FRM Matches EqR on Sudoku-Extreme With 44x Fewer FLOPs
alec_helbling · x · 2026-09-17
Follow-up data from the FRM work: compared to HRM, TRM and masked diffusion, FRMs are dramatically more inference-efficient. On Sudoku-Extreme, FRMs match the next-best method EqR's solve rate with 44x fewer FLOPs while reaching higher peak accuracy.
Related event: Flow Reasoning Models Turn Flow Models into Recurrent Reasoners(3 posts)→
More from Research
- Dream-RSI: Google DeepMind paper makes the research process itself self-improving — McDonaghMatthew · 2026-09-17
- Dream-RSI from Google DeepMind turns AI experiment logs into reusable self-improvement testbeds — McDonaghMatthew · 2026-09-17
- MIT's FloatForm robot boats self-assemble into bridges on water, published in Nature — lukas_m_ziegler · 2026-09-17
- DeepMind open-sources a fruit fly that learned to fly, 59-dim action space on a laptop — anthara_ai · 2026-09-17
- XPeng unveils XPACE, a unified embodied world model powering its IRON humanoid — CyberRobooo · 2026-09-17
- Max-pooling attribution maps model outputs back to input words in new sparse-model release — antoine_chaffin · 2026-09-17