The paper introduces a comprehensive benchmark to test if physics foundation models learn generalizable dynamics, finding that their performance is highly conditional and not universally general.

The paper uses majorization theory to analyze lattice reduction, showing that local swaps smooth the Gram-Schmidt profile and deriving variational and telescoping identities for the worst-case profile…

This paper studies the probability of a trajectory lying in a designated failure region during training of a model with noisy gradient descent, and derives bounds for this probability.

Stochastic Lifting is a novel technique that enhances the modeling of stochastic physical systems by introducing independent random labels to state transitions, allowing a single network to generate d…

The paper introduces the Kerimov-Alekberli model, an information-geometric framework that uses non-equilibrium thermodynamics and stochastic control to provide a physically grounded method for detecti…

This paper investigates how network perturbations can alter the asymptotic agreement trajectory in distributed coordination systems, proving fragility in standard cooperative output regulation schemes…

This paper studies covert communication in a scalar Gaussian model, deriving the maximal reliably transmissible covert payload and establishing first-order optimality.

The paper conducts a preliminary safety evaluation of the open-weight LLM Kimi K2.5, finding that while it is highly capable, it exhibits concerning dual-use risks, particularly regarding CBRNE misuse…

The paper introduces Entropic Projection Alignment (EPA), a unified framework that estimates, explains, and improves model performance under distribution shift by aligning source and target distributi…

The paper introduces Multifidelity Proper Orthogonal Decomposition (MFPOD), a method that significantly reduces the computational cost of dimension reduction by intelligently combining data from cheap…

The paper analyzes the structured CVP distance on the log-unit lattice of cyclotomic fields, significantly reducing the conjectured CDPR factor for the ML-KEM cryptosystem from exponential to sub-poly…

The paper introduces a framework using the 'behavioral geometry' of model populations to efficiently predict jailbreak susceptibility and transfer defenses, achieving high accuracy with significantly…

This paper proposes a human-likeness index based on time laws of human movement to evaluate the comfort of robot movements.

A two-layer framework using a large language model for force-conditioned reinforce learning with recovery maneuvers and force signatures.

The paper introduces SafetyDrift, a predictive model that forecasts when AI agents will violate safety protocols by analyzing the cumulative risk across sequences of individually safe actions.

The paper introduces NewtPhys, a novel 4D dataset of real-world scenes with dense physical annotations, to systematically evaluate and reveal the limitations of foundation models in low-level Newtonia…