Woojeong Jin

Woojeong Jin

Senior Applied Scientist · Hippocratic AI

I am a Senior Applied Scientist at Hippocratic AI, where I build real-time voice agents for healthcare that have handled 10M+ patient calls. My work spans speech and audio LLMs: contextual speech recognition, ASR error detection and recovery, and end-to-end speech-to-response models.

I earned my Ph.D. in Computer Science from the University of Southern California, advised by Prof. Xiang Ren. My doctoral research on multimodal learning and natural language processing appeared at ACL, EMNLP, and The Web Conference.

Before my Ph.D., I received a B.S. in Electrical and Computer Engineering from Seoul National University, where I worked on graph mining with Prof. U Kang.

Interests: Speech & Audio LLMsReal-time Voice AgentsSpeech RecognitionConversational AIMultimodal Learning

Experience

Jun 2024 – Present

Senior Applied Scientist, Hippocratic AI Palo Alto, CA

Jan 2022 – Apr 2022

Research Intern, Microsoft Research Redmond, WA

Jun 2021 – Jan 2022

Research Intern, Microsoft Azure AI Redmond, WA

May 2020 – Aug 2020

Research Intern, Meta AI Menlo Park, CA

Jan 2016 – Apr 2018

Research Assistant, Data Mining Lab, Seoul National University

Jun 2014 – Aug 2014

Research Intern, Creative Innovation Center, LG Electronics

Education

Aug 2018 – May 2024

Ph.D. in Computer Science

University of Southern California, Los Angeles, CA

Feb 2017

B.S. in Electrical and Computer Engineering

Seoul National University, Seoul, Korea

Publications

2026
HARP: Agentic Hybrid Retrieval and Analysis for Long-Form Audio Chin-Jou Li, Masao Someki, Woojeong Jin, Yashish M. Siriwardena, Tanmay Laud, Shanil Puri, and Shinji Watanabe
SLT 2026
Paper
Perfecting Human–AI Interaction at Clinical Scale: Turning Production Signals into Safer, More Human Conversations Subhabrata Mukherjee, Markel Sanz Ausin, Kriti Aggarwal, Debajyoti Datta, Shanil Puri, Woojeong Jin, Tanmay Laud, and 19 othersNeha Manjunath, Jiayuan Ding, Bibek Paudel, Jan Schellenberger, Frazier Huo, Walter Shen, Nima Shirazian, Nate Potter, Sathvik Perkari, Darya Filippova, Anton Morozov, Austin Mease, Ghada Shakir, Alex Miller, Juliana Ghukasyan, Mariska Raglow-Defranco, Maggie Taylor, Herprit Mahal, and Jonathan Agnew
Technical Report
Paper
2024
WinoViz: Probing Visual Properties of Objects Under Different States Woojeong Jin, Tejas Srinivasan, Jesse Thomason, and Xiang Ren
arXiv
Paper
2023
GRILL: Grounded Vision-language Pre-training via Aligning Text and Image Regions Woojeong Jin, Subhabrata Mukherjee, Yu Cheng, Yelong Shen, Weizhu Chen, Ahmed Hassan Awadallah, Damien Jose, and Xiang Ren
arXiv
Paper
Temporal Knowledge Graph Forecasting Without Knowledge Using In-Context Learning Dong-Ho Lee, Kian Ahrabian, Woojeong Jin, Fred Morstatter, and Jay Pujara
EMNLP 2023
Paper
Analyzing Norm Violations in Real-Time Live-Streaming Chat Jihyung Moon*, Dong-Ho Lee*, Hyundong J. Cho, Woojeong Jin, Chan Young Park, Minwoo Kim, Jay Pujara, and Sungjoon Park
EMNLP 2023
Paper
Hybrid Forecasting of Geopolitical Events Daniel M. Benjamin, Fred Morstatter, Ali E. Abbas, …, Woojeong Jin, …, Michael D. Ward, and Aram GalstyanDaniel M. Benjamin, Fred Morstatter, Ali E. Abbas, Andres Abeliuk, Pavel Atanasov, Stephen Bennett, Andreas Beger, Saurabh Birari, David V. Budescu, Michele Catasta, Emilio Ferrara, Lucas Haravitch, Mark Himmelstein, KSM Tozammel Hossain, Yuzhong Huang, Woojeong Jin, Regina Joseph, Jure Leskovec, Akira Matsui, Mehrnoosh Mirtaheri, Xiang Ren, Gleb Satyukov, Rajiv Sethi, Amandeep Singh, Rok Sosic, Mark Steyvers, Pedro A. Szekely, Michael D. Ward, and Aram Galstyan
AI Magazine
Paper
2022
