DiScoFormer: One transformer for density and score, across distributions
AI Classified by Officially
DiScoFormer is a transformer-based density and score estimator that can infer both quantities from a finite sample in one forward pass, generalizing classical KDE while staying accurate in high-dimensional and out-of-distribution settings without retraining for each new distribution.
This is an extract. The publication continues at the source.
Read the original at the source: https://allenai.org/blog/discoformer
Officially imported this from Allen Institute for AI’s own source and shows an extract. If you work there, claiming the profile and verifying the domain lets you choose to show the full text here.
Provenance
- Organization
- Allen Institute for AI — imported from official source
- Official source
- https://allenai.org/rss.xml RSS
- Imported
- September 20, 2026 19:52
- Versions
- 1 recorded
- Identity
-
https://allenai.org/blog/discoformer