Hi! I'm Jiahang Cao.

Occupancy World Model for Robots

Qiang Zhang*, Zhang Zhang*, Wei Cui*, Shuai Shi, Yijie Guo, Gang Han, Wen Zhao, Jingkai Sun, Jiahang Cao, Jiaxu Wang, Hao Cheng, Xiaozhu Ju, Zhengping Che, Renjing Xu, Jian Tang

arXiv 2025

Paper | Bibtex

@article{zhang2025occupancy,
  title={Occupancy World Model for Robots},
  author={Zhang, Zhang and Zhang, Qiang and Cui, Wei and Shi, Shuai and Guo, Yijie and Han, Gang and Zhao, Wen and Sun, Jingkai and Cao, Jiahang and Wang, Jiaxu and others},
  journal={arXiv preprint arXiv:2505.05512},
  year={2025}
}
                        

Modality-Composable Diffusion Policy via Inference-Time Distribution-level Composition

Jiahang Cao, Qiang Zhang, Hanzhong Guo, Jiaxu Wang, Hao Cheng, Renjing Xu

ICLR GenBot 2025 (ICLR Generative Models for Robot Learning Workshop)

Paper | Code | Bibtex

@article{cao2025modality,
  title={Modality-Composable Diffusion Policy via Inference-Time Distribution-level Composition},
  author={Cao, Jiahang and Zhang, Qiang and Guo, Hanzhong and Wang, Jiaxu and Cheng, Hao and Xu, Renjing},
  journal={arXiv preprint arXiv:2503.12466},
  year={2025}
}
                        

EmbodiedVSR: Dynamic Scene Graph-Guided Chain-of-Thought Reasoning for Visual Spatial Tasks

Yi Zhang*, Qiang Zhang*, Xiaozhu Ju*, Zhaoyang Liu, Jilei Mao, Jingkai Sun, Jintao Wu, Shixiong Gao, Shihan Cai, Zhiyuan Qin, Linkai Liang, Jiaxu Wang, Yiqun Duan*, Jiahang Cao, Renjing Xu, Jian Tang,

arXiv 2025

Paper | Bibtex

@article{zhang2025embodiedvsr,
title={EmbodiedVSR: Dynamic scene graph-guided chain-of-thought reasoning for visual spatial tasks},
author={Zhang, Yi and Zhang, Qiang and Ju, Xiaozhu and Liu, Zhaoyang and Mao, Jilei and Sun, Jingkai and Wu, Jintao and Gao, Shixiong and Cai, Shihan and Qin, Zhiyuan and others},
journal={arXiv preprint arXiv:2503.11089},
year={2025}
}
                        

ES-Parkour: Advanced Robot Parkour with Bio-inspired Event Camera and Spiking Neural Network

Qiang Zhang*, Jiahang Cao*, Jingkai Sun*, Yecheng Shao, Gang Han, Wen Zhao, Yijie Guo, Renjing Xu

ICME 2025 (IEEE International Conference on Multimedia & Expo)

Paper | Bibtex

@article{zhang2025parkour,
  title={ES-Parkour: Advanced Robot Parkour with Bio-inspired Event Camera and Spiking Neural Network},
  author={Zhang, Qiang and Cao, Jiahang and Sun, Jingkai and Shao, Yecheng and Han, Gang and Zhao, Wen and Guo, Yijie and Xu, Renjing},
  journal={arXiv preprint arXiv:2503.09985},
  year={2025}
}
                        

HumanoidPano: Hybrid Spherical Panoramic-LiDAR Cross-Modal Perception for Humanoid Robots

Qiang Zhang*, Zhang Zhang*, Wei Cui*, Jingkai Sun, Jiahang Cao, Yijie Guo, Gang Han, Wen Zhao, Jiaxu Wang, Chenghao Sun, Lingfeng Zhang, Hao Cheng, Yujie Chen, Lin Wang, Jian Tang, Renjing Xu

arXiv 2025

Paper | Bibtex

@article{zhang2025humanoidpano,
  title={Humanoidpano: Hybrid spherical panoramic-lidar cross-modal perception for humanoid robots},
  author={Zhang, Qiang and Zhang, Zhang and Cui, Wei and Sun, Jingkai and Cao, Jiahang and Guo, Yijie and Han, Gang and Zhao, Wen and Wang, Jiaxu and Sun, Chenghao and others},
  journal={arXiv preprint arXiv:2503.09010},
  year={2025}
}
                        

Mamba Policy: Towards Efficient 3D Diffusion Policy with Hybrid Selective State Models

