deepseek-ai/DeepSeek-V4-Flash-Vision-Exp Image-Text-to-Text • 305B • Updated about 13 hours ago • 344
mistralai/Voxtral-Mini-4B-Realtime-2602 Automatic Speech Recognition • 4B • Updated Mar 11 • 2.16M • 957
view article Article SynthVision: Building a 110K Synthetic Medical VQA Dataset with Cross-Model Validation OpenMed • Mar 23 • 23