TuringViT: Making SOTA Vision Transformers Accessible to All
- Published
- Source
- arXiv
- Paper number
- 494
- Field
- Computer Vision
- arXiv ID
- 2606.24253
Key points
- TuringViT introduces Turing linear attention (TLA) to efficiently process high-resolution and dynamically resized visual sequences.
- Its VISTA-Curation pipeline curates image and video data to improve data efficiency and support native dynamic-resolution training.
Paper links
External research summaries. These are not HDATF publications or measured product results.