Research
Research
Research
Research
11,565+ open-access research outputs.
Multivariate time series forecasting plays a pivotal role in numerous real-world applications, including financial analysis, energy management, and traffic planning. While Transformer-based architectu…
Large Language Models (LLMs) have rapidly improved in performance across code-related tasks, making their integration into Register Transfer Level (RTL) development increasingly attractive. Mimicking …
Cygnus X-3 is a microquasar composed of a compact object of unknown nature closely orbiting around a Wolf-Rayet star. The particularities of this source make it a unique case among microquasars. This …
We propose a novel mechanism to explain the naturally small vacuum expectation values (VEVs) of exotic multi-Higgs fields by employing non-invertible symmetries. Specifically, we introduce an $SU(2)_L…
Software stacks embedded on microcontroller-based hardware typically provide rudimentary APIs programmed in C/C++, basic connectivity and, sometimes, a firmware update mechanism. Such coarse mechanism…
Deploying Large Language Models (LLMs) on resource-constrained edge devices faces critical bottlenecks in memory bandwidth and power consumption. While ternary quantization (e.g., BitNet b1.58) signif…
Reliable celestial attitude determination is a critical requirement for autonomous spacecraft navigation, yet traditional "Lost-in-Space" (LIS) algorithms often suffer from high computational overhead…
Adversarial Training (AT) is one of the most effective methods for developing robust deep neural networks (DNNs). However, AT faces a trade-off problem between clean accuracy and adversarial robustnes…
Deploying tiny object perception on edge platforms is challenging because practical systems must satisfy both strict compute budgets and end-to-end latency constraints. A common strategy is to first s…
Unified multimodal models typically rely on pretrained vision encoders and use separate visual representations for understanding and generation, creating misalignment between the two tasks and prevent…
Large language models deployed at runtime can misbehave in ways that clean-data validation cannot anticipate: training-time backdoors lie dormant until triggered, jailbreaks subvert safety alignment, …
Naturally tiny neutrino masses can be explained by the low scale seesaw with heavy neutral lepton $N$ coupling to the neutrinophilic Higgs doublet $\Phi_\nu$, which obtains a much smaller vacuum expec…
Hierarchical Risk Parity (De Pardo) and the Schur-complement generalization of Cotton are among the most widely adopted regularised portfolio construction methods, yet both are signal-blind: they solv…
Most two-stream action recognition networks apply the same convolutional backbone to both RGB and optical flow streams, ignoring the fact that the two modalities have fundamentally different structura…
Cygnus X-3, hosting a Wolf-Rayet (WR) star whose dense wind produces various spectral lines due to photoionization by X-rays from a compact object, provides an ideal laboratory for studying wind dynam…
The quality of diabetic retinopathy (DR) screening relies on the ability to correctly grade severity; however, many deep-learning (DL) classifiers cannot be easily interpreted in the clinical context.…
Progress in vision research has been slower downstream than upstream of primary visual cortex (V1). Traditional frameworks have largely overlooked a central constraint: only a tiny fraction of retinal…
Aligned large language models (LLMs) remain vulnerable to adversarial manipulation, and their reliance on web-scale pretraining creates a subtle but consequential attack surface. We study Stealth Pret…
Accurate forecasting of electric load and renewable generation is essential for reliable and cost effective power system operations. Recent advances in transformer based and foundation machine learnin…
We study a minimal framework that naturally yields viable Dark Matter, a strong first-order electroweak phase transition and low-scale resonant leptogenesis. Augmenting the Standard Model with three h…
Free open-access publishing with Google Scholar indexing.
Submission Guide →