3 papers
cs.LG2026
Prediction horizon shapes representations in predictive learning
Aviv Ratzon, Omri Barak
Predictive learning has emerged as a central paradigm for training models across diverse data domains and is increasingly viewed as a foundation for modern artificial intelligence.…
cs.LG2025
Finding separatrices of dynamical flows with Deep Koopman Eigenfunctions
Kabir V. Dabholkar, Omri Barak
Many natural systems, including neural circuits involved in decision making, are modeled as high-dimensional dynamical systems with multiple stable states. While existing analytica…
cs.LG2025
When predict can also explain: few-shot prediction to select better neural latents
Kabir Dabholkar, Omri Barak
Latent variable models serve as powerful tools to infer underlying dynamics from observed neural activity. Ideally, the inferred dynamics should align with true ones. However, due…