device Speech Emotion Recognition
par: Zhang, Zixing, et autres
Publié: (2024)

Uniform large deviations and metastability of random dynamical systems
par: Jiang, Jifa, et autres
Publié: (2024)

A-VL: Adaptive Attention for Large Vision-Language Models
par: Zhang, Junyang, et autres
Publié: (2024)

InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks
par: Chen, Zhe, et autres
Publié: (2023)