Biography

I am a postdoctoral researcher at Tsinghua University (2023-), working with Prof. Wenwu Zhu and Prof. Xin Wang at the Department of Computer Science and Technology. I am a visiting student at Simon Fraser University (2021.7-2022.7), working with Prof. Jiangchuan Liu at the School of Computer Science. I received my Ph.D. from Beijing University of Posts and Telecommunications (2018-2023), supervised by Prof. Jianxin Liao, Prof. Jingyu Wang and Prof. Qi Qi at the State Key Laboratory of Networking and Switching Technology, School of Computer and Science. My recent research interests include Embodied AI, Multimodal World Model, and Low-altitude Intelligence.

News

  • [07-2026] ACM MM: One Paper accepted, thanks to all co-authors!
  • [05-2026] Springer: One book accepted, thanks to all co-authors!
  • [05-2026] TMLR: One paper accepted, thanks to all co-authors!
  • [02-2026] CVPR: One paper accepted, thanks to all co-authors!
  • [01-2026] AAAI: One paper accepted, thanks to all co-authors!
  • [01-2026] IEEE CASM: One paper accepted, thanks to all co-authors!
  • [07-2025] ACM MM: One paper accepted, thanks to all co-authors!
  • [05-2025] ESWA: One paper accepted, thanks to all co-authors!
  • [02-2025] AAAI: One paper accepted, thanks to all co-authors!
  • [10-2024] ACM MM: Best Paper Nomination, thanks to all co-authors!
  • [07-2024] ACM MM: Three papers accepted, thanks to all co-authors!
  • [Before 2024] IEEE TMM: Two paper accepted, thanks to all co-authors!

Selected Publications

Self-evolving Embodied AI
Tongtong Feng, Xin Wang, Wenwu Zhu
Nature Science Review (NSR, 中科院一区top, IF=18.1), 2026.

EvolvingAgent: Curriculum Self-evolving Agent with Continual World Model for Long-Horizon Tasks
Tongtong Feng, Xin Wang, Zekai Zhou, Ren Wang, Yuwei Zhan, Guangyao Li, Qing Li, Wenwu Zhu
IEEE Transactions on Multimedia (TMM, CCF-A), 2026.

Physics Attention: A Physics-Learned Generative World Model for Fluid
Jinghao Cui, Xin Wang, Tongtong Feng*, Yong Rui, Wenwu Zhu
The 34th ACM International Conference on Multimedia (ACM MM, CCF-A), 2026.

ModularAgent: A Task-Aware Modular Framework for Joint Optimization of Multimodal Large Language Models and World Models
Yu-Wei Zhan, Xin Wang, Pengzhe Mao, Tongtong Feng*, Ren Wang, Wenwu Zhu
The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR, CCF-A), 2026.

Autonomous Embodied AI: Towards Self-evolving Intelligence
Xin Wang, Tongtong Feng, Huaping Liu, Wenwu Zhu
Springer Nature, ISBN: 978-9-819-57749-1, 2026.

U2UData+: A Scalable Swarm UAVs Autonomous Flight Dataset for Embodied Long-horizon Tasks
Tongtong Feng, Xin Wang, Feiling Han, Leping Zhang, Wenwu Zhu
The 40th Annual AAAI Conference on Artificial Intelligence (AAAI, CCF-A), 2026.

Embodied AI: From LLMs to World Models [feature]
Tongtong Feng, Xin Wang, Yu-Gang Jiang, Wenwu Zhu
IEEE Circuits and Systems Magazine (IEEE CASM, 中科院二区), 2025.

TCDformer-based Momentum Transfer Model for Long-term Sports Prediction
Hui Liu, Xiyuan Huang, Jiacheng Gu, Junjie Shi, Ning He, Tongtong Feng*
Expert Systems with Applications (ESWA, 中科院一区top), 2025.

Improving Compositional Generalization in Cross-Embodiment Learning via Mixture of Disentangled Prototypes
Ren Wang, Xin Wang, Tongtong Feng, Xinyue Gong, Guangyao Li, Yu-Wei Zhan, Qing Li, Wenwu Zhu
ACM International Conference on Multimedia (ACM MM, CCF-A), 2025.

JAQ: Joint Efficient Architecture Design and Low-Bit Quantization with Hardware-Software Co-Exploration
Mingzi Wang, Yuan Meng, Chen Tang, Weixiang Zhang, Yijian Qin, Yang Yao, Yingxin Li, Tongtong Feng, Xin Wang, Xun Guan, Zhi Wang, Wenwu Zhu
The 39th Annual AAAI Conference on Artificial Intelligence (AAAI, CCF-A), 2025.

U2UData: A Large-scale Cooperative Perception Dataset for Swarm UAVs Autonomous Flight
Tongtong Feng, Xin Wang, Feilin Han, Leping Zhang, Wenwu Zhu
ACM International Conference on Multimedia (ACM MM, CCF-A), 2024. Oral , Best Paper Nomination

Multi-weather Cross-view Geo-localization Using Denoising Diffusion Models
Tongtong Feng, Qing Li, Xin Wang, Mingzi Wang, Guangyao Li, Wenwu Zhu
ACM International Conference on Multimedia (ACM MM Workshop), 2024.

Timely and accurate bitrate switching in HTTP adaptive streaming with date-driven I-frame prediction
Tongtong Feng, Qi Qi, Jingyu Wang, Jianxin Liao, Jiangchuan Liu
IEEE Transaction on Multimedia (TMM, CCF-A), 2023.

Vabis: Video adaptation bitrate system for time-critical live streaming
Tongtong Feng, Haifeng Sun, Qi Qi, Jingyu Wang, Jianxin Liao
IEEE Transactions on Multimedia (TMM, CCF-A), 2020.

Projects

Multi-modal UAV simulation scenes and environmental attributes
02 · AerialDoJo Project

AerialDoJo: Open-world Aerial Object-Goal Search

Aerial agents autonomously search for objects by goal-driven exploration in open-world environments, where agents operate based on high-level semantic goals without relying on detailed instructional guidance.

Simulator DataSet Tasks Benchmark
Explore AerialDoJo ↗

Service

    Area Chair:
    • International Conference on Learning Representations Workshop (ICLR Workshop) 2025
    Conference Reviewer:
    • ACM International Conference on Multimedia (ACMMM) 2024-
    • Annual Conference on Neural Information Processing Systems (NeurIPS) 2024-
    • International Conference on Machine Learning (ICML) 2025-
    • International Conference on Learning Representations (ICLR) 2025-
    • The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2025-
    • The Association for the Advancement of Artificial Intelligence (AAAI) 2025-
    • IEEE International Conference on Multimedia & Expo (ICME) 2022-
    Journal Reviewer:
    • IEEE Transactions on Multimedia (TMM)
    • IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
    • ACM Transactions on Multimedia Computing Communications and Applications (TOMM)
    • IEEE Transactions on Network and Service Management (TNSM)
    • IEEE Transactions on Cognitive Communications and Networking (TCCN)

Contact

Email: fengtongtong@tsinghua.edu.cn
Address: FiT Building 4-305, Tsinghua University, Beijing, China
Post Code: 100084