PLDM
An older world model architecture that attempted to prevent representation collapse by using a loss function with seven different interacting terms, resulting in unstable training with high variance
As defined in LeWorldModel: Stable End-to-End JEPA World Models From Pixels
Where it comes up · 1
Most important claims · 5 of 5Search all claims for “PLDM” →
- LayWM (Low-Rank World Model) is co-authored by a team including AI pioneer Yann LeCun and learns intuitive physics directly from raw video pixels using a novel two-term loss function instead of the seven-term loss function required by older models like PLDM.LeWorldModel: Stable End-to-End JEPA World Models From Pixels
- The fundamental trade-off of forcing AI representations to match a rigid isotropic Gaussian distribution is that the mandatory geometric complexity causes LayWM to fail on simple tasks with low intrinsic dimensionality, such as a 2D dot navigating through a door (two-room environment).LeWorldModel: Stable End-to-End JEPA World Models From Pixels
- Older models like PLDM attempted to prevent representation collapse by designing loss functions with seven different interacting terms, creating extreme training instability due to the combination lock problem—adjusting one parameter unpredictably shifts all others.LeWorldModel: Stable End-to-End JEPA World Models From Pixels
- LayWM requires only a single hyperparameter to tune (lambda), whereas PLDM required balancing seven interacting terms, changing the optimization problem from exponentially difficult multi-variable tuning to a simple logarithmic search.LeWorldModel: Stable End-to-End JEPA World Models From Pixels
- In the PushT robotic manipulation environment (where a 2D robotic arm precisely manipulates a block), LayWM achieved an 18% higher success rate than the older PLDM model, demonstrating accurate physics understanding despite using 200 times fewer tokens than foundation models.LeWorldModel: Stable End-to-End JEPA World Models From Pixels