Ariel N. Lee, Cole Hunter, Nataniel Ruiz
arXiv preprint arxiv:2308.07317 (2023) | Models & Dataset: garage-bAInd | GitHub Repo
Our best model was the global leader in open-source SOTA LLMs at the time of writing. We release our entire dataset, fine-tuning and merging pipeline, and models to the research community.
Ariel N. Lee, Sarah Adel Bargal, Janavi Kasera, Stan Sclaroff, Kate Saenko, Nataniel Ruiz
arXiv preprint arXiv:2306.17848 (2023) - Under ReviewReleased with this paper are two new datasets: Superimposed Masked Dataset & Realistic Occlusion Dataset
8th overall (196 participants) | 1st in AI graduate course challenge (42 participants)
Used a pretrained, Self-Supervised Descriptor for Copy Detection model (ResNeXt101) to find similar, manipulated videos in a dataset of 40,000+ videos.
AI research project for predicting text prompts of generated images using an ensemble of multimodal models, including CLIP, BLIP, and ViT.
Custom, high-quality dataset of 100,000+ generated images, cleaned to have low semantic similarity.
Image prompts scraped from Midjourney discord channel
BU Wheelock Educational Policy Center: Analyzing Classroom Time
MLOps Development Team | Data & Process Engineer
Partnered with TeachForward and Wheelock Educational Policy Center to develop a feature extraction pipeline, analyzing the use of teaching time based on 10,000+ videos of classroom observations. Created a simple user interface for client using gradio and Hugging Face spaces.
Visual Odometry: Mapping Out the Camera Path
3rd in Computer Vision course challenge
Task: Estimate a camera's path by tracking relative motion between successive frames, only using OpenCV for initial feature detection and matching.
Implemented RANSAC and linear triangulation from scratch for fundamental matrix and camera pose estimation, respectively.