omlab/Qwen2.5VL-3B-VLM-R1-REC-500steps Zero-Shot Object Detection β’ 4B β’ Updated Apr 14 β’ 149 β’ 23
HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v2 Feature Extraction β’ 0.5B β’ Updated Oct 8 β’ 2.05k β’ 31
Runtime error 72 VLM R1 Referral Expression π¬ 72 Mark regions in images based on text descriptions