Jiahang Cao*, Qiang Zhang*, Jingkai Sun, Jiaxu Wang, Hao Cheng, Yulin Li, Jun Ma, Yecheng Shao, Wen Zhao, Gang Han, Yijie Guo, Renjing Xu

IROS 2025 (IEEE/RSJ International Conference on Intelligent Robots and Systems)

Paper | Project | Code | Bibtex

@article{cao2024mamba,
  title={Mamba Policy: Towards Efficient 3D Diffusion Policy with Hybrid Selective State Models},
  author={Cao, Jiahang and Zhang, Qiang and Sun, Jingkai and Wang, Jiaxu and Cheng, Hao and Li, Yulin and Ma, Jun and Shao, Yecheng and Zhao, Wen and Han, Gang and others},
  journal={arXiv preprint arXiv:2409.07163},
  year={2024}
}
                        

Distillation-PPO: A Novel Two-Stage Reinforcement Learning Framework for Humanoid Robot Perceptive Locomotion

Qiang Zhang*, Gang Han*, Jingkai Sun*, Wen Zhao*, Chenghao Sun, Jiahang Cao, Jiaxu Wang, Yijie Guo, Renjing Xu

IROS 2025 (IEEE/RSJ International Conference on Intelligent Robots and Systems)

Paper | Bibtex

@article{zhang2025distillation,
  title={Distillation-ppo: A novel two-stage reinforcement learning framework for humanoid robot perceptive locomotion},
  author={Zhang, Qiang and Han, Gang and Sun, Jingkai and Zhao, Wen and Sun, Chenghao and Cao, Jiahang and Wang, Jiaxu and Guo, Yijie and Xu, Renjing},
  journal={arXiv preprint arXiv:2503.08299},
  year={2025}
}
                        

Trinity: A Modular Humanoid Robot AI System

Jingkai Sun*, Qiang Zhang*, Gang Han*, Wen Zhao*, Zhe Yong, Yan He, Jiaxu Wang, Jiahang Cao, Yijie Guo, Renjing Xu

arXiv 2025

Paper | Bibtex

@article{sun2025trinity,
  title={Trinity: A Modular Humanoid Robot AI System},
  author={Sun, Jingkai and Zhang, Qiang and Han, Gang and Zhao, Wen and Yong, Zhe and He, Yan and Wang, Jiaxu and Cao, Jiahang and Guo, Yijie and Xu, Renjing},
  journal={arXiv preprint arXiv:2503.08338},
  year={2025}
}
                        

LiPS: Large-Scale Humanoid Robot Reinforcement Learning with Parallel-Series Structures

Qiang Zhang*, Gang Han*, Jingkai Sun*, Wen Zhao*, Jiahang Cao, Jiaxu Wang, Hao Cheng, Lingfeng Zhang, Yijie Guo, Renjing Xu

arXiv 2025

Paper | Bibtex

@article{zhang2025lips,
  title={Lips: Large-scale humanoid robot reinforcement learning with parallel-series structures},
  author={Zhang, Qiang and Han, Gang and Sun, Jingkai and Zhao, Wen and Cao, Jiahang and Wang, Jiaxu and Cheng, Hao and Zhang, Lingfeng and Guo, Yijie and Xu, Renjing},
  journal={arXiv preprint arXiv:2503.08349},
  year={2025}
}
                        

RoboDexVLM: Visual Language Model-Enabled Task Planning and Motion Control for Dexterous Robot Manipulation

Haichao Liu, Sikai Guo, Pengfei Mai, Jiahang Cao, Haoang Li, Jun Ma

IROS 2025 (IEEE/RSJ International Conference on Intelligent Robots and Systems)

Paper | Project | Bibtex

@article{liu2025robodexvlm,
  title={RoboDexVLM: Visual Language Model-Enabled Task Planning and Motion Control for Dexterous Robot Manipulation},
  author={Liu, Haichao and Guo, Sikai and Mai, Pengfei and Cao, Jiahang and Li, Haoang and Ma, Jun},
  journal={arXiv preprint arXiv:2503.01616},
  year={2025}
}
                        

Representation Convergence: Mutual Distillation is Secretly a Form of Regularization

Zhengpeng Xie*, Jiahang Cao*, Qiang Zhang, Jianxiong Zhang, Changwei Wang, Renjing Xu

arXiv 2025

Paper | Project | Bibtex

@article{xie2025meta,
  title={Representation Convergence: Mutual Distillation is Secretly a Form of Regularization},
  author={Xie, Zhengpeng and Cao, Jiahang and Zhang, Qiang and Zhang, Jianxiong and Wang, Changwei and Xu, Renjing},
  journal={arXiv preprint arXiv:2501.02481},
  year={2025}
}
                        

