About Me

I am a Member of Technical Staff at Physion Labs, working on World Critic Model. Prior to this, I was a Senior Research Scientist at Tencent Hunyuan, working on Full-Duplex Dialogue LLM.

I received my Ph.D. in Computer Science at Northeastern University. My research focuses on Video Understanding Methods to address key challenges in Video-Language Models (VLM) and Assistant AI. During my Ph.D. study, I intern at Amazon AGI, AWS and Microsoft. In the past, I also worked as a Student Researcher at Chinese Academic of Sciences.

Recent Updates

July 2026 I joined Physion Labs as Member of Technical Staff.
May 2026 My paper on Feature Space Data Augmentation is accepted at ECCV 2026.
Feb 2026 My paper on Referring Grounding LLM is accepted at CVPR 2026.
Jan 2026 I received my PhD and joined Tencent as Senior Research Scientist.
Oct 2025 My paper on Multi-modal Few-shot Learning is presented at ICCV 2025.
Apr 2025 My intern paper at Microsoft is accepted to CVPR 2025.
Apr 2024 3 papers accepted to CVPR 2024. One paper designated as "Highlight".

Selected Publications

LogFA: Feature-Space Data Augmentation in Long Egocentric Videos Using Foundation Models

Zijia Lu, Ehsan Elhamifar

ECCV 2026

Paper Code

STORM: End-to-End Referring Multi-Object Tracking in Videos

Zijia Lu, Jingru Yi, Jue Wang, Yuxiao Chen, Junwen Chen, Xinyu Li, Davide Modolo

CVPR Finding 2026

Paper Dataset

Multi-Modal Few-shot Temporal Action Segmentation

Zijia Lu, Ehsan Elhamifar

ICCV 2025

Paper Code

DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos

Zijia Lu, A S M Iftekhar, Gaurav Mittal, Tianjian Meng, Xiawei Wang, Cheng Zhao, Rohith Kukkala, Ehsan Elhamifar, Mei Chen

CVPR 2025

Project Paper Code

FACT: Frame-Action Cross-Attention Temporal Modeling for Efficient Fully-Supervised Action Segmentation

Zijia Lu, Ehsan Elhamifar

CVPR 2024

Paper Code

Error Detection in Egocentric Procedural Task Videos

Shih-Po Lee, Zijia Lu, Zekun Zhang, Minh Hoai, Ehsan Elhamifar

CVPR 2024

Paper Code & Dataset

Self-Supervised Multi-Object Tracking with Path Consistency

Zijia Lu, Bing Shuai, Yanbei Chen, Zhenlin Xu, Davide Modolo

CVPR 2024 Highlight

Paper Code

Set-Supervised Action Learning in Procedural Task Videos via Pairwise Order Consistency

Zijia Lu, Ehsan Elhamifar

CVPR 2022

Paper Code

Weakly-supervised Action Segmentation and Alignment via Transcript-Aware Union-of-subspaces Learning

Zijia Lu, Ehsan Elhamifar

ICCV 2022

Paper Code

Dft-Net: Disentanglement of Face Deformation and Texture Synthesis for Expression Editing

Jinghui Wang, Jie Zhang, Zijia Lu, Shiguang Shan

ICIP 2019

Paper

Zero-Shot Facial Expression Recognition with Multi-Label Label Propagation

Zijia Lu, Jiabei Zeng, Shiguang Shan, Xilin Chen

ACCV 2018 Oral

Paper Code & Dataset

Experience

Research Intern at Amazon AGI

06/2025 - 11/2025

Research Intern at Microsoft

06/2024 - 09/2024

Applied Scientist Intern at Amazon AWS AI Lab

09/2022 - 03/2023

Graduate Research Assistant in Northeastern University

09/2019 - Present

Student Researcher at Chinese Academy of Science

01/2018 - 12/2018

Architecture Summer Intern at NVIDIA Shanghai

06/2016 - 09/2016

B.S in Computer Science and Economics at NYU Shanghai

2014 - 2019 (Gap Year 2018)