pottrait

Zhiwen ("Aaron") Fan

Texas A&M University

About Me

I am an Assistant Professor in the Department of Electrical and Computer Engineering at Texas A&M University.
I'm recruiting ENERGETIC students (regardless of research background) for Fall 2026 PhD cycles and US-based internship opportunities. Please email me your resume along with a one-page research plan to apply.

Recent News

  • (2025): Accepted papers include 2 at ICLR, 2 at CVPR, 2 at ICCV, and 2 at NeurIPS.
  • Our paper VLM-3R received the Best Paper Award at ACM MM 2025’s Multimodal Foundation Models for Spatial Intelligence Workshop.
  • We won 3rd place in the ICCV 2025 COGS Challenge for Compact 3D Representation.
  • I will serve as the Area Chair for ICLR 2026.
  • Our paper VideoLifter received the Best Paper Award at CVPR 2025’s AI for Content Creation Workshop.
  • We are organizing End-to-End 3D Learning workshop at ICCV 2025.
  • I will serve as the Area Chair for NeurIPS 2025.
  • Our ICLR'25 (4K4DGen) is selected as spotlight presentation.
  • (2024): Accepted papers include 2 at CVPR, 3 at ECCV, 1 at IROS, 1 at AISTATS, and 3 at NeurIPS.
  • Our NeurIPS'24 (LightGaussian) is selected as spotlight presentation.
  • Our Symbolic Visual RL was accepted by IEEE Trans. PAMI.
  • Our IROS'24 (Multi-modal 3DGS SLAM) is selected as oral pitch finalist presentation.
  • Our CVPR'24 (Feature-3DGS) is selected as highlight presentation.
  • (2023): Accepted papers include 1 at ICLR, 1 at CVPR, 2 at ICCV, and 2 at ICCAD.
  • Our CVPR'23 (NeuralLift-360) is selected as highlight presentation.
  • (2022): Accepted papers include 1 at 3DV, 2 at CVPR, 3 at ECCV, and 2 at NeurIPS.
  • I was one of the awardees of the Qualcomm Innovation Fellowship (North America) 2022 (QIF 2022). Innovation title: "Real-time Visual Processing for Autonomous Driving via Video Transformer with Data-Model-Accelerator Tri-design".
  • We won 3rd place in the University Demo Best Demonstration at the 59th Design Automation Conference (DAC 2022). We demo for a multi-task vision transformer on FPGA.
  • Our CVPR'22 (CADTransformer) is selected as oral presentation.
  • Our paper for CVPR'20 (Cascade Cost Volume) is selected as oral presentation.

Researches Interests

My research goal is to build spatial foundations for embodied and XR intelligence by developing world modeling systems from multimodal physical data.

Research Group

PhD Students

  • Nuo Chen - PhD student, Computer Engineering.
  • Dayou Li - PhD student, Mechanical Engineering.

Visiting Students and Interns

  • Tracy Han - Research Assistant, Stanford University.
  • Xinmiao Xiong - Master Student, University of Wisconsin–Madison.
  • Lulin Liu - Senior undergraduate, University of Minnesota.
  • Zihao Zhu - Senior undergraduate, Texas A&M University.

Selected Publications
Full publication list at Google Scholar

* denotes equal contribution, † denotes project lead.

World Modeling

LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS
Zhiwen Fan*†, Kevin Wang*, Kairun Wen, Zehao Zhu, Dejia Xu, Zhangyang Wang
NeurIPS 2024 (Spotlight, top 2.1%), 3rd Place COGS 2025@ICCV
DynamicVerse: Physically-Aware Multimodal Modeling for Dynamic 4D Worlds
Kairun Wen et al., Zhiwen Fan
NeurIPS 2025
Can Test‑Time Scaling Improve World Foundation Model?
Wenyan Cong, Hanqing Zhu, Peihao Wang, Bangya Liu, Dejia Xu, Kevin Wang, David Z. Pan, Yan Wang, Zhiwen Fan, Zhangyang Wang
COLM 2025
VideoLifter: Lifting Videos to 3D with Fast Hierarchical Stereo Alignment
Wenyan Cong et al. , Zhiwen Fan
3DV 2026, CVPR 2025 AI4CC Workshop (Best Paper Award)
Cascade Cost Volume thumbnail
Cascade Cost Volume for High‑Resolution Multi‑View Stereo and Stereo Matching
Zhiwen Fan*, Xiaodong Gu*, Siyu Zhu, Zuozhuo Dai, Feitong Tan, Ping Tan
CVPR 2020 (Oral Presentation, top 5% of submissions)

Spatial VLMs

VLM-3R thumbnail
VLM‑3R: Vision‑Language Models Augmented with Instruction‑Tuned 3D Reconstruction
Zhiwen Fan et al.
ACM MM 2025 MFMSI Workshop (Best Paper Award)
Large Spatial Model: Real‑time Unposed Images to Semantic 3D
Zhiwen Fan et al., Yue Wang
NeurIPS 2024
Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields
Shijie Zhou, Haoran Chang, Sicheng Jiang, Zhiwen Fan, Zehao Zhu, Dejia Xu, Pradyumna Chari, Suya You, Zhangyang Wang, Achuta Kadambi
CVPR 2024 (Highlight, 2.8% of 11 532)

