Hi, I'm Jintang Xue

Final-year Ph.D. Candidate at USC Viterbi (ECE)

I'm a final-year Ph.D. Candidate at USC Viterbi (ECE) in the Media Communication Lab, advised by Prof. C.-C. Jay Kuo. My research focuses on multimodal foundation models — bridging large language models with 3D scene understanding, multimodal reasoning, and structured semantic representation. I'm currently on the academic and industry job market for 2026.

Research

Large Language Models

Reasoning, generation, and grounding of foundation language models.

Multimodal Learning

Bridging language with vision and 3D scenes through joint representations.

3D Understanding

Point cloud reasoning, scene segmentation, and language-conditioned 3D analysis.

Natural Language Processing

Word embeddings, fairness in dialogue systems, and efficient feature selection.

Education

  1. 2023 - present

    Ph.D. in Electrical and Computer Engineering

    University of Southern California , Los Angeles, CA

    Advised by Prof. C.-C. Jay Kuo Media Communication Lab

  2. 2021 - 2023

    M.S. in Electrical and Computer Engineering

    University of Southern California , Los Angeles, CA

  3. 2017 - 2021

    B.S. in Communication Engineering

    Shanghai University , Shanghai, China

Publications

Descrip3D: Enhancing Large Language Model-based 3D Scene Understanding with Object-Level Text Descriptions

Jintang Xue, Ganning Zhao, Jie-En Yao, Hong-En Chen, Yue Hu, Meida Chen, Suya You, C.-C. Jay Kuo

WACV • 2026

Injecting object-level text descriptions into LLMs significantly improves 3D scene understanding — without retraining the visual backbone.

Code

Bias and Fairness in Chatbots: An Overview

Jintang Xue, Yun-Cheng Wang, Chengwei Wei, Xiaofeng Liu, Jonghye Woo, C.-C. Jay Kuo

APSIPA Transactions on Signal and Information Processing • 2024

A comprehensive survey of bias and fairness challenges across modern chatbot systems.

Word Embedding Dimension Reduction via Weakly-Supervised Feature Selection

Jintang Xue, Yun-Cheng Wang, Chengwei Wei, C.-C. Jay Kuo

APSIPA Transactions on Signal and Information Processing • 2024

Weakly-supervised feature selection compresses word embeddings while preserving their semantic structure.

Code

A Tiny Machine Learning Model for Point Cloud Object Classification

Min Zhang*, Jintang Xue*, Pranav Kadam, Hardik Prajapati, Shan Liu, C.-C. Jay Kuo

APSIPA Transactions on Signal and Information Processing • 2023

A lightweight, feed-forward model for point cloud classification, designed for resource-constrained devices. (* equal contribution)

Code

An Overview on Generative AI at Scale with Edge-Cloud Computing

Yun-Cheng Wang, Jintang Xue, Chengwei Wei, C.-C. Jay Kuo

IEEE Open Journal of the Communications Society • 2023

Survey of large-scale generative AI under edge-cloud computing constraints.

S3I-PointHop: SO(3)-Invariant PointHop for 3D Point Cloud Classification

Pranav Kadam, Hardik Prajapati, Min Zhang, Jintang Xue, Shan Liu, C.-C. Jay Kuo

ICASSP • 2023

For a complete publication list, see Google Scholar .