STEM-Bank-26: largest open STEM microscopy dataset, 929GB, at NeurIPS
charlesxjyang · x · 2026-11-02
A UPenn team's STEM-Bank-26 paper is accepted to the AI4Mat Workshop at NeurIPS Sydney. It's the largest open scanning transmission electron microscopy dataset to date: 929GB, 37,921 images spanning 1,095 material samples across 1,499 sessions, with EDS or EELS spectroscopy for 65.5% of sessions. The team extracts microscope control trajectories from sequential-image metadata and provides tools for building similar datasets from archival data.
More from Research
- HalachaBench sparks debate: is Talmudic Q&A testing knowledge or reasoning? — teortaxesTex · 2026-11-02
- Sebastian Raschka releases free 11-hour course on building reasoning models from scratch — AxSaucedo · 2026-11-02
- Microsoft and Berkeley open-source TokenEconomizer, cutting coding agent costs 18–31% — victor_explore · 2026-11-02
- TLA-Verus uses LLM agents to prove temporal properties of TLA+ specs — tianyin_xu · 2026-11-02
- J-Lens is just a first-order Taylor expansion, researcher points out — burny_tech · 2026-11-02
- Mollick: expert-level work benchmarks are brutally hard, and ARC-AGI, GDPval, METR are saturated — emollick · 2026-11-02