Generative Models

4K4DGen: Panoramic 4D Generation at 4K Resolution
Renjie Li, Panwang Pan, et al., Zhiwen Fan
ICLR 2025 (Spotlight, 3.2% of 11 672)
DreamScene360: Unconstrained Text‑to‑3D Scene Generation with Panoramic Gaussian Splatting
Shijie Zhou*†, Zhiwen Fan*†, Dejia Xu*, Haoran Chang, Pradyumna Chari, Tejas Bharadwaj, Suya You, Zhangyang Wang, Achuta Kadambi
ECCV 2024
Unified Implicit Neural Stylization
Zhiwen Fan*†, Yifan Jiang*, Peihao Wang*, Xinyu Gong, Dejia Xu, Zhangyang Wang
ECCV 2022

Digital Human

Expressive Gaussian Human Avatars from Monocular RGB Video
Hezhen Hu, Zhiwen Fan, Tianhao Wu, Yihan Xi, Seoyoung Lee, Georgios Pavlakos, Zhangyang Wang
NeurIPS 2024
MMHU thumbnail
MMHU: A Massive‑Scale Multimodal Benchmark for Human Behavior Understanding in Autonomous Driving
Renjie Li, Ruijie Ye, Mingyang Wu, Hao Frank Yang, Zhiwen Fan, Hezhen Hu, Zhengzhong Tu
Preprint

AI for Science

Martian World Model thumbnail
Martian World Model: Controllable Video Synthesis with Physically Accurate 3D Reconstructions
Longfei Li, Zhiwen Fan†, et al.
NeurIPS 2025
CryoFastAR: Fast Cryo-EM Ab Initio Reconstruction Made Easy
Jiakai Zhang, Shouchen Zhou, Haizhao Dai, Xinhang Liu, Peihao Wang, Zhiwen Fan, Yuan Pei, Jingyi Yu
ICCV 2025
X2‑Gaussian: 4D Radiative Gaussian Splatting for Continuous‑time Tomographic Reconstruction
Weihao Yu, Yuanhao Cai, Ruyi Zha, Zhiwen Fan, Chenxin Li, Yixuan Yuan
ICCV 2025
Joint CS‑MRI thumbnail
Joint CS‑MRI Reconstruction and Segmentation with a Unified Deep Network
Liyan Sun*, Zhiwen Fan*, Xinghao Ding, Yue Huang, John Paisley
IPMI 2019

Others

Generative AI for Autonomous Driving: Frontiers and Opportunities thumbnail
Generative AI for Autonomous Driving: Frontiers and Opportunities
GenAI4AD Survey

Invited Talks

  • Real-Time Spatial Intelligence @ Meta. June 2025.
  • Scalable 3D/4D Assets Creation @ Duke. November 2024.
  • E cient 3D Learning for Autonomous System @ UNC, Guest Lecture. November 2024.
  • Empowering Machines to Understand 3D @ Stanford, ASU, JHU, Yale. October 2024.
  • 3D Computer Vision @ TAMU, Guest Lecture. October 2024.
  • From Efficient 3D Learning to 3D Foundation Models @ UCLA and CalTech. October 2024.
  • Towards Universal, Real-Time 3D Construction and Interaction @ TAMU AI Lunch. October 2024.
  • Spatial Intelligence via Reconstruction, Distillation, and Generation @ Shanghai AI Lab. July 2024.
  • Streamlined 3D/4D: From Hours to Seconds to Millisecond @ Google Research, VALSE Webinar . May 2024.
  • Streamlined 3D/4D: From Hours to Seconds to Millisecond @ Google Research. May 2024.
  • Real-Time Few-shot View Synthesis w/ Gaussian Splatting @ IARPA WRIVA Workshop. April 2024.
  • Data-efficient and Rendering-efficient Neural Rendering @ IFML Workshop on Gen AI. November 2023.
  • Unified Implicit Neural Stylization @ Xiamen University; Kungfu.ai. July 2022.

Experience

  • Meta, Reality Lab, Burlingame:
    Research Intern (year of 2024).
  • NVIDIA Research (remote):
    Research Intern (year of 2024).
  • Google, San Francisco:
    Research Intern (year of 2022).

Services

  • Area Chairs: 
    NeurIPS, ICLR.
  • Journal Reviewers: 
    TPAMI, TIP, IJCV, Neurocomputing.
  • Conference Reviewers: 
    NeurIPS, ICLR, ICML, CVPR, ICCV, ECCV.

Student Mentoring

  • Kevin Wang (Undergraduate Student @ UT Austin → PhD Student @ UT Austin)
  • Hanxue Liang (Graduate Student @ ETH → PhD Student @ Cambridge)
  • Renjie Li (Graduate Student @ Tsinghua → PhD Student @ TAMU)
  • Chenxin Li (Graduate Student @ XMU → PhD Student @ CUHK)