WorldRuler: rule-graph world models that honor user-defined game rules
AlayaLab · hf · 2026-11-19
WorldRuler (Alaya Lab, BIT, U Tokyo et al.) tackles rule-state persistence and rule-to-visual realization in generative world models via an executable 3D rule graph linking rule execution, video generation and perceptual feedback, with counterfactual reconstruction training and a GTA-V/Habitat-derived RuleVerse dataset.
More from Research
- Epoch AI: Models prefer their own outputs over human gold standard in 23 of 24 tests — BethMayBarnes · 2026-11-19
- tessera-small: a diffusion-LLM-based pixel-art text-to-image model — thejagstudio · 2026-11-19
- NexSight: verifiable long-video tasks show top models score only 54.5% — nex-agi · 2026-11-19
- PReMind: benchmark + RL framework for hazard-aware personalized VLM assistants — SeoulNatlUniv · 2026-11-19
- Late Entry in looped LLMs delivers up to 12.5x lossy and 8.4x exact speedups — NanyangTechnologicalUniversity · 2026-11-19
- Optimization × AI Forum on Nov 20: two Peking University talks on AI-driven math discovery — aaron_defazio · 2026-11-19