Zilong Chen's CV

• Phone: +86 186 2945 1544
• Email: jaysonabcchen@gmail.com
• Location: Tsinghua University, Beijing, China
• Website: heheyas.github.io
• LinkedIn: zilong-chen-99671523b
• GitHub: heheyas
• Google Scholar: 2pbka1gAAAAJ

Summary

I am interested in multimodal generation. Previously, my primary research focused on 3D reconstruction and generation. I am a Ph.D student at Department of Computer Science and Technology, Tsinghua University, where I am advised by Prof. Huaping Liu. Before joining Tsinghua University, I completed my undergraduate studies at Xi'an Jiaotong University under the supervision of Prof. Minnan Luo, focusing on knowledge graphs and their applications in natural language processing.

Education

Tsinghua University, PhD in Computer Science

• Sept 2022 – present
• Advisor: Huaping Liu

Xi'an Jiaotong University, BS in Physics

• Sept 2018 – July 2022
• Advisor: Minnan Luo

Experience

Shengshu Inc., Research intern on video and 3D generation

• Nov 2023 – Mar 2025
• Beijing, China
• Alleviating Janus problem in optimization-based 3D generation methods. (CVPR 2024 [3])
• Finetune video diffusion model for 3D generation.
• Native 3D generation using limited 3D data. (CVPR 2025 Highlight [1])

Publications (= Indicates Equal Contribution)

[1] MeshGen: Generating PBR Textured Mesh with Render-Enhanced Auto-Encoder and Generative Data Augmentation (https://heheyas.github.io/MeshGen)

• CVPR 2025 (Highlight)
• #underline[Zilong Chen], Yikai Wang, Wenqiang Sun, Feng Wang, Yiwen Chen, Huaping Liu

[2] V3d: Video diffusion models are effective 3d generators (https://heheyas.github.io/V3D)

• Submitted to T-PAMI 2024
• #underline[Zilong Chen], Yikai Wang, Feng Wang, Zhengyi Wang, Huaping Liu

[3] Text-to-3d using gaussian splatting (https://gsgen3d.github.io/)

• CVPR 2024
• #underline[Zilong Chen], Feng Wang, Yikai Wang, Huaping Liu

[4] Gaussianeditor: Swift and controllable 3d editing with gaussian splatting (https://buaacyw.github.io/gaussian-editor/)

• CVPR 2024
• Yiwen Chen=, #underline[Zilong Chen]=, Chi Zhang, Feng Wang, Xiaofeng Yang, Yikai Wang, Zhongang Cai, Lei Yang, Huaping Liu, Guosheng Lin

[5] Masked space-time hash encoding for efficient dynamic scene reconstruction (https://masked-spacetime-hashing.github.io/)

• NeurIPS 2023 (Spotlight)
• Feng Wang=, #underline[Zilong Chen]=, Guokang Wang, Yafei Song, Huaping Liu

[6] Video4DGen: Enhancing Video and 4D Generation through Mutual Optimization (https://vidu4d-dgs.github.io/)

• T-PAMI 2025
• Yikai Wang, Guangce Liu, Xinzhou Wang, #underline[Zilong Chen], Jiafang Li, Xin Liang, Fuchun Sun, Jun Zhu

[7] Vidu4d: Single generated video to high-fidelity 4d reconstruction with dynamic gaussian surfels (https://vidu4d-dgs.github.io/)

• NeurIPS 2024
• Yikai Wang, Xinzhou Wang, #underline[Zilong Chen], Zhengyi Wang, Fuchun Sun, Jun Zhu

[8] Meshanything v2: Artist-created mesh generation with adjacent mesh tokenization (https://buaacyw.github.io/meshanything-v2/)

• arxiv 2024
• Yiwen Chen, Yikai Wang, Yihao Luo, Zhengyi Wang, #underline[Zilong Chen], Jun Zhu, Chi Zhang, Guosheng Lin

[9] Dimensionx: Create any 3d and 4d scenes from a single image with controllable video diffusion (https://chenshuo20.github.io/DimensionX/)

• arxiv 2024
• Wenqiang Sun, Shuo Chen, Fangfu Liu, #underline[Zilong Chen], Yueqi Duan, Jun Zhang, Yikai Wang

[10] Freeplane: Unlocking Free Lunch in Triplane-Based Sparse-View Reconstruction Models (https://freeplane3d.github.io/)

• arxiv 2024
• Wenqiang Sun, Zhengyi Wang, Shuo Chen, Yikai Wang, #underline[Zilong Chen], Jun Zhu, Jun Zhang

[11] Twibot-22: Towards graph-based twitter bot detection

• NeurIPS 2022
• Shangbin Feng=, Zhaoxuan Tan=, Herun Wan=, Ningnan Wang=, #underline[Zilong Chen]=, Binchi Zhang=, Qinghua Zheng, Wenqian Zhang, Zhenyu Lei, Shujie Yang, others

[12] Knowledge graph augmented political perspective detection in news media

• arxiv 2021
• Shangbin Feng, #underline[Zilong Chen], Qingyao Li, Minnan Luo

[13] Encoding heterogeneous social and political context for entity stance prediction

• arxiv 2021
• Shangbin Feng, #underline[Zilong Chen], Peisheng Yu, Minnan Luo

[14] KCD: Knowledge walks and textual cues enhanced political perspective detection in news media

• NAACL 2022 (Oral)
• Wenqian Zhang=, Shangbin Feng=, #underline[Zilong Chen]=, Zhenyu Lei, Jundong Li, Minnan Luo

[15] BIC: Twitter bot detection with text-graph interaction and semantic consistency

• ACL 2023
• Zhenyu Lei, Herun Wan, Wenqian Zhang, Shangbin Feng, #underline[Zilong Chen], Jundong Li, Qinghua Zheng, Minnan Luo

[16] KRACL: Contrastive learning with graph context modeling for sparse knowledge graph completion

• WWW 2023
• Zhaoxuan Tan, #underline[Zilong Chen], Shangbin Feng, Qingyue Zhang, Qinghua Zheng, Jundong Li, Minnan Luo

[17] Kgap: Knowledge graph augmented political perspective detection in news media

• arxiv 2021
• Shangbin Feng, #underline[Zilong Chen], Wenqian Zhang, Qingyao Li, Qinghua Zheng, Xiaojun Chang, Minnan Luo

[18] PAR: Political Actor Representation Learning with Social Context and Expert Knowledge

• EMNLP 2022
• Shangbin Feng, Zhaoxuan Tan, #underline[Zilong Chen], Ningnan Wang, Peisheng Yu, Qinghua Zheng, Xiaojun Chang, Minnan Luo

Projects

3D Gaussian Splatting

• 2024
• Implementing 3D Gaussian Splatting using pure CUDA.
• Support my own researches on 3D Gaussian Splatting related topics.

Segment Anything in NeRF

• 2024
• Extending Segment Anything to 3D scenes with NeRF and support natural language prompt with CLip-Seg.
• Using depth-based point prompt for accurate 3D point prompting.

Awards

Huiyan Scholarship (Tsinghua University)

• 2024

Track winner, BMW hackthon

• 2023

Technologies

• Languages: C++, C, CUDA, Python
• Software: Blender, LaTeX