Related papers: Sdft: A PDG-based Summarization for Efficient Dyna…
Knowledge distillation has become increasingly important in model compression. It boosts the performance of a miniaturized student network with the supervision of the output distribution and feature maps from a sophisticated teacher…
Spiking Neural Networks (SNNs) present a more energy-efficient alternative to Artificial Neural Networks (ANNs) by harnessing spatio-temporal dynamics and event-driven spikes. Effective utilization of temporal information is crucial for…
The identification of deterministic finite automata (DFAs) from labeled examples is a cornerstone of automata learning, yet traditional methods focus on learning monolithic DFAs, which often yield a large DFA lacking simplicity and…
Context: There is an increase in the investment and development of data-intensive (DI) solutions, systems that manage large amounts of data. Without careful management, this growing investment will also grow associated technical debt (TD).…
Diffusion Transformer (DiT), an emerging diffusion model for visual generation, has demonstrated superior performance but suffers from substantial computational costs. Our investigations reveal that these costs primarily stem from the…
Fine-tuning plays a crucial role in adapting models to downstream tasks with minimal training efforts. However, the rapidly increasing size of foundation models poses a daunting challenge for accommodating foundation model fine-tuning in…
Wireless digital twins can be leveraged to provide site-specific synthetic channel information through precise physical modeling and signal propagation simulations. This can help reduce the overhead of channel state information (CSI)…
Digital twin (DT) offers significant opportunities for enhancing facility management (FM) in campus environments. However, existing research often focuses narrowly on isolated domains, such as point-cloud geometry or energy analytics,…
Supervised fine-tuning (SFT) has become a crucial step for aligning pretrained large language models (LLMs) using supervised datasets of input-output pairs. However, despite being supervised, SFT is inherently limited by its generative…
We propose a new method of calculating electronically excited states that combines a density functional theory (DFT) based ground state calculation with a linear response treatment that employs approximations used in the time-dependent…
Scan-based Design-for-Testability (DFT) measures are prevalent in modern digital integrated circuits to achieve high test quality at low hardware cost. With the advent of 3D heterogeneous integration and chiplet-based systems, the role of…
The Fast Fourier Transform (FFT) is a fundamental numerical technique with widespread application in a range of scientific problems. As scientific simulations attempt to exploit exascale systems, there has been a growing demand for…
Deep learning and signal processing are closely correlated in many IoT scenarios such as anomaly detection to empower intelligence of things. Many IoT processors utilize digital signal processors (DSPs) for signal processing and build deep…
While standard computational protocols for density functional theory (DFT) have universal applicability, differences exist in code implementations. Specific applications require manual parameter optimization, whereas high-throughput…
Diffusion Transformers (DiTs) have achieved state-of-the-art performance in image and video generation, but their success comes at the cost of heavy computation. This inefficiency is largely due to the fixed tokenization process, which uses…
Modern software systems have become increasingly complex, which makes them difficult to test and validate. Detecting software partial anomalies in complex systems at runtime can assist with handling unintended software behaviors, avoiding…
Automating physical database design has remained a long-term interest in database research due to substantial performance gains afforded by optimised structures. Despite significant progress, a majority of today's commercial solutions are…
Background: Debugging is a key task during the software development cycle. Spectrum-based Fault Localization (SFL) is a promising technique to improve and automate debugging. SFL techniques use control-flow spectra to pinpoint the most…
Existing tracking algorithms typically rely on low-frame-rate RGB cameras coupled with computationally intensive deep neural network architectures to achieve effective tracking. However, such frame-based methods inherently face challenges…
Timing side-channel attacks exploit variations in program execution time to recover sensitive information. Cryptographic implementations are especially vulnerable to these attacks, since even small timing differences in operations such as…