ReflectWorld-MM: An Entity-Oriented Multimodal Memory System for Open-Ended Video Streams Paper • 2607.09759 • Published 6 days ago • 16
Running on Zero Agents Featured 484 DeepSeek OCR 2 Demo 🚀 484 Try out DeepSeek-OCR-2 on your PDFs or images
Infinity-Parser2 Collection Multimodal Synthetic Dataset and Multi-Task Reinforcement Learning Document Parser • 4 items • Updated 19 days ago • 2
Trust the Right Teacher: Quality-Aware Self-Distillation for GUI Grounding Paper • 2606.18101 • Published Jun 16 • 15