Minheng Ni

@article{wu2026postreality,
  title = {{Becoming the “Post-Reality”: AIGC, Memory Generation, and an Experimental Foray into AI Anthropology}},
  author = {Wu, Ennan and Ni, Minheng},
  journal = {Big Data \& Society},
  year = {2026},
  doi = {10.1177/20539517261481725},
  volume = {13},
  number = {3},
  pages = {20539517261481725}
}

arXiv

ComBodied Agents: A New Paradigm of Human-Centric Agentic AI

Qianggang Ding, Xingyao Wang, Rui Feng, Zhibin Wang, Feixiang Yao, Kelong Mao, Hao Sun, Zhiyao Luo, Jiankai Tang, Lei Li, Jiadong Guo, Minheng Ni, Weicong Lin, Chenxi Yang, Hongxiang Gao, Zhenghua Chen, Yang Bai, Min Wu, Jun Cheng, Huazhu Fu, Dacheng Tao, and Bang Liu

arXiv preprint arXiv:2608.10915, 2026

@article{ding2026combodied,
  title = {{ComBodied Agents: A New Paradigm of Human-Centric Agentic AI}},
  author = {Ding, Qianggang and Wang, Xingyao and Feng, Rui and Wang, Zhibin and Yao, Feixiang and Mao, Kelong and Sun, Hao and Luo, Zhiyao and Tang, Jiankai and Li, Lei and Guo, Jiadong and Ni, Minheng and Lin, Weicong and Yang, Chenxi and Gao, Hongxiang and Chen, Zhenghua and Bai, Yang and Wu, Min and Cheng, Jun and Fu, Huazhu and Tao, Dacheng and Liu, Bang},
  journal = {arXiv preprint arXiv:2608.10915},
  year = {2026},
}

SCIS

Ref-Diff: Zero-Shot Referring Image Segmentation with Generative Models

Minheng Ni, Yabo Zhang, Kailai Feng, Xiaoming Li, Yiwen Guo, and Wangmeng Zuo

Science China Information Sciences, 2026

@article{ni2025refdiff,
  title = {{Ref-Diff: Zero-Shot Referring Image Segmentation with Generative Models}},
  author = {Ni, Minheng and Zhang, Yabo and Feng, Kailai and Li, Xiaoming and Guo, Yiwen and Zuo, Wangmeng},
  journal = {Science China Information Sciences},
  year = {2026},
}

arXiv

Beyond Captions: Context-Grounded Reconstruction for Biomedical Multimodal Continued Pretraining

Guanghao Zhu, Zeyu Liu, Zhitian Hou, Pengkai Wang, Zhijie Sang, Yang Yu, Minheng Ni, Wenjun Wang, Yanggan Gu, Shuo Cai, Congkai Xie, Jianmin Wu, and Hongxia Yang

arXiv preprint arXiv:2606.01049, 2026

@article{zhu2026beyondcaptions,
  title = {{Beyond Captions: Context-Grounded Reconstruction for Biomedical Multimodal Continued Pretraining}},
  author = {Zhu, Guanghao and Liu, Zeyu and Hou, Zhitian and Wang, Pengkai and Sang, Zhijie and Yu, Yang and Ni, Minheng and Wang, Wenjun and Gu, Yanggan and Cai, Shuo and Xie, Congkai and Wu, Jianmin and Yang, Hongxia},
  journal = {arXiv preprint arXiv:2606.01049},
  year = {2026},
}

arXiv

CoEditor++: Instruction-Based Visual Editing via Cognitive Reasoning

Minheng Ni, Yutao Fan, Zhengyuan Yang, Yeli Shen, Yuxiang Wei, Yaowen Zhang, Lijuan Wang, Lei Zhang, and Wangmeng Zuo

arXiv preprint arXiv:2603.05518, 2026

@article{ni2026coeditor,
  title = {{CoEditor++: Instruction-Based Visual Editing via Cognitive Reasoning}},
  author = {Ni, Minheng and Fan, Yutao and Yang, Zhengyuan and Shen, Yeli and Wei, Yuxiang and Zhang, Yaowen and Wang, Lijuan and Zhang, Lei and Zuo, Wangmeng},
  journal = {arXiv preprint arXiv:2603.05518},
  year = {2026},
}

