3 papers
cs.LG2026
The Objective Is the Bottleneck: Latent World Models Encode What Their Planners Cannot Use
Joyjeet Singh
Latent world models are judged by how well they predict, so when planning fails at long horizons the natural reading is that the predictor degrades. On a reproduction of LeWorldMod…
cs.LG2026
The Evaluation Protocol Determines the Result: An Independent Reproduction of LeWorldModel on TwoRoom
Joyjeet Singh
LeWorldModel trains a latent world model with a prediction loss and a single anti-collapse regulariser, and reports approximately 87% of goals reached on TwoRoom, its simplest diag…
cs.LG2026
The Equilibrium Is the Initialization: Lazy Identity Collapse in Physics-Structured Deep Equilibrium Reasoning
Joyjeet Singh
Deep equilibrium models promise input-adaptive implicit computation: harder problems should demand more solver iterations, and the solved equilibrium should encode the result of ge…