Study questions if spatial transcriptomics foundation models learn biology
lpachter · x · 2026-08-22
New work assesses whether spatial transcriptomics foundation models (SFMs) actually learn biologically meaningful spatial patterns. The results suggest that most current models fail to learn multi-scale spatial variation in gene expression effectively.
More from Research
- Scratch-built engine beats vendor runtime for ternary 8B models on free ARM cores — Annual_Manner_5901 · 2026-08-22
- Deep Dive: AI Text Watermarking Is Free and Good, So Why Is Everyone Mad? — Don't Worry About the Vase (Zvi) · 2026-08-22
- Virtual Embryo Challenge: Humans Break 200 Score, AI Agents Close the Gap — anshulkundaje · 2026-08-22
- CHIVE: Evaluating LLM explanations via counterfactual experiments — common interpretability techniques show no uplift — a_karvonen · 2026-08-22
- Interpretability Tools Fail to Beat Reading Transcripts in Agent Diagnostics — a_karvonen · 2026-08-22
- CHIVE Pipeline Reveals Gemma Coding Errors Due to Misleading Variable Names — a_karvonen · 2026-08-22