Groma: Localized Visual Tokenization for Grounding Multimodal Large Language Models
Paper
•
2404.13013
•
Published
•
30
MMLM
-
-
Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing
Paper • 2404.12253 • Published • 54 -
Data-Efficient Contrastive Language-Image Pretraining: Prioritizing Data Quality over Quantity
Paper • 2403.12267 • Published -
No More Adam: Learning Rate Scaling at Initialization is All You Need
Paper • 2412.11768 • Published • 41