A wonderful collaborative effort from UMD. We hope our works will help those looking for the big picture in Vision-Language Models. We came across this comprehensive overview of SoTA large models, covering model architectures, new models, benchmarks, the hottest VLM RL alignment, and applications. If you're new to VLM or want to learn more, you can check out this paper and the associated GitHub list. Hopefully it would help you with your conference submissions! Link: github.com/zli12321/Vision-L… #MultimodalAI #LargeModels #NeurIPS #CVPR #R1 #AhaMoment #GPT #NIPS #EMNLP #ACL #ICLR #ICML #LargeModelSurvey #TopTierConference