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models

Hao Cheng*, Erjia Xiao*, Jiayan Yang, Jiahang Cao, Qiang Zhang, Jize Zhang, Kaidi Xu, Jindong Gu, Renjing Xu

CVPR 2025 (IEEE / CVF Computer Vision and Pattern Recognition Conference)

Paper | Code | Dataset | Bibtex

@inproceedings{cheng2025not,
  title={Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models},
  author={Cheng, Hao and Xiao, Erjia and Yang, Jiayan and Cao, Jiahang and Zhang, Qiang and Zhang, Jize and Xu, Kaidi and Gu, Jindong and Xu, Renjing},
  booktitle={Proceedings of the Computer Vision and Pattern Recognition Conference},
  pages={2997--3007},
  year={2025}
}
                        

Adaptive Calibration: A Unified Conversion Framework of Spiking Neural Network

Ziqing Wang*, Yuetong Fang*, Jiahang Cao, Hongwei Ren, Renjing Xu

AAAI 2025 Oral (Annual AAAI Conference on Artificial Intelligence)

Paper | Code | Bibtex

@inproceedings{wang2025adaptive,
  title={Adaptive calibration: A unified conversion framework of spiking neural networks},
  author={Wang, Ziqing and Fang, Yuetong and Cao, Jiahang and Ren, Hongwei and Xu, Renjing},
  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
  volume={39},
  number={2},
  pages={1583--1591},
  year={2025}
}
                        

Event Masked Autoencoder: Point-wise Action Recognition with Event-Based Cameras

Jingkai Sun*, Qiang Zhang*, Jinzhao Zhou, Jiaxu Wang, Jiahang Cao, Hao Cheng, Renjing Xu

ICASSP 2025 (IEEE International Conference on Acoustics, Speech, and Signal Processing)

Paper | Bibtex

@article{sun2025event,
  title={Event Masked Autoencoder: Point-wise Action Recognition with Event-Based Cameras},
  author={Sun, Jingkai and Zhang, Qiang and Wang, Jiaxu and Cao, Jiahang and Xu, Renjing},
  journal={arXiv preprint arXiv:2501.01040},
  year={2025}
}
                        

Fully Spiking Neural Network for Legged Robots

Xiaoyang Jiang*, Qiang Zhang*, Jingkai Sun, Jiahang Cao, Jingtong Ma, Renjing Xu

ICASSP 2025 (IEEE International Conference on Acoustics, Speech, and Signal Processing)

Paper | Bibtex

@inproceedings{jiang2025fully,
  title={Fully spiking neural network for legged robots},
  author={Jiang, Xiaoyang and Zhang, Qiang and Sun, Jingkai and Cao, Jiahang and Ma, Jingtong and Xu, Renjing},
  booktitle={ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={1--5},
  year={2025},
  organization={IEEE}
}
                        

Robust SG-NeRF: Robust Scene Graph Aided Neural Surface Reconstruction

Yi Gu, Dongjun Ye, Zhaorui Wang, Jiaxu Wang, Jiahang Cao, Renjing Xu

arXiv 2024

Paper | Project | Bibtex

@article{gu2024robust,
  title={Robust SG-NeRF: Robust Scene Graph Aided Neural Surface Reconstruction},
  author={Gu, Yi and Ye, Dongjun and Wang, Zhaorui and Wang, Jiaxu and Cao, Jiahang and Xu, Renjing},
  journal={arXiv preprint arXiv:2411.13620},
  year={2024}
}
                        

Manipulation Facing Threats: Evaluating Physical Vulnerabilities in End-to-End Vision Language Action Models

Hao Cheng*, Erjia Xiao*, Chengyuan Yu, Zhao Yao, Jiahang Cao, Qiang Zhang, Jiaxu Wang, Mengshu Sun, Kaidi Xu, Jindong Gu, Renjing Xu

arXiv 2024

Paper | Project | Bibtex

@article{cheng2024manipulation,
  title={Manipulation Facing Threats: Evaluating Physical Vulnerabilities in End-to-End Vision Language Action Models},
  author={Cheng, Hao and Xiao, Erjia and Yu, Chengyuan and Yao, Zhao and Cao, Jiahang and Zhang, Qiang and Wang, Jiaxu and Sun, Mengshu and Xu, Kaidi and Gu, Jindong and others},
  journal={arXiv preprint arXiv:2409.13174},
  year={2024}
}
                        

