Related papers: The Observer Effect in World Models: Invasive Adap…

The multiscale and turbulent nature of Earth's atmosphere has historically rendered accurate weather modeling a hard problem. Recently, there has been an explosion of interest surrounding data-driven approaches to weather modeling, which in…

We present a smoothly broken power law functional form (that we refer to as a Broken Neural Scaling Law (BNSL)) that accurately models & extrapolates the scaling behaviors of deep neural networks (i.e. how the evaluation metric of interest…

We present an adaptive reduced-order model for the efficient time-resolved simulation of fluid-structure interaction problems with complex and non-linear deformations. The model is based on repeated linearizations of the structural balance…

Video world models trained with Joint Embedding Predictive Architectures (JEPA) acquire rich spatiotemporal representations by predicting masked regions in latent space rather than reconstructing pixels. This removes the visual verification…

We propose a new method to measure time-dependent linear susceptibilities in molecular simulations, which does not require the use of nonequilibrium simulations, subtraction techniques, or fluctuation-dissipation theorems. The main idea is…

This paper shows how the theory of nonlinear adaptive observers can be effectively used in the design of internal models for nonlinear output regulation. The theory substantially enhances the existing results in the context of {\em…

We propose Obfuscated Semantic Null space Injection for Privacy (OSNIP), a lightweight client-side encryption framework for privacy-preserving LLM inference. Generalizing the geometric intuition of linear kernels to the high-dimensional…

There is a family of label modification approaches including self and non-self label correction (LC), and output regularisation. They are widely used for training robust deep neural networks (DNNs), but have not been mathematically and…

Most real world phenomena such as sunlight distribution under a forest canopy, minerals concentration, stock valuation, exhibit nonstationary dynamics i.e. phenomenon variation changes depending on the locality. Nonstationary dynamics pose…

World models aim to improve robotic decision making by predicting the consequences of actions. However, in practice, their predictions often become unreliable once the robot encounters states outside the training distribution, limiting…

State-of-the-art machine-learning-based models are a popular choice for modeling and forecasting energy behavior in buildings because given enough data, they are good at finding spatiotemporal patterns and structures even in scenarios where…

The structural response under the earthquake excitations can be simulated by scaled-down model shake table tests or full-scale model shake table tests. In this paper, adaptive control theory is used as a nonlinear shake table control…

Pseudo-Labeling has emerged as a simple yet effective technique for semi-supervised object detection (SSOD). However, the inevitable noise problem in pseudo-labels significantly degrades the performance of SSOD methods. Recent advances…

A data analyst might worry about generalization if dropping a very small fraction of data points from a study could change its substantive conclusions. Checking this non-robustness directly poses a combinatorial optimization problem and is…

We have developed a simulation model to describe particle adsorption to and desorption from liquid interfaces. Using this model we formulate a closed interfacial equation of state for repulsive elastic spheres. The effect of a long-range…

Models of spontaneous wave function collapse describe the quantum-to-classical transition by assuming a progressive breakdown of the superposition principle when the mass of the system increases, providing a well-defined phenomenology in…

State estimation is key to both analyzing physical mechanisms and enabling real-time control of fluid flows. A common estimation approach is to relate sensor measurements to a reduced state governed by a reduced-order model (ROM). (When…

In supervisory control settings, autonomous systems are not monitored continuously. Instead, monitoring often occurs at sporadic intervals within known bounds. We study the problem of deception, where an agent pursues a private objective…

Open-set semi-supervised learning (OSSL) leverages unlabeled data containing both in-distribution (ID) and unknown out-of-distribution (OOD) samples, aiming simultaneously to improve closed-set accuracy and detect novel OOD instances.…

We develop biologically plausible training mechanisms for self-supervised learning (SSL) in deep networks. Specifically, by biological plausible training we mean (i) All updates of weights are based on current activities of pre-synaptic…