-
MoE-LLaVA: Mixture of Experts for Large Vision-Language Models
Paper • 2401.15947 • Published • 53 -
How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites
Paper • 2404.16821 • Published • 59 -
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 • 33
Mayank Kumar
mayankgrd
·
AI & ML interests
None yet
Organizations
None yet
Interesting papers
-
MoE-LLaVA: Mixture of Experts for Large Vision-Language Models
Paper • 2401.15947 • Published • 53 -
How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites
Paper • 2404.16821 • Published • 59 -
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 • 33