Wenqing Wang

I am Wenqing Wang (王文青), a CS PhD candidate at Khoury College of Computer Sciences, Northeastern University. I am advised by Prof. Yun Raymond Fu (Member of the Academy of Europe, European Academy of Sciences and Arts, ACM; Fellow of UAI, AAAS, AAAI, IEEE; etc.), and I am a member of the SMILE Lab. I earned my B.S. in Computer Science and B.A. in Psychology from the University of California, Davis.

My research interests span computer vision, generative AI, and general AI. In particular, I focus on generative AI [VLMs/LLMs/VLAs, multi-modal generation, diffusion models, video and image generation/understanding, AI agents]; neural rendering [NeRF, Gaussian Splatting, 3D novel-view synthesis]; and general AI [ML/DL, brain-inspired algorithms, AGI, AI-driven longevity/health, AI-cosmology, autonomous driving]. I am always open to collaboration.

Currently seeking 2026 Spring & Summer internship opportunities.

News

Sep 21, 2025 09/21/25	BEAR: Benchmarking Multimodal Language Models for Atomic Embodied Reasoning Abilities is accepted to NeurIPS 2025 LLM Evaluation Workshop 🎉
September 15, 2025 09/15/25	Started research scientist internship at Samsung Research America 🚀
Jul 11, 2025 07/11/25	RealTalk: Realistic Emotion-Aware Lifelike Talking-Head Synthesis is accepted to ICCV 2025 Workshop on Artificial Social Intelligence 🎉
June 2, 2025 06/02/25	Started research scientist internship at Socure 🚀
Dec 7, 2024 12/07/24	Preprint of Text-to-3D Gaussian Splatting with Physics-Grounded Motion Generation is available
Oct 7, 2024 10/07/24	EmoGene: Audio-Driven Emotional 3D Talking-Head Generation is accepted to FG 2025 🎉
May 24, 2024 05/24/24	Started research scientist internship at bitHuman 🚀
Sep 1, 2022 09/01/22	Started Ph.D. at Northeastern University
Jun 10, 2022 06/10/22	Graduated from University of California, Davis

Selected Publications

DeltaGS: Ultra-Efficient 150X Compression for High-Fidelity 3D Gaussian Splatting

Wenqing Wang, Yun Fu

Under review, 2025

@misc{wang2025deltags,
                      title={DeltaGS: Ultra-Efficient 150X Compression for High-Fidelity 3D Gaussian Splatting}, 
                      author={Wenqing Wang and Yun Fu},
                      year={2025},
                }

images/publication_preview/diffphygs.png

DiffuPhyGS: Text-to-Video Generation with 3D Gaussians and Learnable Physical Properties via Diffusion Priors

Wenqing Wang, Yun Fu

Under review, 2025

@misc{wang2025diffuphygs,
                      title={DiffuPhyGS: Text-to-Video Generation with 3D Gaussians and Learnable Physical Properties via Diffusion Priors}, 
                      author={Wenqing Wang and Yun Fu},
                      year={2025},
                }

BEAR: Benchmarking and Enhancing Multimodal Language Models for Atomic Embodied Capabilities

Yu Qi, Haibo Zhao, Ziyu Guo, Siyuan Ma, Ziyan Chen, Yaokun Han, Renrui Zhang, Zitiantao Lin, Shiji Xin, Yijian Huang, Kai Cheng, Peiheng Wang, Jiazheng Liu, Jiayi Zhang, Yizhe Zhu, Wenqing Wang, Yiran Qin, Xupeng Zhu, Haojie Huang, Lawson L.S. Wong

Preprint, 2025

Pdf Cite

@misc{qi2025bearbenchmarkingenhancingmultimodal,
                      title={BEAR: Benchmarking and Enhancing Multimodal Language Models for Atomic Embodied Capabilities}, 
                      author={Yu Qi and Haibo Zhao and Ziyu Guo and Siyuan Ma and Ziyan Chen and Yaokun Han and Renrui Zhang and Zitiantao Lin and Shiji Xin and Yijian Huang and Kai Cheng and Peiheng Wang and Jiazheng Liu and Jiayi Zhang and Yizhe Zhu and Wenqing Wang and Yiran Qin and Xupeng Zhu and Haojie Huang and Lawson L. S. Wong},
                      year={2025},
                      eprint={2510.08759},
                      archivePrefix={arXiv},
                      primaryClass={cs.CV},
                      url={https://arxiv.org/abs/2510.08759}, 
                }

BEAR: Benchmarking Multimodal Language Models for Atomic Embodied Reasoning Abilities

