About
12
Publications
3,133
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
77
Citations
Introduction
Additional affiliations
August 2019 - August 2022
August 2015 - May 2019
Education
August 2019 - March 2022
August 2015 - May 2019
Publications
Publications (12)
Reinforcement learning with human feedback~(RLHF) is critical for aligning Large Language Models (LLMs) with human preference. Compared to the widely studied offline version of RLHF, \emph{e.g.} direct preference optimization (DPO), recent works have shown that the online variants achieve even better alignment. However, online alignment requires on...
Accurately predicting joint torque using wearable sensors is crucial for designing assist-as-needed exoskeleton controllers to assist muscle-generated torque and ensure successful task performance. In this paper, we estimated ankle dorsiflexion/plantarflexion, knee flexion/extension, hip flexion/extension, and hip abduction/adduction torques from e...
Shift equivariance is a fundamental principle that governs how we perceive the world - our recognition of an object remains invariant with respect to shifts. Transformers have gained immense popularity due to their effectiveness in both language and vision tasks. While the self-attention operator in vision transformers (ViT) is permutation-equivari...
Automated HTML/CSS code generation from screenshots is an important yet challenging problem with broad applications in website development and design. In this paper, we present a novel vision-code transformer approach that leverages an Encoder-Decoder architecture as well as explore actor-critic fine-tuning as a method for improving upon the baseli...
Estimation of joint torque during movement provides important information in several settings, such as effect of athletes' training or of a medical intervention, or analysis of the remaining muscle strength in a wearer of an assistive device. The ability to estimate joint torque during daily activities using wearable sensors is increasingly relevan...
A leading cause of physical injury sustained by elderly persons is the event of unintentionally falling onto a hard surface. Approximately 32-42% of those 70 and over fall at least once each year, and those who live in assisted living facilities fall with greater frequency per year than those who live in residential communities. Delay between the t...
explores an RNN-based approach to online handwritten recognition problem. Our method uses data from an accelerometer and a gyroscope mounted on a handheld pen-like device to train and run a character pre-diction model. We have built a dataset of timestamped gyroscope and accelerometer data gathered during the manual process of handwriting Latin cha...
We have successfully implemented the "Learn to Pay Attention" model of attention mechanism in convolutional neural networks, and have replicated the results of the original paper in the categories of image classification and fine-grained recognition.
Even only in the US each year 10s of thousands of wildfires devastate millions of acres of land, causing major environmental damage and having annualized economic burden in tens of billions of dollars. Therefore it is necessary to be able to predict these events in order to be able to prevent or extinguish the fire in the early stages, this can be...
Cryptocurrency has become an important part of the industry. One of the major cryptocurrencies - Bitcoin has reached capitalization of over $600 billion at its peak. With millions of people trading in Bitcoin daily, the platform presents a good research opportunity. This study aims at using machine learning algorithms for predicting exchange rate s...
Abstract: The article addresses the issue of Georgian handwritten text recognition. As a result of theperformed research activity, a framework for recognizing handwritten Georgian text using Self-Normalizing Convolutional Neural Networks (CNN) was developed. To train the CNN model, an extensivedataset was created with over 200 000 character samples...