arXiv:2511.15083v1 Announce Type: new Abstract: Time-series anomaly detection plays a critical role in numerous real-world applications, including industrial monitoring and fault diagnosis. Recently, Mamba-based state-space models have shown remarkable efficiency in long-sequence modeling. However, directly applying Mamba to anomaly detection…
arXiv:2410.03103v4 Announce Type: replace Abstract: Fill-in-the-Middle (FIM), or infilling, has become integral to code language models, enabling generation of missing code given both left and right contexts. However, the current FIM training paradigm which performs next-token prediction (NTP) over reordered…
arXiv:2511.15112v1 Announce Type: new Abstract: The innovation of the study is that the deep learning method and sentiment analysis are integrated in traditional business model analysis and forecasting, and the research subject is TSMC for industry trend prediction of semiconductor…
arXiv:2505.05226v2 Announce Type: replace Abstract: The Combined Algorithm Selection and Hyperparameter optimization (CASH) is a challenging resource allocation problem in the field of AutoML. We propose MaxUCB, a max k-armed bandit method to trade off exploring different model classes and…
arXiv:2511.15125v1 Announce Type: new Abstract: Conventional radio frequency (RF) passive components modeling based on machine learning requires extensive electromagnetic (EM) simulations to cover geometric and frequency design spaces, creating computational bottlenecks. In this paper, we introduce an uncertainty-aware Bayesian online…
arXiv:2507.08424v3 Announce Type: replace Abstract: Random telegraph noise is a prevalent variability phenomenon in nanoelectronic devices, arising from stochastic carrier exchange at defect sites and critically impacting device reliability and performance. Conventional analysis techniques often rely on restrictive assumptions or…
arXiv:2511.15136v1 Announce Type: new Abstract: Past efforts to map the Medline database have been limited to small subsets of the available data because of the exponentially increasing memory and processing demands of existing algorithms. We designed a novel algorithm for…
arXiv:2511.15137v1 Announce Type: new Abstract: The reasoning capabilities of large language models (LLMs) have been significantly improved through reinforcement learning (RL). Nevertheless, LLMs still struggle to consistently verify their own reasoning traces. This raises the research question of how to…
arXiv:2511.06157v2 Announce Type: replace Abstract: A promising alternative to the computationally expensive Neural Architecture Search (NAS) involves the development of Zero Cost Proxies (ZCPs), which correlate well with trained performance, but can be computed through a single forward/backward pass on…
arXiv:2511.15138v1 Announce Type: new Abstract: Deep learning models perform best with abundant, high-quality labels, yet such conditions are rarely achievable in EEG-based emotion recognition. Electroencephalogram (EEG) signals are easily corrupted by artifacts and individual variability, while emotional labels often stem…
