Home
News
Members
Publications
NVIDIA Research
Light
Dark
Automatic
RADIO Amplified: Improved Baselines for Agglomerative Vision Foundation Models
Greg Heinrich
,
Mike Ranzinger
,
Hongxu (Danny) Yin
,
Yao Lu
,
Jan Kautz
,
Bryan Catanzaro
,
Andrew Tao
,
Pavlo Molchanov
June 2025
Cite
arXiv
Type
Conference paper
Publication
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Greg Heinrich
Hongxu (Danny) Yin
Jan Kautz
Team Leader
Pavlo Molchanov
Related
FasterViT: Fast Vision Transformers with Hierarchical Attention
VILA: On pretraining for vision language models
AM-RADIO: Agglomerative Model - Reduce All Domains Into One
Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders
Flextron: Many-in-One Flexible Large Language Model
Cite
×