Kestrel: 300M-Param Pathology Vision Foundation Model Pretrained on 400M Slide Patches
kjgeras · x · 2026-07-06
The underlying pathology signal for the AI test comes from Kestrel, a 303M-parameter ViT-L model. It uses the DINOv2 method for self-supervised pretraining on 400M pathology image patches from 45,000 slides, learning morphological features directly from H&E images rather than relying on hand-crafted features.
More from Research
- Hierarchical continuous flow language models make pathwise RL more robust to critic exploitation — vxnuaj · 2026-10-27
- rauchg reproduces OpenAI's covert CPU-channel finding: chat across Firecracker microVMs with no network — ccerrato147 · 2026-10-27
- Microsoft Research: ForkPilot cuts long-horizon agent compute by up to 59% — EliasEskin · 2026-10-27
- Microsoft's TeleTune evolves agent skills from offline user telemetry — EliasEskin · 2026-10-27
- FlexGlue: sparse-to-dense matching that beats dense accuracy at a fraction of the cost — zhenjun_zhao · 2026-10-27
- PixGR: pixel-space generative decoding for fast feed-forward 3D Gaussian reconstruction — zhenjun_zhao · 2026-10-27