Related papers: Formally and Empirically Verified Methodologies fo…
Modern computer vision systems increasingly encounter performance limitations in data-scarce domains, where collecting large-scale, high-quality labeled data is costly or impractical. While controllable diffusion models enable scalable…
A key aspect in creating models of production systems with the use of model-based systems engineering (MBSE) lies in the description of system functions. These functions shouldbe described in a clear and standardized manner.The VDI/VDE 3682…
Large-eddy simulation (LES) is a well-established numerical technique, which resolves the most energetic turbulent fluctuations in the planetary boundary layers. Averaging these fluctuations, high-quality profiles of mean values and…
Spreadsheet software is the tool of choice for interactive ad-hoc data management, with adoption by billions of users. However, spreadsheets are not scalable, unlike database systems. On the other hand, database systems, while highly…
Symbolic execution is a powerful technique for analyzing the behavior of software yet scalability remains a challenge due to state explosion in control and data flow. Existing tools typically aim at managing control flow internally, often…
Most work in privacy-preserving federated learning (FL) has focused on horizontally partitioned datasets where clients hold the same features and train complete client-level models independently. However, individual data points are often…
Large language models (LLMs) deliver impressive generation quality, but incur very high inference cost because each output token is generated auto-regressively through all model layers. Early-exit based self-speculative decoding (EESD) has…
Applications in quantitative finance such as optimal trade execution, risk management of options, and optimal asset allocation involve the solution of high dimensional and nonlinear Partial Differential Equations (PDEs). The connection…
We study the problem of maintaining a breadth-first spanning tree (BFS tree) in partially dynamic distributed networks modeling a sequence of either failures or additions of communication links (but not both). We present deterministic…
Selective State Space Models (SSMs) achieve linear-time inference, yet their gradient-based sensitivity analysis remains bottlenecked by O(L) memory scaling during backpropagation. This memory constraint precludes genomic-scale modeling (L…
We investigate the computational complexity of neural network verification in quantised settings. We distinguish three classes of Feedforward Neural Networks (FNNs): rational FNNs with exact rational weights, quantised FNNs whose weights…
Structural balance modeling for signed graph networks presents how to model the sources of conflicts. The state-of-the-art focuses on computing the frustration index of a signed graph, a critical step toward solving problems in social and…
Verifying that input-output relationships of a neural network conform to prescribed operational specifications is a key enabler towards deploying these networks in safety-critical applications. Semidefinite programming (SDP)-based…
State-of-the-art text-to-image models produce high-quality images, but inference remains expensive as generation requires several sequential ODE or denoising steps. Native one-step models aim to reduce this cost by mapping noise to an image…
BFS (Breadth-First Search) is a typical graph algorithm used as a key component of many graph applications. However, current distributed parallel BFS implementations suffer from irregular data communication with large volumes of transfers…
We propose and implement a Privacy-preserving Federated Learning ($PPFL$) framework for mobile systems to limit privacy leakages in federated learning. Leveraging the widespread presence of Trusted Execution Environments (TEEs) in high-end…
With the increasing adoption of Continuous Integration and Continuous Deployment pipelines, securing software supply chains has become a critical challenge for modern DevOps teams. This study addresses these challenges by applying a…
Efficient exploitation of exascale architectures requires rethinking of the numerical algorithms used in many large-scale applications. These architectures favor algorithms that expose ultra fine-grain parallelism and maximize the ratio of…
Universal force fields generalizable across the periodic table represent a new trend in computational materials science. However, the applications of universal force fields in material simulations are limited by their slow inference speed…
Modelling software product line (SPL) features plays a crucial role to a successful development of SPL. Feature diagram is one of the widely used notations to model SPL variants. However, there is a lack of precisely defined formal…