ZIMO WEN

Biography

I am an undergraduate researcher in Computer Science at Shanghai Jiao Tong University, in the Zhiyuan Honors Program and MVIG Lab, advised by Professors Cewu Lu and Chuan Wen. My research interests span embodied intelligence, agentic systems, and multimodal models, with a focus on robot self-improvement, unified visual understanding and generation, and efficient learning systems.

News

• 2026/09SenseNova-U1.5 technical report is now available.
• 2026/09RoboRSI research report and project demos are now available.
• 2026/08Argus preprint is available on arXiv.
• 2026/07Mage-Flow preprint is available on arXiv.
• 2026/06RESOURCE2SKILL preprint is available on arXiv.
• 2026/03UniG2U-Bench preprint is available on arXiv.

Selected Projects

Agentic Systems3›

Project video

Argus: A General-Purpose Agentic Reasoning Runtime for Long-Horizon Tasks

Boxiu Li^*, Zimo Wen^*, Yijia Fan^*, Chuan Wen, Fan Yang, Hangxi Guo, Jiaao Wu, Jiachen Zhang, Junxiang Lei, Mukai Li, Ruize Tang, Runjing Gu, Shibo Hu, Sihan Chen, Sufeng Guo, Wanbo Zhang, Xian Zhang, Xiaoyu Chen, Xuanhe Zhou, Xuyao Huang, Yifei Gao, Yifei Shen, Yilin Chen, Yuheng Wu, Yuzhe Zhang, Zelong Zhao, Zhijie Deng (* equal contribution)

Agentic systemsarXiv 2026

PaperWebsiteCodeVideoScholar

Project video

RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources

Yijia Fan^*, Zonglin Di^*, Zimo Wen^*, Yifan Yang, Mingxi Cheng, Qi Dai, Bei Liu, Kai Qiu, Yue Dong, Ji Li, Chong Luo (* equal contribution)

Skill learningarXiv 2026

PaperWebsiteCodeVideoScholar

Tri-MARF: A Tri-Modal Multi-Agent Responsive Framework for Comprehensive 3D Object Annotation

Jusheng Zhang^*, Yijia Fan^*, Zimo Wen^*, Jian Wang, Keze Wang (* equal contribution)

3D annotationNeurIPS 2025

PaperWebsiteScholar

Robotics2›

RoboRSI · project demonstration

RoboRSI: Stable, Efficient, and Reusable Robot Self-Evolution

Noematrix Team

Robot self-improvementResearch Report · 2026

ReportWebsiteCode

LIFT · towel folding

Never Too Late for Force: Accelerating VLA Post-Training with Reactive Force Injection

Yi Wang^*, Wendi Chen^*, Zimo Wen^*, Han Xue, Xueqi Li, Wenye Yu, Zhijie Chen, Hao Yang, Jun Lv, Chuan Wen, Cewu Lu (* equal contribution)

Robot learningCoRL 2026

PaperWebsiteScholar

Multimodal Learning1›

UniG2U-Bench: Do Unified Models Advance Multimodal Understanding?

Zimo Wen, Boxiu Li, Wanbo Zhang, Junxiang Lei, Xiaoyu Chen, Yijia Fan, Qi Zhang, Yujiang Wang, Lili Qiu, Bo Li, Ziwei Liu, Caihua Shan, Yifan Yang, Yifei Shen

Multimodal evaluationarXiv 2026

PaperWebsiteCodeScholar

Time Series & Dynamics3›

DANet: A RAG-Inspired Dual Attention Model for Few-Shot Time Series Prediction

Zimo Wen, Hanwen Hu, Nan Fang, Shiyou Qian, Jian Cao

Time-series predictionCIKM 2025

PaperCodeScholar

PI-GNN: A Physics-Informed Graph Neural Network for Spatio-Temporal Diffusion Prediction

Zimo Wen, Cheng Zeng, Hanwen Hu, Shiyou Qian, Jian Cao

Physics-informed learningICASSP 2026

PaperScholar

PAST: A Primary-Auxiliary Spatio-Temporal Network for Traffic Time Series Imputation

Hanwen Hu, Zimo Wen, Shiyou Qian, Jian Co

Time-series imputationarXiv 2025

PaperCodeScholar

Technical Reports2›

Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing

Xinjie Zhang, Peng Zhang, Shicheng Zheng, Jinghao Guo, Zhaoyang Jia, Yifei Shen, Xun Guo, Yuxuan Luo, Jiahao Li, Wenxuan Xie, Fanyi Pu, Xiaoyi Zhang, Kaichen Zhang, Zongyu Guo, Tianci Bi, Dongnan Gui, Zhening Liu, Zimo Wen, Zihan Zheng, Senqiao Yang, Xiao Li, Jinglu Wang, Bin Li, Yan Lu

Image generationTechnical Report · 2026

PaperWebsiteCodeScholar

SenseNova-U1.5: Towards Native Unified Visual Intelligence

Haiwen Diao, Jiahao Wang, Chenjing Ding, …, Zimo Wen, …, Dahua Lin

Unified visual intelligenceTechnical Report · 2026

PaperWebsiteCode

No publications match your search. Try another keyword or year.

Experience

• Shanghai Jiao Tong University, MVIG LabUndergraduate Research Intern with Professors Cewu Lu and Chuan WenEmbodied intelligence, force-aware interaction, and vision-language-action systems.
  Oct 2024 – Present
• SenseTimeTop InternSenseNova-U1.5: unified visual understanding and generation.
• Microsoft Research AsiaTomorrow Star ProgramScaling laws of multimodal generative models, video generation, and multimodal training infrastructure.
  Jun 2025 – Dec 2025
• Shanghai Jiao Tong University, Collaborative Intelligence Technology LabTime-Series Forecasting ResearchRetrieval-augmented few-shot time-series forecasting, leading to DANet.
  Feb 2024 – Dec 2024

Community Contribution

• lmms-eval, ContributorA unified evaluation toolkit for multimodal models across text, image, video, and audio.
• lmms-engine, ContributorA flexible training engine for large multimodal models.
• Flash Linear Attention, ContributorEfficient implementations and kernels for linear attention and related sequence models.