3 papers
cs.LG2026
Moonwalk: Inverse-Forward Differentiation
Dmitrii Krylov, Armin Karamzade, Roy Fox
Backpropagation's main limitation is its need to store intermediate activations (residuals) during the forward pass, which restricts the depth of trainable networks. This raises a…
cs.LG2026
Model-Based Reinforcement Learning under Random Observation Delays
Armin Karamzade, Kyungmin Kim, JB Lanier +2
Delays frequently occur in real-world environments, yet standard reinforcement learning (RL) algorithms often assume instantaneous perception of the environment. We study random se…
cs.LG2025
Adapting World Models with Latent-State Dynamics Residuals
JB Lanier, Kyungmin Kim, Armin Karamzade +5
Simulation-to-reality reinforcement learning (RL) faces the critical challenge of reconciling discrepancies between simulated and real-world dynamics, which can severely degrade ag…