2 papers
cs.LG2026
Learning the Koopman Operator using Attention Free Transformers
Mohammed Nagdi, Evangelos-Marios Nikolados, Alexey Yermakov +3
Learning Koopman operators with autoencoders enables linear prediction in a latent space, but long-horizon rollouts often drift off the learned manifold, leading to phase and ampli…
cs.LG2025
Exploring Human-AI Conceptual Alignment through the Prism of Chess
Semyon Lomasov, Judah Goldfeder, Mehmet Hamza Erol +5
Do AI systems truly understand human concepts or merely mimic surface patterns? We investigate this through chess, where human creativity meets precise strategic concepts. Analyzin…