multimodal-vision-ai/OvisOCR3-0.8B-WebGPU-ONNX
Image-Text-to-Text • Updated • 29
AI & ML interests
Multimodal AI, Vision-Language Models, Document Intelligence, OCR, Handwriting Recognition, Compact VLMs, Multimodal Post-Training, SFT, GRPO
Recent Activity
View all activity
multimodal-vision-ai/Wang-Qwen3.5-2B-DocTags-ONNX
Image-Text-to-Text • Updated • 62 • 1
multimodal-vision-ai/Wang-Qwen3.5-2B-DocTags
Image-Text-to-Text • 2B • Updated • 45
multimodal-vision-ai/R3-OvisOCR3-DocTags-0.8B-ONNX
Image-Text-to-Text • Updated • 53
multimodal-vision-ai/mvai-video-action-compare-models
Video Classification • Updated • 584