TREVIS learns sparse decision trees via transformer variational auto-encoders
Giacomo Fidone · hf · 2026-09-15
TREVIS is a new method for learning sparse decision trees using a tree transformer variational auto-encoder.
Core idea: decision trees are discrete structures that are hard to optimize directly. TREVIS encodes them into a continuous latent space, optimizes the latent representation with a tree-structured transformer VAE, and decodes back to trees — jointly improving predictive accuracy and structural sparsity while preserving interpretability.
More from Research
- k-server Conjecture Proved, Closing a Classic Online Algorithms Open Problem — minilek · 2026-09-15
- Yale physicists re-grade AI benchmarks: most are broken, frontier models near saturation — inductionheads · 2026-09-15
- Negative Self-Distillation: A Label-Free Method That Trains LLMs to Explicitly Avoid Flaws — kastnerkyle · 2026-09-15
- Podcast: Microsoft researcher hits ~45% on ARC-AGI with tiny recursive networks — ziv_ravid · 2026-09-15
- At ACM AI Summit, formal methods and neurosymbolic AI pitched as ready-made paths to safer AI — luislamb · 2026-09-15
- Oxford Paper 'Theory Is All You Need' Argues LLMs Are Mathematically Incapable of True Novelty — gvachtan · 2026-09-15