UMD team releases icalens: GPU-accelerated ICA fitting with early stopping for interpretability research
sarahwiegreffe · x · 2026-10-22
The UMD team (Sarah Wiegreffe, Sida Liu, Feijiang Han, Furong Huang et al.) released icalens, an interpretability research tool installable via pip install icalens, alongside a paper, website, and GitHub repo.
Key points:
- They sped up the canonical CPU-based scikit-learn ICA implementation substantially using PyTorch/GPUs;
- They designed an early-stopping rule that works well for interpretability purposes;
- Paper, code, and demo site are all publicly available.
More from Research
- Future Chunk Prediction: teaching autoregressive video models real physics — yshan2u · 2026-10-22
- Google's on-device AI matches expert sonographers in prenatal ultrasound study — ymatias · 2026-10-22
- Artios launches as a fully open-source system for de novo enzyme design — DeryaTR_ · 2026-10-22
- U of T launches project on culturally grounded AI for mental health care in Bangladesh — ishtiaqueSIA · 2026-10-22
- Obsession With AI May Be Starving the Research Fields It Needs to Survive — Symbiot10000 · 2026-10-22
- Computational simulations back archaeology: spatial bottlenecks slow cultural diffusion — abenitezburraco · 2026-10-22