Related papers: Formal specification of the FlexRay protocol using…
Federated Learning (FL) is an established paradigm for training deep learning models on decentralized data. However, as the size of the models grows, conventional FL approaches often require significant computational resources on client…
Focus, a framework for formal specification and development of interactive systems, was introduced approx. 25 years ago. Since then this approach was broadly used in academic and industrial studies, as well as provided a basis for a number…
Weighted finite-state transducers (FSTs) are frequently used in language processing to handle tasks such as part-of-speech tagging and speech recognition. There has been previous work using multiple CPU cores to accelerate finite state…
This report gives an overview of our efforts towards a formalization for a food processing demonstrator plant. Our BeSpaceD framework is used for the formalization. The formalization comprises properties of components and relations between…
Despite demonstrating superior performance across a variety of linguistic tasks, pre-trained large language models (LMs) often require fine-tuning on specific datasets to effectively address different downstream tasks. However, fine-tuning…
One of the main barriers preventing widespread use of formal methods is the elicitation of formal specifications. Formal specifications facilitate the testing and verification process for safety critical robotic systems. However, handling…
Adapting Foundation Models (FMs) for downstream tasks through Federated Learning (FL) emerges a promising strategy for protecting data privacy and valuable FMs. Existing methods fine-tune FM by allocating sub-FM to clients in FL, however,…
fairseq is an open-source sequence modeling toolkit that allows researchers and developers to train custom models for translation, summarization, language modeling, and other text generation tasks. The toolkit is based on PyTorch and…
We propose a programming technology that bridges cross-platform compatibility and hardware acceleration in ray tracing applications. Our methodology enables developers to define algorithms while our translator manages implementation…
The current fabrication and assembly of fluidic circuits for soft robots relies heavily on manual processes; as the complexity of fluidic circuits increases, manual assembly becomes increasingly arduous, error-prone, and timeconsuming. We…
The wealth of high-quality observational data from the epoch of reionization that will become available in the next decade motivates further development of modeling techniques for their interpretation. Among the key challenges in modeling…
Current high-resolution vision-language models encode images as high-resolution image tokens and exhaustively take all these tokens to compute attention, which significantly increases the computational cost. To address this problem, we…
Private Set Multi-Party Computations are protocols that allow parties to jointly and securely compute functions: apart from what is deducible from the output of the function, the input sets are kept private. Then, a Private Set Union (PSU),…
Speech separation and enhancement (SSE) has advanced remarkably and achieved promising results in controlled settings, such as a fixed number of speakers and a fixed array configuration. Towards a universal SSE system, single-channel…
This paper introduces a fully free and open source software (FOSS) architecture-neutral FPGA framework comprising of Yosys for Verilog synthesis, and nextpnr for placement, routing, and bitstream generation. Currently, this flow supports…
Although Federated Learning has been widely studied in recent years, there are still high overhead expenses in each communication round for large-scale models such as Vision Transformer. To lower the communication complexity, we propose a…
We investigate transmission protocols for relay-assisted free-space optical (FSO) systems, when multiple parallel relays are employed and there is no direct link between the source and the destination. As alternatives to all-active FSO…
Recent progress in image deblurring techniques focuses mainly on operating in both frequency and spatial domains using the Fourier transform (FT) properties. However, their performance is limited due to the dependency of FT on stationary…
We present XekRung, a frontier large language model for cybersecurity, designed to provide comprehensive security capabilities. To achieve this, we develop diverse data synthesis pipelines tailored to the cybersecurity domain, enabling the…
The purpose of fingerprinting is to compare long messages with low communication complexity. Compared with its classical version, the quantum fingerprinting can realize exponential reduction in communication complexity. Recently, the…