Neural signals provide key information for decision-making processes in multiple disciplines including medicine, engineering, and neuroscience. The correct interpretation of these signals, however, requires substantial processing, especially when the signals exhibit low Signal to Noise Ratio (SNR). Electroencephalographic (EEG) signals are considered among this group and require effective handling of multiple types of artifactual components. Unfortunately, most available de-noising tools are suitable only for offline signal processing. For some artifacts (e.g., EEG motion artifacts), no established method of effective denoising exists for offline or real-time applications. Thus, there is a critical need for methods that can handle artifacts in neural signals with high performance, reliability and real-time capability. Here, we propose novel methods for handling some of the most challenging artifacts that exhibit highly complex dynamics, including motion artifacts. Having the same core sample-adaptive processing tool used for handling different types of artifacts, we present our efforts towards a unified framework for neural data artifact denoising with real-time compatibility.