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
- EMNLP Oral: training-free Nexus Sampling cuts KV-cache memory 10x; OpenResearcher tops BrowseComp-Plus at 54.8% — yuz9yuz · 2026-10-27
- ICML 2026 position paper: LLM 'thinking traces' are a harmful anthropomorphism — rao2z · 2026-10-27
- Forking gap follows a power law in context frequency; masking rare n-grams shrinks it — ZimingLiu11 · 2026-10-27
- How forking happens: n-gram tables split logits into non-interacting subspaces — ZimingLiu11 · 2026-10-27
- The best LoRA explainer video yet: rank constraints meet intrinsic dimension — sophiamyang · 2026-10-27
- No π0 weights changed: Motoniq layer lifts real-robot precision fitting from 0/10 to 9/10 — hbouammar · 2026-10-27