MoE-LLaVA: Mixture of Experts for Large Vision-Language Models
Paper
•
2401.15947
•
Published
•
54
Interesting papers
-
-
How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites
Paper • 2404.16821 • Published • 58 -
Physically Grounded Vision-Language Models for Robotic Manipulation
Paper • 2309.02561 • Published • 9 -
MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark
Paper • 2409.02813 • Published • 32