Creative chess puzzle generation with diffusion models: new RL recipe, open weights
TZahavy · x · 2026-10-03
Eric Malmi's team released a preprint on creative chess puzzle generation using masked diffusion models. In his MSc thesis, Aatu Selkee added a new RL recipe on top of the masked diffusion model, improving on prior SOTA. The generator can be conditioned by theme, partial board position, or best move, extending the team's earlier puzzle-generation work. They are open-sourcing the model — the first open-weights models for chess puzzle generation — alongside a public demo and paper.
More from Research
- CMU blog: harness engineering boosts scientific agents without retraining models — niloofar_mire · 2026-10-03
- Automated agent harness search vs human taste: no winner across drug design tasks — niloofar_mire · 2026-10-03
- AI agents settle all 15,973 semigroups of order 6 with 5M lines of verified Lean — KyleCranmer · 2026-10-03
- Dev open-sources Peacebell, a from-scratch 291M WWII domain LLM built over 11 months — wayneworkman · 2026-10-03
- Dev vibecodes AtlasBench Europe spatial reasoning benchmark; GPT-6.1 tops at 84.67% — flowersslop · 2026-10-03
- Light-powered AI detects deepfakes with nearly 98% accuracy — ai-edition · 2026-10-03