COMPASS Uses Two-Stage Training: Self-Supervised Pre-Training and Cohort Fine-Tuning
marinkazitnik · x · 2026-07-03
COMPASS employs a two-stage training architecture. It first undergoes self-supervised pre-training on 10,184 tumor samples across 33 cancer types to learn universal tumor immune representations. Subsequently, it is fine-tuned on 16 clinical cohorts spanning 7 cancer types. This supports various adaptation strategies ranging from zero-shot inference to full-parameter updates, with training methods calibrated based on cohort size.
More from Research
- Navier-Stokes, Riemann, P vs NP: what this week's math buzzwords mean for you — koltregaskes · 2026-09-11
- Fruit fly connectome LLM weights land on Hugging Face, transformers-compatible — ngxson · 2026-09-11
- Fruit fly brain as an LLM: connectome-driven language model demo goes live — ngxson · 2026-09-11
- Harry Collins: LLMs can't do frontier science because they can't invent new language — whoamisri · 2026-09-11
- The Waymo effect: how AI is quietly making research less collaborative — JohnHammersley · 2026-09-11
- Causal-only attention for non-generative tasks is wasteful, argues HF engineer — antoine_chaffin · 2026-09-11