A Good Prompt Is Worth Millions of Parameters: Low-resource Prompt-based Learning for Vision-Language Models Woojeong Jin, Yu Cheng, Yelong Shen, Weizhu Chen, and Xiang Ren
ACL 2022
Paper Code
Leveraging Visual Knowledge in Language Tasks: An Empirical Study on Intermediate Pre-training for Cross-Modal Knowledge Transfer Woojeong Jin*, Dong-Ho Lee*, Chenguang Zhu, Jay Pujara, and Xiang Ren
ACL 2022
Paper
2021
MSD: Saliency-aware Knowledge Distillation for Multimodal Understanding Woojeong Jin, Maziar Sanjabi, Shaoliang Nie, Liang Tan, Xiang Ren, and Hamed Firooz
Findings of EMNLP 2021
Paper
ForecastQA: A Question Answering Challenge for Event Forecasting with Temporal Text Data Woojeong Jin, Rahul Khanna, Suji Kim, Dong-Ho Lee, Fred Morstatter, Aram Galstyan, and Xiang Ren
ACL 2021
Paper Website Leaderboard
Modality-specific Distillation Woojeong Jin, Maziar Sanjabi, Shaoliang Nie, Liang Tan, Xiang Ren, and Hamed Firooz
MAI @ NAACL 2021
Paper
2020
Recurrent Event Network: Autoregressive Structure Inference over Temporal Knowledge Graphs Woojeong Jin, Meng Qu, Xisen Jin, and Xiang Ren
EMNLP 2020
Paper Code
Accurate Relational Reasoning in Edge-labeled Graphs by Multi-Labeled Random Walk with Restart Jinhong Jung, Woojeong Jin, Ha-myung Park, and U Kang
World Wide Web Journal
Paper
Temporal Attribute Prediction via Joint Modeling of Multi-Relational Structure Evolution Sankalp Garg*, Navodita Sharma*, Woojeong Jin, and Xiang Ren
IJCAI 2020
Paper Code
2019
Collaborative Policy Learning for Open Knowledge Graph Reasoning Cong Fu, Tong Chen, Meng Qu, Woojeong Jin, and Xiang Ren
EMNLP 2019
Paper Code
Recurrent Event Network for Reasoning over Temporal Knowledge Graphs Woojeong Jin, Changlin Zhang, and Xiang Ren
RLGM @ ICLR 2019
Paper
Jointly Learning Explainable Rules for Recommendation with Knowledge Graph Weizhi Ma, Min Zhang, Yue Cao, Woojeong Jin, Chenyang Wang, Yiqun Liu, Shaoping Ma, and Xiang Ren
WWW 2019 18% acceptance rate
Paper Code
Supervised and Extended Restart in Random Walks for Ranking and Link Prediction in Networks Woojeong Jin, Jinhong Jung, and U Kang
PLOS ONE
Paper Website
Random Walk Based Ranking in Signed Social Networks: Model and Algorithms Jinhong Jung, Woojeong Jin, and U Kang
KAIS
Paper Website
2018
Fast and Accurate Random Walk with Restart on Dynamic Graphs with Guarantees Minji Yoon, Woojeong Jin, and U Kang
WWW 2018 14.8% acceptance rate
Paper
2016
Personalized Ranking in Signed Networks using Signed Random Walk with Restart Jinhong Jung, Woojeong Jin, Lee Sael, and U Kang
ICDM 2016 19.6% acceptance rate
Paper Supplement Website

Patents

United States
Real-time Use of Multiple Parallel Automatic Speech Recognition (ASR) Modules in a Conversational Artificial Intelligence (AI) Architecture Woojeong Jin, Subhabrata Mukherjee, Shanil Puri, Tanmay Laud, and Jan Schellenberger
Granted · Apr 2026 U.S. Patent 12,597,512 B2
Patent
Conversational Artificial Intelligence System with Contextual Speech Recognition, Domain Vocabulary, and Evaluation Model Co-inventor. Continuation of U.S. Patent 12,597,512.
Published Application · Jul 2026 US 2026/0213004 A1
Application
Dynamic Persona Switching in a Conversational Artificial Intelligence (AI) Based Agent Based on Conversation Attributes Woojeong Jin, Kriti Aggarwal, Subhabrata Mukherjee, Shanil Puri, Tanmay Laud, and Jan Schellenberger
Published Application · Oct 2026 US 2026/0321406 A1
Application
Korea
Method and Apparatus for Providing Supervised and Extended Restart in Random Walks for Ranking and Link Prediction in Networks Woojeong Jin, Jinhong Jung, and U Kang
Registered · Nov 2019 KR Patent 10-2048442
Method for Personalized Ranking in Signed Networks, Recording Medium and Device for Performing the Method Woojeong Jin, Jinhong Jung, and U Kang
Registered · Jun 2018 KR Patent 10-1866866