Yanghao Li
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision TokenizerSaved credit: First author · 2026Explore people connected to this work →
- Masked Autoencoders Are Scalable Vision LearnersSaved credit: Contributor · 2021Explore people connected to this work →
- MViTv2: Improved Multiscale Vision Transformers for Classification and DetectionSaved credit: First author · 2022Explore people connected to this work →
- Scaling Language-Image Pre-training via MaskingSaved credit: First author · 2023Explore people connected to this work →
- Hiera: A Hierarchical Vision Transformer without the Bells-and-WhistlesSaved credit: Contributor · 2023Explore people connected to this work →