DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation Paper โข 2410.18666 โข Published 27 days ago โข 18
InfiMM-WebMath-40B: Advancing Multimodal Pre-Training for Enhanced Mathematical Reasoning Paper โข 2409.12568 โข Published Sep 19 โข 47
Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone Paper โข 2404.14219 โข Published Apr 22 โข 253
InfiMM-HD: A Leap Forward in High-Resolution Multimodal Understanding Paper โข 2403.01487 โข Published Mar 3 โข 14
COCO is "ALL'' You Need for Visual Instruction Fine-tuning Paper โข 2401.08968 โข Published Jan 17 โข 2
CORE-MM: Complex Open-Ended Reasoning Evaluation For Multi-Modal Large Language Models Paper โข 2311.11567 โข Published Nov 20, 2023 โข 8