Joel Konitzer's repositories
content-unaware-segmentation
Unsupervised Video Summarization via Successor Embeddings
chanscope-knowledge-agents
A containerized implementation of the Knowledge Agents framework, providing a scalable three-stage pipeline for text analysis using multiple LLM providers (OpenAI, Grok, Venice). Features Docker deployment, asynchronous processing, and configurable model selection for embeddings, chunk analysis, and summarization tasks.
clip-video-encode
Easily compute clip embeddings from video frames
Bioinformatics
Pre-processing of raw data into structured and organized datasets
ccxt
A JavaScript / Python / PHP cryptocurrency trading API with support for more than 100 bitcoin/altcoin exchanges
Chanscope
Heuristic-guided learning using Uncertainty-aware Self-training with Uncertainty Sampled Training (UST).
FitBit-Data-Analysis-2020-
Data analysis process of my Fitbit data from January 2020 to July 2020.
Generative-Modeling
Experiment and showcase custom and pre-built generative models. Boto3 & ClearML SDK integrations
knowledge-agents
An advanced NLP system that leverages cloud storage and multiple LLM providers (OpenAI, Grok, Venice) to process and analyze large text datasets.
MSDS-RegisU---Year-1
Collection of selected work completed throughout the first year of graduate school.
chanscope-lambda
Highly configurable AWS Lambda to gather and preprocess 4chan data. Includes a function to create a separate rolling subset of the data post preprocessing.
simple_Hadoop_MapReduce_example
A simple example of Hadoop MapReduce in Python.