Occam's Razor

Prediction Under Imperfect Compression: A Theory of Approximate MDL

Announce Type: new Abstract: Minimum Description Length (MDL) formalizes the principle of Occam's razor by optimizing the total description length: $L(\mathrm{model})+L(\mathrm{data} \ | \ \mathrm{model})$. For sequential prediction, the MDL method repeatedly selects a model with a minimum objective score of the observed prefix for the next step prediction. Classical MDL prediction theory shows that exact optimization of the MDL objective indeed provides a strong compression guarantee that...

World-Task Factorization for Robot Learning

arXiv:2606.02027v1 Announce Type: new Abstract: Robot learning must produce policies that generalize to new combinations of constraints, teammates, and environments. To achieve this, we must structurally factor the policy, which is a choice that dictates what generalizes, what requires retraining, and what remains entangled. Existing methods span a wide spectrum, from expecting structure to emerge from data scaling, to hand-designing it via hierarchies, skill libraries or learned...

Internalizing Temporal Consistency in Video Object-Centric Learning without Explicit Regularization

arXiv:2605.31508v1 Announce Type: new Abstract: Video Object-Centric Learning (OCL) aims to represent objects as \textit{slot} vectors and maintain their consistency across frames. Slot-Slot Contrastive (SSC) loss has become the cornerstone for state-of-the-art (SOTA) video OCL methods. While highly effective, SSC relies on one-to-one object correspondence across frames and introduces an extra loss.

That an app 'Fits on a Floppy' is still a useful measure in 2026

Barnwell on the much anticipated A.J. Brown trade:...

Before the Rams decided to throw the NFL news cycle into overdrive by trading for a future Hall of Famer in Myles Garrett, there was another trade that was supposed to dominate June 1. And after months of waiting, the Eagles and Patriots finally consummated their long-rumored deal, with wide receiver A.J. Brown heading to New England to join Drake Maye's offense. The Eagles pick up a 2028 first-round pick in return for their star wideout, with an additional 2027 fifth-rounder heading to...

Sharpness-Aware Hybrid Model Learning for Architecture-Agnostic Parameter Estimation

arXiv:2602.06837v2 Announce Type: replace Abstract: Hybrid modeling, the combination of machine learning models and scientific mathematical models, enables flexible and robust data-driven prediction with partial interpretability. However, the unknown parameters of the scientific model cannot necessarily be estimated properly, since the flexibility of the machine learning model might make the scientific model part effectively ignored in prediction.