• Publications
  • Influence
ParsiNLU: A Suite of Language Understanding Challenges for Persian
TLDR
This work introduces ParsiNLU, the first benchmark in Persian language that includes a range of language understanding tasks—reading comprehension, textual entailment, and so on, and presents the first results on state-of-the-art monolingual and multilingual pre-trained language models on this benchmark and compares them with human performance.
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
TLDR
Evaluation of OpenAI's GPT models, Google-internal dense transformer architectures, and Switch-style sparse transformers on BIG-bench, across model sizes spanning millions to hundreds of billions of parameters finds that model performance and calibration both improve with scale, but are poor in absolute terms.
Fast Startup of LC VCOs Using Circuit Asymmetries
An LC VCO whose design includes deliberate circuit mismatches is presented. It is shown that such mismatches can reduce the oscillation start-up time due to a common-mode disturbance simultaneous
A Deep Learning Approach to Predict Blood Pressure from PPG Signals
TLDR
This work proposes an advanced personalized data-driven approach that uses a three-layer deep neural network to estimate BP based on PPG signals, outperforming prior works.
Personalized Stress Monitoring using Wearable Sensors in Everyday Settings
TLDR
This study captures the stress levels of fourteen volunteers through self-reported questionnaires, and explored binary stress detection based on HR and HRV using Machine Learning methods, which observe promising preliminary results given that the dataset is collected in the challenging environments of everyday settings.
Data Collection and Labeling of Real-Time IoT-Enabled Bio-Signals in Everyday Settings for Mental Health Improvement
TLDR
A system for the real-time collection and analysis of photoplethysmogram, acceleration, gyroscope, and gravity data from a wearable sensor, as well as self-reported stress labels based on Ecological Momentary Assessment (EMA), and a dataset to extract statistics of users’ response to queries.