Mamba as decision maker: Exploring multi-scale sequence modeling in offline reinforcement learning

Jiahang Cao*, Qiang Zhang*, Ziqing Wang, Jingkai Sun, Jiaxu Wang, Hao Cheng, Yecheng Shao, Wen Zhao, Gang Han, Yijie Guo, Renjing Xu

arXiv 2024

Paper | Bibtex

@article{cao2024mamba,
  title={Mamba as decision maker: Exploring multi-scale sequence modeling in offline reinforcement learning},
  author={Cao, Jiahang and Zhang, Qiang and Wang, Ziqing and Sun, Jingkai and Wang, Jiaxu and Cheng, Hao and Shao, Yecheng and Zhao, Wen and Han, Gang and Guo, Yijie and others},
  journal={arXiv preprint arXiv:2406.02013},
  year={2024}
}
                        

E2H: A Two-Stage Non-Invasive Neural Signal Driven Humanoid Robotic Whole-Body Control Framework

Yiqun Duan*, Qiang Zhang*, Jinzhao Zhou, Jingkai Sun, Xiaowei Jiang, Jiahang Cao*, Jiaxu Wang, Yiqian Yang, Wen Zhao, Gang Han, Yijie Guo, Chin-Teng Lin

arXiv 2024

Paper | Bibtex

@article{duan2024e2h,
  title={E2H: A Two-Stage Non-Invasive Neural Signal Driven Humanoid Robotic Whole-Body Control Framework},
  author={Duan, Yiqun and Zhang, Qiang and Zhou, Jinzhao and Sun, Jingkai and Jiang, Xiaowei and Cao, Jiahang and Wang, Jiaxu and Yang, Yiqian and Zhao, Wen and Han, Gang and others},
  journal={arXiv preprint arXiv:2410.02141},
  year={2024}
}
                        

Spiking Neural Network as Adaptive Event Stream Slicer

Jiahang Cao*, Mingyuan Sun*, Ziqing Wang*, Hao Cheng, Qiang Zhang, Shibo Zhou, Renjing Xu

NeurIPS 2024 (Conference on Neural Information Processing Systems)

Paper | Code | Bibtex

@inproceedings{caospiking,
  title={Spiking Neural Network as Adaptive Event Stream Slicer},
  author={Cao, Jiahang and Sun, Mingyuan and Wang, Ziqing and Cheng, Hao and Zhang, Qiang and Xu, Renjing and others},
  booktitle={The Thirty-eighth Annual Conference on Neural Information Processing Systems}
}
                        

Reinforcement Learning with Generalizable Gaussian Splatting

Jiaxu Wang*, Qiang Zhang*, Jingkai Sun, Jiahang Cao, Yecheng Shao, Renjing Xu

IROS 2024 (IEEE/RSJ International Conference on Intelligent Robots and Systems)

Paper | Bibtex

@inproceedings{wang2024reinforcement,
  title={Reinforcement learning with generalizable gaussian splatting},
  author={Wang, Jiaxu and Zhang, Qiang and Sun, Jingkai and Cao, Jiahang and Han, Gang and Zhao, Wen and Zhang, Weining and Shao, Yecheng and Guo, Yijie and Xu, Renjing},
  booktitle={2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  pages={435--441},
  year={2024},
  organization={IEEE}
}
                        

Gaining the Sparse Rewards by Exploring Lottery Tickets in Spiking Neural Network

Hao Cheng*, Jiahang Cao*, Erjia Xiao, Mengshu Sun, Renjing Xu

IROS 2024 (IEEE/RSJ International Conference on Intelligent Robots and Systems)

Paper | Bibtex

@inproceedings{cheng2024gaining,
  title={Gaining the Sparse Rewards by Exploring Lottery Tickets in Spiking Neural Networks},
  author={Cheng, Hao and Cao, Jiahang and Xiao, Erjia and Sun, Mengshu and Xu, Renjing},
  booktitle={2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  pages={442--449},
  year={2024},
  organization={IEEE}
}
                        

Spiking Wavelet Transformer

Yuetong Fang*, Ziqing Wang*, Lingfeng Zhang, Jiahang Cao, Honglei Chen, Renjing Xu

ECCV 2024 (European Conference on Computer Vision)

Paper | Code | Bibtex

@inproceedings{fang2024spiking,
  title={Spiking wavelet transformer},
  author={Fang, Yuetong and Wang, Ziqing and Zhang, Lingfeng and Cao, Jiahang and Chen, Honglei and Xu, Renjing},
  booktitle={European Conference on Computer Vision},
  pages={19--37},
  year={2024},
  organization={Springer}
}
                        

