Qwen-2.5-VL

The 'Qwen2.5-VL' dataset/benchmark is used to evaluate the performance of multimodal large language models (MLLMs) in visual tasks by assessing their ability to process and interpret visual information effectively.

Papers using Qwen-2.5-VL (7)

HAWK: Head Importance-Aware Visual Token Pruning in Multimodal Models2026Think-as-You-See: Streaming Chain-of-Thought Reasoning for Large Vision-Language Models2026HALP: Detecting Hallucinations in Vision-Language Models without Generating a Single Token2026Cost-Efficient Multimodal LLM Inference via Cross-Tier GPU Heterogeneity2026Medvlthinker: Simple Baselines For Multimodal Medical Reasoning2025MASSV: Multimodal Adaptation and Self-Data Distillation for Speculative Decoding of Vision-Language Models2025Nexus: An Omni-Perceptive And -Interactive Model for Language, Audio, And Vision2025