Cover Image

Flash-VL 2B: Optimizing Vision-Language Model Performance for Ultra-Low Latency and High Throughput

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Bo, Li, Shuo, Tian, Runhe, Yang, Yang, Tang, Jixin, Zhou, Jinhao, Ma, Lin
Format:	Preprint
Published:	2025
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

VL-Reader: Vision and Language Reconstructor is an Effective Scene Text Recognizer
by: Zhong, Humen, et al.
Published: (2024)

FlashClear: Ultra-Fast Image Content Removal via Efficient Step Distillation and Feature Caching
by: Tang, Yixin, et al.
Published: (2026)

PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model
by: Cui, Cheng, et al.
Published: (2025)

Multimodal Interpretation of Remote Sensing Images: Dynamic Resolution Input Strategy and Multi-scale Vision-Language Alignment Mechanism
by: Zhang, Siyu, et al.
Published: (2025)

Firebolt-VL: Efficient Vision-Language Understanding with Cross-Modality Modulation
by: Trinh, Quoc-Huy, et al.
Published: (2026)

Florence-VL: Enhancing Vision-Language Models with Generative Vision Encoder and Depth-Breadth Fusion
by: Chen, Jiuhai, et al.
Published: (2024)

BREATH-VL: Vision-Language-Guided 6-DoF Bronchoscopy Localization via Semantic-Geometric Fusion
by: Tian, Qingyao, et al.
Published: (2026)

Youtu-VL: Unleashing Visual Potential via Unified Vision-Language Supervision
by: Wei, Zhixiang, et al.
Published: (2026)

DP^2-VL: Private Photo Dataset Protection by Data Poisoning for Vision-Language Models
by: Miao, Hongyi, et al.
Published: (2026)

VL-RewardBench: A Challenging Benchmark for Vision-Language Generative Reward Models
by: Li, Lei, et al.
Published: (2024)

Qwen3-VL-Seg: Unlocking Open-World Referring Segmentation with Vision-Language Grounding
by: Yao, Yuan, et al.
Published: (2026)

VisualThink-VLA: Visual Intermediate Reasoning for Effective and Low-Latency Vision-Language-Action Policies
by: Gao, Mingjian, et al.
Published: (2026)

SDAR-VL: Stable and Efficient Block-wise Diffusion for Vision-Language Understanding
by: Cheng, Shuang, et al.
Published: (2025)

LEO-VL: Efficient Scene Representation for Scalable 3D Vision-Language Learning
by: Huang, Jiangyong, et al.
Published: (2025)

Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images
by: Gao, Kuofeng, et al.
Published: (2024)

Qianfan-VL: Domain-Enhanced Universal Vision-Language Models
by: Dong, Daxiang, et al.
Published: (2025)

FlashCap: Millisecond-Accurate Human Motion Capture via Flashing LEDs and Event-Based Vision
by: Wu, Zekai, et al.
Published: (2026)

Thermo-VL: Extending Vision-Language Models to Thermal Infrared Perception
by: Thushara, Rusiru, et al.
Published: (2026)

3VL: Using Trees to Improve Vision-Language Models' Interpretability
by: Yellinek, Nir, et al.
Published: (2023)

VL4Gaze: Unleashing Vision-Language Models for Gaze Following
by: Wang, Shijing, et al.
Published: (2025)

ADEM-VL: Adaptive and Embedded Fusion for Efficient Vision-Language Tuning
by: Hao, Zhiwei, et al.
Published: (2024)

Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
by: Wang, Peng, et al.
Published: (2024)

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation
by: Lu, Jinghui, et al.
Published: (2026)

ZipVL: Efficient Large Vision-Language Models with Dynamic Token Sparsification
by: He, Yefei, et al.
Published: (2024)

FA: Forced Prompt Learning of Vision-Language Models for Out-of-Distribution Detection
by: Lu, Xinhua, et al.
Published: (2025)

EarthVL: A Progressive Earth Vision-Language Understanding and Generation Framework
by: Wang, Junjue, et al.
Published: (2026)

A-VL: Adaptive Attention for Large Vision-Language Models
by: Zhang, Junyang, et al.
Published: (2024)

GMAI-VL & GMAI-VL-5.5M: A Large Vision-Language Model and A Comprehensive Multimodal Dataset Towards General Medical AI
by: Li, Tianbin, et al.
Published: (2024)

CoME-VL: Scaling Complementary Multi-Encoder Vision-Language Learning
by: Deria, Ankan, et al.
Published: (2026)

DiffusionVL: Translating Any Autoregressive Models into Diffusion Vision Language Models
by: Zeng, Lunbin, et al.
Published: (2025)

ShotVL: Human-Centric Highlight Frame Retrieval via Language Queries
by: Xue, Wangyu, et al.
Published: (2024)

Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders
by: Zhang, Boqiang, et al.
Published: (2026)

STEP3-VL-10B Technical Report
by: Huang, Ailin, et al.
Published: (2026)

Hierarchical Vision-Language Learning for Medical Out-of-Distribution Detection
by: Lai, Runhe, et al.
Published: (2025)

InfiniteVL: Synergizing Linear and Sparse Attention for Highly-Efficient, Unlimited-Input Vision-Language Models
by: Tao, Hongyuan, et al.
Published: (2025)

VL-Uncertainty: Detecting Hallucination in Large Vision-Language Model via Uncertainty Estimation
by: Zhang, Ruiyang, et al.
Published: (2024)

GraSP-VL: Length as a Semantic Granularity Interface for Vision-Language Representations
by: Li, Zesheng, et al.
Published: (2026)

VL4AD: Vision-Language Models Improve Pixel-wise Anomaly Detection
by: Zhong, Liangyu, et al.
Published: (2024)

TinyChemVL: Advancing Chemical Vision-Language Models via Efficient Visual Token Reduction and Complex Reaction Tasks
by: Zhao, Xuanle, et al.
Published: (2025)

OmniVL-Guard Pro: A Tool-Augmented Agent for Omnibus Vision-Language Forensics
by: Shen, Jinjie, et al.
Published: (2026)