Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution — mentioned by michaelt

Tue, 01 Apr 2025 22:47:27 GMT

qwen2.5-vl-72b-instruct seems perfectly happy outputting bounding boxes in my testing. There's also a paper https://arxiv.org/pdf/2409.12191 where they explicitly say some of their training included bounding boxes and coordinates.

Paper and discussion history. A mention is not an endorsement.

Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution · HackerPapers discussions

Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution — mentioned by michaelt