Yuetian's Projects
Age and gender recognition using arcface and MLP.
This is a final project for RPI CSCI 4963. We introduce a TCP-based end-to-end Draw and Guess Demo using Java. All UI components are implemented using Java Swing
This is an archive of image recognition and classification tasks from 2018
This project (https://doi.org/10.1145/3512452.3512455) investigates and summarizes the superiority and limitations of different dimensionality reduction schemes as well as classification methods in specific single-cell RNA sequencing (scRNA-seq) data sets.
Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
The pytorch implementation for our paper "Enhancing Sentiment Analysis Results through Outlier Detection Optimization"
Prompt tuning toolkit for GPT-2 and GPT-Neo - Forked for adding modification
Privacy Meter: An open-source library to audit data privacy in statistical and machine learning algorithms.
:fire: OpenPose api wrapper in PyTorch, but optimized for a better performance!
[CVPR 2023] Official Pytorch code for PROB: Probabilistic Objectness for Open World Object Detection
We explores humor generation using GPT-3 by modeling human comedy writing theory and leveraging step-by-step thinking instructions. In addition, we explore the role of cognitive distance in creating humor. Our findings suggest that GPT-3's ability to generate humor can be significantly improved by theory-driven step-by-step thinking instructions.
Reflections & Resonance: Two-Agent Partnership for Advancing LLM-based Story Annotation (COLING 2024)
Temporal Difference Variational Auto-Encoder (TD-VAE) (Implementation in PyTorch)
[ICASSP 2023] Official Tensorflow implementation of "Temporal Modeling Matters: A Novel Temporal Emotional Modeling Approach for Speech Emotion Recognition".
UNION: An Unreferenced Metric for Evaluating Open-ended Story Generation
We designed an end-to-end framework that encourage interactive narrative experience based on keyword control and image generation.