AI RESEARCH

Qwen3-VL-Seg: Unlocking Open-World Referring Segmentation with Vision-Language Grounding

arXiv CS.AI

ArXi:2605.07141v1 Announce Type: cross Open-world referring segmentation requires grounding unconstrained language expressions to precise pixel-level regions. Existing multimodal large language models (MLLMs) exhibit strong open-world visual grounding, but their outputs remain limited to sparse bounding-box coordinates and are insufficient for dense visual prediction.