Related papers: Parametric-Sensitivity Aware Retransmission for Ef…

Large language models (LLMs) enhanced with retrieval-augmented generation (RAG) have introduced a new paradigm for web search. However, the limited context awareness of LLMs degrades their performance on RAG tasks. Existing methods to…

Adapters have been widely explored to alleviate computational and storage costs when fine-tuning pretrained foundation models. However, the adapter itself can exhibit redundancy, leading to unnecessary storage overhead and inferior…

Novel bitwise retransmission schemes are devised which retransmit only the bits received with small reliability. The retransmissions are used to accumulate the reliabilities of individual bits. Unlike the conventional automatic repeat…

Power consumption plays a crucial role in on-device streaming speech recognition, significantly influencing the user experience. This study explores how the configuration of weight parameters in speech recognition models affects their…

Most current Deep Learning-based Semantic Communication (DeepSC) systems are designed and trained exclusively for particular single-channel conditions, which restricts their adaptability and overall bandwidth utilization. To address this,…

The growing scale of deep learning models has rendered standard hyperparameter (HP) optimization prohibitively expensive. A promising solution is the use of scale-aware hyperparameters, which can enable direct transfer of optimal HPs from…

Parallel applications are often unable to take full advantage of emerging parallel architectures due to scaling limitations, which arise due to inter-process communication. Performance models are used to analyze the sources of communication…

Provenance embedding algorithms are well known for tracking the footprints of information flow in wireless networks. Recently, low-latency provenance embedding algorithms have received traction in vehicular networks owing to strict…

State-of-the-art parameter-efficient fine-tuning methods rely on introducing adapter modules between the layers of a pretrained language model. However, such modules are trained separately for each task and thus do not enable sharing…

Transformers have shown improved performance when compared to previous architectures for sequence processing such as RNNs. Despite their sizeable performance gains, as recently suggested, the model is computationally expensive to train and…

We propose a novel framework, termed Fourier-Activated Adapter (FAA), for parameter-efficient fine-tuning of large pre-trained language models. By incorporating random Fourier features into lightweight adapter modules, FAA decomposes…

Integrated sensing and communication (ISAC) is a key technology for enabling a wide range of applications in future wireless systems. However, the sensing performance is often degraded by model mismatches caused by geometric errors (e.g.,…

With the proliferation of wideband active services in bands shared with passive receivers for remote sensing and radio astronomy, new methods are needed for deconflicting active and passive users. We have developed a technique for…

Pairwise comparison data arise in many domains with subjective assessment experiments, for example in image and video quality assessment. In these experiments observers are asked to express a preference between two conditions. However, many…

As wireless networks transition toward 6G, high mobility, clustered scattering, and hardware impairments increasingly challenge classical assumptions on channel sparsity, resolvability, and stationarity. In these regimes, performance…

Integrated sensing and communication is widely acknowledged as a foundational technology for next-generation mobile networks. Compared with monostatic sensing, multi-access point (AP) collaborative sensing endows mobile networks with…

Earth observations from low Earth orbit satellites provide vital information for decision makers to better manage time-sensitive events such as natural disasters. For the data to be most effective for first responders, low latency is…

Transfer learning techniques aim to leverage information from multiple related datasets to enhance prediction quality against a target dataset. Such methods have been adopted in the context of high-dimensional sparse regression, and some…

Human vision models are at the core of image processing. For instance, classical approaches to the problem of image quality are based on models that include knowledge about human vision. However, nowadays, deep learning approaches have…

Integrated Sensing and Communication (ISAC) is a key enabler of high speed, ultra low latency vehicular communication in 6G. ISAC leverages radar signal processing (RSP) to localize multiple unknown targets amid static clutter by jointly…