Related papers: On Strong Observational Refinement and Forward Sim…

As large-scale training regimes have gained popularity, the use of pretrained models for downstream tasks has become common practice in machine learning. While pretraining has been shown to enhance the performance of models in practice, the…

Hyperproperties allow one to specify properties of systems that inherently involve not single executions of the system, but several of them at once: observational determinism and non-inference are two examples of such properties used to…

The back-propagation algorithm has long been the de-facto standard in optimizing weights and biases in neural networks, particularly in cutting-edge deep learning models. Its widespread adoption in fields like natural language processing,…

The paper extends core results of behavioral systems theory from linear to affine time-invariant systems. We characterize the behavior of affine time-invariant systems via kernel, input-output, state-space, and finite-horizon data-driven…

Ensuring compliance with Information Flow Security (IFS) is known to be challenging, especially for concurrent systems with large codebases such as multicore operating system (OS) kernels. Refinement, which verifies that an implementation…

Conservative inference is a major concern in simulation-based inference. It has been shown that commonly used algorithms can produce overconfident posterior approximations. Balancing has empirically proven to be an effective way to mitigate…

For ordinary matrix models, the eigenvalue probability density decays rapidly as one goes to infinity, in other words, has "short tails". This ensures that all the multiple trace correlators (multipoint moments) are convergent and…

Foundation models are routinely fine-tuned for use in particular domains, yet safety assessments are typically conducted only on base models, implicitly assuming that safety properties persist through downstream adaptation. We test this…

Hyperproperties are properties of computational systems that require more than one trace to evaluate, e.g., many information-flow security and concurrency requirements. Where a trace property defines a set of traces, a hyperproperty defines…

We consider the problem of under and over-approximating the image of general vector-valued functions over bounded sets, and apply the proposed solution to the estimation of reachable sets of uncertain non-linear discrete-time dynamical…

Motion forecasting is crucial in enabling autonomous vehicles to anticipate the future trajectories of surrounding agents. To do so, it requires solving mapping, detection, tracking, and then forecasting problems, in a multi-step pipeline.…

The knowledge that humans hold about a problem often extends far beyond a set of training data and output labels. While the success of deep learning mostly relies on supervised training, important properties cannot be inferred efficiently…

One central issue in the formal design and analysis of reactive systems is the notion of refinement that asks whether all behaviors of the implementation is allowed by the specification. The local interpretation of behavior leads to the…

Traces are used to show whether a model complies with the intended behavior. A modeler can use trace checking to ensure the preservation of the model behavior during the refinement process. In this paper, we present a trace refinement…

It has been observed that visual classification models often rely mostly on the image background, neglecting the foreground, which hurts their robustness to distribution changes. To alleviate this shortcoming, we propose to monitor the…

Scientists often use observational time series data to study complex natural processes, but regression analyses often assume simplistic dynamics. Recent advances in deep learning have yielded startling improvements to the performance of…

Correctness conditions for concurrent objects describe how atomicity of an abstract sequential object may be decomposed. Many different concurrent objects and proof methods for them have been developed. However, arguments about correctness…

In High Energy Physics, as in many other fields of science, the application of machine learning techniques has been crucial in advancing our understanding of fundamental phenomena. Increasingly, deep learning models are applied to analyze…

Hyperspectral object tracking using snapshot mosaic cameras is emerging as it provides enhanced spectral information alongside spatial data, contributing to a more comprehensive understanding of material properties. Using transformers,…

In continual RL we want agents capable of never-ending learning, and yet our evaluation methodologies do not reflect this. The standard practice in RL is to assume unfettered access to the deployment environment for the full lifetime of the…