MDL
Qwen-VL
Qwen
Capability
—
percentile index
Downloads
127.9K
on HF
Likes
281
Avg score
—
Weights
Open
Released
Aug 18, 2023
About
Qwen-VL is a open-weights model in the Qwen family from Qwen.
text-generation
Benchmark scores · 0
No benchmark scores yet.
The research behind this model
all papers mentioning it →Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and BeyondQwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments▲ 140 on HF · May 28, 2026Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models▲ 30 on HF · Jun 17, 2026Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution76 cites · Sep 18, 2024Mitigating Hallucination in Vision-Language Models through Barrier-Regulated Adaptive Closed-form SteeringMay 28, 2026
Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.