Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges Paper • 2406.12624 • Published Jun 18 • 35
InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD Paper • 2404.06512 • Published Apr 9 • 29
Mixture-of-Depths: Dynamically allocating compute in transformer-based language models Paper • 2404.02258 • Published Apr 2 • 102
Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models Paper • 2403.18814 • Published Mar 27 • 42
mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding Paper • 2403.12895 • Published Mar 19 • 29
LLaVA-UHD: an LMM Perceiving Any Aspect Ratio and High-Resolution Images Paper • 2403.11703 • Published Mar 18 • 15