Graph Neural Networks (GNNs) present a fundamental hardware challenge by fusing irregular, memory-bound graph traversals with regular, compute-intensive dense m...
Digital Twins (DTs) are increasingly used as autonomous decision-makers in complex socio-technical systems. Their mathematically optimal decisions often diverge...
Software plays an ever increasing role in complex system development and prototyping, and in recent years, MIT Lincoln Laboratory has sought to improve both the...
Relational data, occurring in the real world, are often structured as graphs, which provide the logical abstraction required to make analytical derivations simp...
Software supply chain attacks have revealed blind spots in existing SCA tools, which are often limited to a single ecosystem and assess either software artifact...
Advanced deep learning architectures, particularly recurrent neural networks (RNNs), have been widely applied in audio, bioacoustic, and biomedical signal analy...
This paper explores the integration of MPI-based synchronization techniques into distributed fuzzing frameworks, highlighting possible substantial performance i...
Fuzzing is a highly effective method for uncovering software vulnerabilities, but analyzing the resulting data typically requires substantial manual effort. Thi...
In many academic disciplines, software is created during the research process or for a research purpose. The crucial role of software for research is increasing...
Federated Learning is a popular approach for distributed learning due to its security and computational benefits. With the advent of powerful devices in the net...
Covid has made online teaching and learning acceptable and students, faculty, and industry professionals are all comfortable with this mode. This comfort can be...
We present Conformer-based decoders for the LibriBrain 2025 PNPL competition, targeting two foundational MEG tasks: Speech Detection and Phoneme Classification....
Many modern software projects evolve rapidly to incorporate new features and security patches. It is important for users to update their dependencies to safer v...
Serverless Large Language Models (LLMs) have emerged as a cost-effective solution for deploying AI services by enabling a 'pay-as-you-go' pricing model through ...
This paper introduces a new family of multi-parent recombination operators for Genetic Algorithms (GAs), based on normalized Pascal (binomial) coefficients. Unl...
In this paper we investigate a neural network model in which weights between computational nodes are modified according to a local learning rule. To determine w...
The Machine Consciousness Hypothesis states that consciousness is a substrate-free functional property of computational systems capable of second-order percepti...
Inference over large-scale foundation models within heterogeneous edge environments necessitates a fundamentally reconfigurable orchestration substrate. Static ...
Federated fine-tuning offers a promising solution for adapting Large Language Models (LLMs) to downstream tasks while safeguarding data privacy. However, its hi...
Microservices have transformed software architecture through the creation of modular and independent services. However, they introduce operational complexities ...
Quality-Diversity (QD) algorithms constitute a branch of optimization that is concerned with discovering a diverse and high-quality set of solutions to an optim...
As large language models (LLMs) scale out with tensor parallelism (TP) and pipeline parallelism (PP) and production stacks have aggressively optimized the data ...
Reasoning over dynamic visual content remains a central challenge for multimodal large language models. Recent thinking models generate explicit reasoning trace...
Recent multimodal large language models (MLLMs) have advanced video understanding, yet most still 'think about videos' ie once a video is encoded, reasoning unf...
