How HiRO-ACEv2 works: ACE emulates at 100 km, HiROv2 downscales to 3 km
allen_ai · x · 2026-10-15
A thread post on Ai2's HiRO-ACEv2 explaining the two-stage architecture: ACE, an AI climate emulator, simulates climate at a coarser 100 km resolution; HiROv2, an AI downscaling model, sharpens outputs to 3 km. V2 adds near-surface wind and sea level pressure downscaling beyond v1's rainfall-only scope.
More from Research
- Open scaling-law questions: NTP on a code repo vs RL on its tasks — which is more compute-efficient? — brianryhuang · 2026-10-15
- Zero-knowledge training: contributing to models without sharing the data — rickasaurus · 2026-10-15
- What creativity leaderboards actually measure: 15 benchmarks point to long-tail performance — shangbinfeng · 2026-10-15
- Random Brainfuck programs on a 2D grid spontaneously evolve self-replicators — spikedoanz · 2026-10-15
- Classifier run on 42,000+ ICLR 2027 submissions finds over half nearly fully AI-assisted — nsaphra · 2026-10-15
- LLM4Code workshop at ICSE 2027 opens call for papers, due Nov 13, 2026 — LingmingZhang · 2026-10-15