Yuqiang Xie

I am a Research Scientist at Skywork AI, Kunlun Inc. Currently, I am passionate about Story-driven World Model and AI Game. I received my Ph.D. from Institute of Information Engineering (IIE), Chinese Academy of Sciences (CAS), advised by Prof. Yue Hu.

Contact: indexfziq [AT] gmail.com

Google Scholar GitHub Twitter Zhihu

Research Highlights

My research focuses on Multimodal Story Understanding & Generation and Cognitive Modeling, spanning applications in story/script/novel generation, social AI, gaming, and metaverse. My interdisciplinary interests include: (1) leveraging deep learning to investigate cognitive psychology and sociology questions; (2) applying cognitive and sociological insights to advance NLP and multimodal intelligence. My ultimate vision is to build a Ready Player One-style Metaverse — an immersive world where AI systems can understand human minds, create compelling narratives, and enable seamless human-agent interaction.

News

[3/2026] SkyReels-V4 ranks #1 globally on the Artificial Analysis Text to Video (With Audio) leaderboard.
[3/2026] Our paper on Cognitive Analysis Graph for Multi-Turn LLM Safety is accepted to ACL 2026 Findings.
[1/2026] Released SkyReels-V4: Multi-modal Video-Audio Generation, Inpainting and Editing Model.
[12/2025] Our paper on MetaGDPO for alleviating catastrophic forgetting is accepted to AAAI 2025.
[10/2025] Released SkyReels-V3 Technical Report on advanced video generation.
[5/2025] Two papers accepted to ACL 2025: Dynamic Evaluation for LLM Safety and MAGI for Psychiatric Assessment.

Selected Publications

Full list available on Google Scholar. * denotes equal contribution, † denotes corresponding author.

2026

SkyReels-V4: Multi-modal Video-Audio Generation, Inpainting and Editing Model

SkyReels Team @ Skywork AI

Technical Report, 2026

[Paper]
Cognitive Analysis Graph–Guided Multi-Turn Safety Enhancement for Large Language Models

Lanxue Zhang, Yuqiang Xie, Yanan Cao, Fang Fang, Yangxi Li

ACL 2026 Findings (CCF A)

2025

SkyReels-V3 Technical Report

SkyReels Team @ Skywork AI

Technical Report, 2025

[Paper] [Code]
Improving Narrative Video Moment Retrieval via Native Multimodality and Theory-of-Mind Reasoning

Xuanyue Zhong*, Yuqiang Xie* (equal contribution), Guanqun Bi, Junping Yang, Guibin Chen

Technical Report, 2025

[Paper]
MetaGDPO: Alleviating Catastrophic Forgetting with Metacognitive Knowledge through Group Direct Preference Optimization

Lanxue Zhang*, Yuqiang Xie* (equal contribution), Fang Fang, Fanglong Dong, Rui Liu, Yanan Cao

AAAI 2025 (CCF A)

[Paper]
Dynamic Evaluation with Cognitive Reasoning for Multi-turn Safety of Large Language Models

Lanxue Zhang, Yanan Cao, Yuqiang Xie, Fang Fang, Yangxi Li

ACL 2025 (CCF A)

[Paper] [Code]
MAGI: Multi-Agent Guided Interview for Psychiatric Assessment

Guanqun Bi, Zhuang Chen, Zhoufu Liu, Hongkai Wang, Xiyao Xiao, Yuqiang Xie, Wen Zhang, Yongkang Huang, Yuxuan Chen, Minlie Huang

ACL 2025 Findings (CCF A)

[Paper]
A Group Fairness Lens for Large Language Models

Guanqun Bi, Lei Shen, Yuqiang Xie, Yanan Cao, Tiangang Zhu, Xiaodong He

EMNLP 2025 Findings (CCF B)

[Paper]

2024

SkyScript-100M: 1,000,000,000 Pairs of Scripts and Shooting Scripts for Short Drama

Jing Tang, Quanlu Jia, Yuqiang Xie† (corresponding), Zeyu Gong, Xiang Wen, Jiayi Zhang, Yalong Guo, Guibin Chen, Jiangping Yang

Technical Report, 2024

[Paper] [Code]

2023

DiffusEmp: A Diffusion Model-Based Framework with Multi-Grained Control for Empathetic Response Generation

Guanqun Bi, Lei Shen, Yanan Cao, Meng Chen, Yuqiang Xie, Zheng Lin, Xiaodong He

ACL 2023 (CCF A, Oral)

[Paper] [Code]
Learning to Know Myself: A Coarse-to-Fine Persona-Aware Training Framework for Personalized Dialogue Generation

Yunpeng Li, Yue Hu, Yajing Sun, Luxi Xing, Ping Guo, Yuqiang Xie, Wei Peng

AAAI 2023 (CCF A)

[Paper]

2022

COMMA: Modeling Relationship among Motivations, Emotions and Actions in Language-based Human Activities

Yuqiang Xie, Yue Hu, Wei Peng, Guanqun Bi, Luxi Xing

COLING 2022 (CCF B)

[Paper] [Code]
Psychology-guided Controllable Story Generation

Yuqiang Xie, Yue Hu, Yunpeng Li, Guanqun Bi, Luxi Xing, Wei Peng

COLING 2022 (CCF B)

[Paper] [Code]
CLSEG: Contrastive Learning of Story Ending Generation

Yuqiang Xie, Yue Hu, Luxi Xing, Yunpeng Li, Wei Peng, Ping Guo

ICASSP 2022 (CCF B)

[Paper] [Code]

2021

IIE-NLP-Eyas at SemEval-2021 Task 4: Enhancing PLM for ReCAM with Special Tokens, Re-Ranking, Siamese Encoders and Back Translation

Yuqiang Xie, Luxi Xing, Wei Peng, Yue Hu

SemEval @ ACL-IJCNLP 2021 (Top 8/237 Teams)

[Paper] [Code]

Education

2017 - 2023

University of Chinese Academy of Sciences (CAS)

Institute of Information Engineering

Ph.D. in Cyberspace Security

Advisor: Prof. Yue Hu

2013 - 2017

China University of Mining and Technology (CUMT)

School of Computer Science and Technology

B.E. in Network Engineering

Work Experience

2023 - Present

Skywork AI, Kunlun Inc.

Research Scientist

• IC, AI Gaming (2023.07 - 2024.05)

• Leader, Story Foundation Model (2024.06 - 2025.05)

• IC, Video Generation Model (2025.06 - Present)

2022 - 2023

Baidu

Core Search Strategy Department

Research Intern

Scholarships & Awards

2021 CIPS-NLGIW Chinese Story Generation: 60M Track 1st Place

2020 SemEval @ COLING Commonsense Validation & Explanation: 3rd/609 Teams

2021 SemEval @ ACL-IJCNLP Reading Comprehension Abstract Summarization: 8/237 (Top 3%) Teams

2018-2019 Outstanding Student Leader, University of Chinese Academy of Sciences

2018-2019 Merit Student, University of Chinese Academy of Sciences

2017 Outstanding Graduation Project, China University of Mining and Technology

Professional Service

Reviewer / Program Committee: ACL, EMNLP, AAAI, TASLP, NLPCC (2020 - Present)

Open Source Contributions

GNN4NLP Paper List (⭐ 900+): github.com/IndexFziQ/GNN4NLP-Papers
Diffusion4NLP Paper List (⭐ 100+): github.com/IndexFziQ/Diffusion4NLP-Papers