rEFIt
PulseAugur coverage of rEFIt — every cluster mentioning rEFIt across labs, papers, and developer communities, ranked by signal.
-
New methods optimize visual tokenization for large vision-language models · 4 sources tracked
Researchers have developed several new methods to optimize visual tokenization for large vision-language models (VLMs), aiming to reduce computational overhead while maintaining accuracy. MixTok introduces a hybrid appr…
-
New REFIT method calibrates wearable sensors without labels
Researchers have developed REFIT, a novel calibration technique for activity-recognition models that use wearable sensors. This method addresses issues where sensor placement shifts, such as moving a watch to a differen…
-
New REFIT method calibrates wearable sensors without labels
Researchers have developed REFIT, a novel method for calibrating activity-recognition models that use wearable sensors. This technique addresses the issue of sensor placement shifts, where a device like a smartwatch is …
-
AI system disaggregates smart meter data to identify appliance energy use
Researchers have developed a novel system to break down domestic smart meter electricity usage data into specific appliance categories. This method combines event detection for high-power appliances with questionnaire-g…
-
New NILM Method Improves Appliance Power Estimation Accuracy
Researchers have developed a novel method for non-intrusive load monitoring (NILM) that improves appliance power sequence estimation from aggregate power data. The technique, which combines label-preserving aggregate re…
-
Study reveals battery degradation costs can exceed energy savings by 1060%
A new study published on arXiv explores the hidden costs of battery degradation in home energy management systems (HEMS) that solely optimize for energy costs. Researchers used a mixed-integer linear programming model w…