Adaptive second-order discretizations beat entropy rate for optimal diffusion solvers
LucaAmb · x · 2026-10-10
Luca Ambrogioni's lab shares the first paper of bachelor's student Ella Kemperman: while second-order solvers offer impressive sampling acceleration, entropy rate alone cannot find optimal discretizations. The paper introduces a family of adaptive second-order discretizations that solve this. arXiv link and open-source GitHub code are available.
More from Research
- Embedding arithmetic demo: cartoon − animation − comic = diagram — mayfer · 2026-10-23
- Omnii Genome: Single Generalist Model Outperforms AlphaGenome Across All Benchmarks — JosephJacks_ · 2026-10-23
- Domingos Cites New Result Claiming RL Is 'Basically Useless' vs Supervised Learning — pmddomingos · 2026-10-23
- Word Arithmetic on Embeddings: "Bathroom Minus Toilet Equals Kitchen" Beats SAE Probing — mayfer · 2026-10-23
- Wolfram Opens Rule 30 Prizes to AIs: $30,000 for Three Open Problems — cephaloform · 2026-10-23
- Stanford and Databricks use AI agents to reproduce medical findings and test analytical robustness — ChengleiSi · 2026-10-23