Unveiling Typographic Deceptions: Insights of the Typographic Vulnerability in Large Vision-Language Model

Hao Cheng*, Erjia Xiao*, Jindong Gu, Le Yang, Jinhao Duan, Jize Zhang, Jiahang Cao, Kaidi Xu, Renjing Xu

ECCV 2024 (European Conference on Computer Vision)

Paper | Code | Bibtex

@inproceedings{cheng2024unveiling,
  title={Unveiling typographic deceptions: Insights of the typographic vulnerability in large vision-language models},
  author={Cheng, Hao and Xiao, Erjia and Gu, Jindong and Yang, Le and Duan, Jinhao and Zhang, Jize and Cao, Jiahang and Xu, Kaidi and Xu, Renjing},
  booktitle={European Conference on Computer Vision},
  pages={179--196},
  year={2024},
  organization={Springer}
}
                        

Spiking Diffusion Models

(The extended version of Spiking Denoising Diffusion Probabilistic Models)

Jiahang Cao*, Hanzhong Guo*, Ziqing Wang*, Deming Zhou, Hao Cheng, Qiang Zhang, Renjing Xu

TAI 2024 (IEEE Transactions on Artificial Intelligence)

Paper | Code | Bibtex

@article{cao2024spiking,
  title={Spiking Diffusion Models},
  author={Cao, Jiahang and Guo, Hanzhong and Wang, Ziqing and Zhou, Deming and Cheng, Hao and Zhang, Qiang and Xu, Renjing},
  journal={IEEE Transactions on Artificial Intelligence},
  year={2024},
  publisher={IEEE}
}
                        

Chasing Day and Night: Towards Robust and Efficient All-Day Object Detection Guided by an Event Camera

Jiahang Cao, Xu Zheng, Yuanhuiyi Lyu, Jiaxu Wang, Renjing Xu, Lin Wang

ICRA 2024 (IEEE International Conference on Robotics and Automation)

Paper | Project | Code | Bibtex

@inproceedings{cao2024chasing,
  title={Chasing day and night: Towards robust and efficient all-day object detection guided by an event camera},
  author={Cao, Jiahang and Zheng, Xu and Lyu, Yuanhuiyi and Wang, Jiaxu and Xu, Renjing and Wang, Lin},
  booktitle={2024 IEEE International Conference on Robotics and Automation (ICRA)},
  pages={9026--9032},
  year={2024},
  organization={IEEE}
}
                        

Spiking Denoising Diffusion Probabilistic Models

Jiahang Cao*, Ziqing Wang*, Hanzhong Guo*, Hao Cheng, Qiang Zhang, Renjing Xu

WACV 2024 (IEEE/CVF Winter Conference on Applications of Computer Vision)

Paper | Code | Bibtex

@inproceedings{cao2024spiking,
  title={Spiking denoising diffusion probabilistic models},
  author={Cao, Jiahang and Wang, Ziqing and Guo, Hanzhong and Cheng, Hao and Zhang, Qiang and Xu, Renjing},
  booktitle={Proceedings of the IEEE/CVF winter conference on applications of computer vision},
  pages={4912--4921},
  year={2024}
}
                        

Knowledge Graph Embedding: A Survey from the Perspective of Representation Spaces

Jiahang Cao*, Jinyuan Fang*, Zaiqiao Meng, Shangsong Liang

ACM Computing Surveys 2024

Paper | Bibtex

@article{cao2024knowledge,
  title={Knowledge graph embedding: A survey from the perspective of representation spaces},
  author={Cao, Jiahang and Fang, Jinyuan and Meng, Zaiqiao and Liang, Shangsong},
  journal={ACM Computing Surveys},
  volume={56},
  number={6},
  pages={1--42},
  year={2024},
  publisher={ACM New York, NY}
}
                        

Masked Spiking Transformer

Ziqing Wang*, Yuetong Fang*, Jiahang Cao, Qiang Zhang, Zhongrui Wang, Renjing Xu

ICCV 2023 (IEEE/CVF International Conference on Computer Vision)

Paper | Code | Bibtex

@inproceedings{wang2023masked,
  title={Masked spiking transformer},
  author={Wang, Ziqing and Fang, Yuetong and Cao, Jiahang and Zhang, Qiang and Wang, Zhongrui and Xu, Renjing},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={1761--1771},
  year={2023}
}