Yu Qi, Haibo Zhao, Ziyu Guo, Siyuan Ma, Ziyan Chen, Yaokun Han, Renrui Zhang, Zitiantao Lin, Shiji Xin, Yijian Huang, Kai Cheng, Peiheng Wang, jiazheng liu, Jiayi Zhang, Yizhe Zhu, Wenqing Wang, Yiran Qin, Xupeng Zhu, Haojie Huang, Lawson L.S. Wong

NeurIPS 2025 LLM Evaluation Workshop, 2025

Pdf Cite

@inproceedings{qi2025bear,
                      title={BEAR: Benchmarking Multimodal Language Models for Atomic Embodied Reasoning Abilities},
                      author={Qi, Yu and Zhao, Haibo and Guo, Ziyu and Ma, Siyuan and Chen, Ziyan and Han, Yaokun and Zhang, Renrui and Lin, Zitiantao and Xin, Shiji and Huang, Yijian and others},
                      booktitle={NeurIPS 2025 Workshop on Evaluating the Evolving LLM Lifecycle: Benchmarks, Emergent Abilities, and Scaling}
                    }

RealTalk: Realistic Emotion-Aware Lifelike Talking-Head Synthesis

Wenqing Wang, Yun Fu

ICCV 2025 Workshop on Artificial Social Intelligence, 2025

Pdf Cite

@article{wang2025realtalk,
                      title={RealTalk: Realistic Emotion-Aware Lifelike Talking-Head Synthesis},
                      author={Wang, Wenqing and Fu, Yun},
                      journal={arXiv preprint arXiv:2508.12163},
                      year={2025}
                    }

images/publication_preview/wang2024textto3dgaussiansplattingphysicsgrounded.gif

Text-to-3D Gaussian Splatting with Physics-Grounded Motion Generation

Wenqing Wang, Yun Fu

Preprint, 2024

Pdf Cite

@article{wang2024text,
                  title={Text-to-3D Gaussian Splatting with Physics-Grounded Motion Generation},
                  author={Wang, Wenqing and Fu, Yun},
                  journal={arXiv preprint arXiv:2412.05560},
                  year={2024}
                }

images/publication_preview/wang2024audiodrivenemotional3dtalkinghead.gif

EmoGene: Audio-Driven Emotional 3D Talking-Head Generation

Wenqing Wang, Yun Fu

2025 IEEE 19th International Conference on Automatic Face and Gesture Recognition (FG)

Pdf Cite Project

@INPROCEEDINGS{11099460,
                author={Wang, Wenqing and Fu, Yun},
                booktitle={2025 IEEE 19th International Conference on Automatic Face and Gesture Recognition (FG)}, 
                title={EmoGene: Audio-Driven Emotional 3D Talking-Head Generation}, 
                year={2025},
                volume={},
                number={},
                pages={1-10},
                keywords={Deformable models;Accuracy;Three-dimensional displays;Lips;Gesture recognition;Sampling methods;Neural radiance field;Rendering (computer graphics);Synchronization;Videos},
                doi={10.1109/FG61629.2025.11099460}}

Experience

Sep. 2025 - Present

Research Scientist Intern

Samsung Research America, Inc.

Topics: Camera/motion controllable video generation using diffusion transformer (DiT).

Jun. 2025 - Aug. 2025

Research Scientist Intern

Socure, Inc.

Topics: Realistic ID image generation using multi-modal DiT model for ID fraud prevention.

May 2024 - Aug. 2024

Research Scientist Intern

bitHuman, Inc.

Topics: NeRF-based realistic audio‑driven 3D emotional talking‑head generation.

Sep. 2023 - May 2024

Research Assistant

Northeastern University

PhD Advisor: Prof. Yun Raymond Fu

Jun. 2019 - Jun. 2022

Research Assistant

University of California, Davis

Advisors: Prof. George Mangun, Prof. Andrew Fox, Prof. Jeffrey Schank

Grants

ICCV Travel Grant, 2025

FG PhD Doctoral Consortium Travel Grant, 2025

Teaching

Courses TA'd: CS5100 Foundations of Artificial Intelligence; CS5150/4150 Game Artificial Intelligence; CS5340: Computer/Human Interaction; CS3200: Intro to Database Systems

Academic Services

Conference Reviewer: CVPR, ICCV, ICLR, NeurIPS, MM, FG

Journal Reviewer: Neural Computing and Applications, TPAMI, TKDD, Neural networks, IEEE TNNLS, Knowledge‑Based Systems, AI Reviews, Multimedia Tools and Applications