DYSCO recovers governing equations from noisy high-dim data, accepted at NeurIPS
burny_tech · x · 2026-09-27
Paolo Muratore's DYSCO paper is now accepted at NeurIPS. It tackles recovering the equations governing a dynamical system directly from noisy, high-dimensional observations: it learns latent spaces capturing underlying dynamics and enables recovery of governing equations from them.
More from Research
- A Historical Introduction to Self-Play in Reinforcement Learning, Explained — cephaloform · 2026-09-27
- BrushArena streams its RL training runs live, letting anyone watch paintings evolve — xeophon · 2026-09-27
- Digital Consciousness Model Paper: Evidence Against 2024 LLM Consciousness Is Not Decisive — burny_tech · 2026-09-27
- Xiaomi open-sources RL environments on Hugging Face, potentially worth millions — burny_tech · 2026-09-27
- Solomonoff induction mirrors how intelligence works — but is physically impossible — burny_tech · 2026-09-27
- Xiaomi open-sources 7,000+ RL task environments used to train MiMo — burny_tech · 2026-09-27