Spoiler Detection as Semantic Text Matching
Ryan Tran, Canwen Xu, Julian McAuley
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Ryan Tran
Brief Biography
I am a lead software engineer at Neutralino Space Ventures. I earned my master's degree in Computer Science and Engineering from UC San Diego and my bachelor's degree in Electrical Engineering and Computer Sciences from UC Berkeley. I enjoy applying machine learning solutions to problems in the fields of computer vision and natural language understanding.
News
[September 2023] Beginning new full-time software engineer position at Neutralino Space Ventures.
[March 2023] Graduated with my M.S. degree in Computer Science and Engineering from UC San Diego.
[March 2023] Published my master's thesis on Spoiler Recognition as Semantic Text Matching to EMNLP 2023.
[March 2023] Published "Fast Object Detection in High-Resolution Videos" to ICCV 2023 workshop on Resource Efficient Deep Learning for CV together with my team at percipient.ai.
[January 2022] Returning to percipient.ai to begin a part-time internship concurrent with my graduate studies.
[December 2021] Our paper "Conditional Synthetic Data Generation for Robust Machine Learning Applications with Limited Pandemic Data" is accepted to AAAI 2022.
[December 2021] Published the open-source package sortinghatinf, a Python library that uses machine learning to infer the feature types of the columns of a Pandas dataframe.
[September 2021] Starting my master's degree in computer science at UC San Diego.
[July 2021] Our paper "CDCGen: Cross-Domain Conditional Generation via Normalizing Flows and Adversarial Training" is accepted for a Spotlight Talk at Workshop on Machine Learning for Data: Automated Creation, Privacy, Bias at the International Conference on Machine Learning (ICML) 2021.
[July 2021] Our paper "CDCGen: Cross-Domain Conditional Generation via Normalizing Flows and Adversarial Training" is accepted for an Oral Presentation at Workshop on Data-Efficient Machine Learning (DeMaL) at KDD 2021.
[May 2021] Returning to percipient.ai to begin a machine learning research internship for the summer.
[May 2021] Graduated with my B.S. degree in Electrical Engineering and Computer Sciences from UC Berkeley.
[April 2021] Our paper "Conditional Synthetic Data Generation for Robust Machine Learning Applications with Limited Pandemic Data" is accepted at ICLR 2021 workshop on Machine Learning for Preventing and Combating Pandemics.
[May 2020] Starting a machine learning research internship at percipient.ai for the summer.
[May 2019] Starting a machine learning research internship at NASA JPL for the summer.
Publications
Fast Object Detection in High-Resolution Videos
Ryan Tran, Atul Kanaujia, Vasu Parameswaran
2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)
Conditional Synthetic Data Generation for Robust Machine Learning Applications with Limited Pandemic Data
Hari Prasanna Das, Ryan Tran, Japjot Singh, Xiangyu Yue, Geoffrey Tison, Alberto Sangiovanni-Vincentelli, and Costas J. Spanos
Proceedings of the AAAI Conference on Artificial Intelligence 2022
CDCGen: Cross-Domain Conditional Generation via Normalizing Flows and Adversarial Training
Hari Prasanna Das, Ryan Tran, Japjot Singh, Yu-Wen Lin, and Costas J. Spanos
Workshop on Machine Learning for Data: Automated Creation, Privacy, Bias; International Conference on Machine Learning (ICML) 2021
Workshop on Data-Efficient Machine Learning (DeMaL); Conference on Knowledge Discovery and Data Mining (KDD) 2021
Projects
sortinghatinf: Python library that uses machine learning to infer the feature types of the columns of a Pandas dataframe. See Project SortingHat for more details.
NotaryBot: AWS cloud-native bot that automates subscribing to events based on time, distance, and monetary constraints queried from Google Cloud APIs.