2025

arXiv

TechImage-Bench: Rubric-Based Evaluation for Technical Image Generation

Minheng Ni, Zhengyuan Yang, Yaowen Zhang, Linjie Li, Chung-Ching Lin, Kevin Lin, Zhendong Wang, Xiaofei Wang, Shujie Liu, Lei Zhang, Wangmeng Zuo, and Lijuan Wang

arXiv preprint arXiv:2512.12220Originally released as ProImage-Bench. , 2025

@article{ni2025techimage,
  title = {{TechImage-Bench: Rubric-Based Evaluation for Technical Image Generation}},
  author = {Ni, Minheng and Yang, Zhengyuan and Zhang, Yaowen and Li, Linjie and Lin, Chung-Ching and Lin, Kevin and Wang, Zhendong and Wang, Xiaofei and Liu, Shujie and Zhang, Lei and Zuo, Wangmeng and Wang, Lijuan},
  journal = {arXiv preprint arXiv:2512.12220},
  year = {2025},
}

arXiv

ResponsibleRobotBench: Benchmarking Responsible Robot Manipulation Using Multi-Modal Large Language Models

Lei Zhang, Ju Dong, Kaixin Bai, Minheng Ni, Zoltan-Csaba Marton, Zhaopeng Chen, and Jianwei Zhang

arXiv preprint arXiv:2512.04308, 2025

Bib HTML Website

@article{zhang2025responsiblerobotbench,
  title = {{ResponsibleRobotBench: Benchmarking Responsible Robot Manipulation Using Multi-Modal Large Language Models}},
  author = {Zhang, Lei and Dong, Ju and Bai, Kaixin and Ni, Minheng and Marton, Zoltan-Csaba and Chen, Zhaopeng and Zhang, Jianwei},
  journal = {arXiv preprint arXiv:2512.04308},
  year = {2025},
}

NeurIPS

MIRAGE: Assessing Hallucination in Multimodal Reasoning Chains of MLLM

Bowen Dong, Minheng Ni, Zitong Huang, Guanglei Yang, Wangmeng Zuo, and Lei Zhang

In Advances in Neural Information Processing Systems, 2025

@inproceedings{dong2025mirage,
  title = {{MIRAGE: Assessing Hallucination in Multimodal Reasoning Chains of MLLM}},
  author = {Dong, Bowen and Ni, Minheng and Huang, Zitong and Yang, Guanglei and Zuo, Wangmeng and Zhang, Lei},
  booktitle = {Advances in Neural Information Processing Systems},
  year = {2025},
}

NeurIPS

Point-RFT: Improving Multimodal Reasoning with Visually Grounded Reinforcement Finetuning

Minheng Ni, Zhengyuan Yang, Linjie Li, Chung-Ching Lin, Kevin Lin, Wangmeng Zuo, and Lijuan Wang

In Advances in Neural Information Processing Systems, 2025

Bib HTML Code Website

@inproceedings{ni2025pointrft,
  title = {{Point-RFT: Improving Multimodal Reasoning with Visually Grounded Reinforcement Finetuning}},
  author = {Ni, Minheng and Yang, Zhengyuan and Li, Linjie and Lin, Chung-Ching and Lin, Kevin and Zuo, Wangmeng and Wang, Lijuan},
  booktitle = {Advances in Neural Information Processing Systems},
  year = {2025},
}

RA-L

Don’t Let Your Robot Be Harmful: Responsible Robotic Manipulation via Safety-as-Policy

Minheng Ni, Lei Zhang, Zihan Chen, Kaixin Bai, Zhaopeng Chen, Jianwei Zhang, Lei Zhang, and Wangmeng Zuo

IEEE Robotics and Automation Letters, 2025

Bib HTML Code Website

@article{ni2025safetyaspolicy,
  title = {{Don't Let Your Robot Be Harmful: Responsible Robotic Manipulation via Safety-as-Policy}},
  author = {Ni, Minheng and Zhang, Lei and Chen, Zihan and Bai, Kaixin and Chen, Zhaopeng and Zhang, Jianwei and Zhang, Lei and Zuo, Wangmeng},
  journal = {IEEE Robotics and Automation Letters},
  year = {2025},
}

ICLR

Visual-O1: Understanding Ambiguous Instructions via Multi-Modal Multi-Turn Chain-of-Thoughts Reasoning

Minheng Ni, Yutao Fan, Lei Zhang, and Wangmeng Zuo

In International Conference on Learning Representations, 2025

@inproceedings{ni2025visualo1,
  title = {{Visual-O1: Understanding Ambiguous Instructions via Multi-Modal Multi-Turn Chain-of-Thoughts Reasoning}},
  author = {Ni, Minheng and Fan, Yutao and Zhang, Lei and Zuo, Wangmeng},
  booktitle = {International Conference on Learning Representations},
  year = {2025},
}

arXiv

Measurement of LLM’s Philosophies of Human Nature

Minheng Ni, Ennan Wu, Zidong Gong, Zhengyuan Yang, Linjie Li, Chung-Ching Lin, Kevin Lin, Lijuan Wang, and Wangmeng Zuo

arXiv preprint arXiv:2504.02304, 2025

@article{ni2025philosophies,
  title = {{Measurement of LLM’s Philosophies of Human Nature}},
  author = {Ni, Minheng and Wu, Ennan and Gong, Zidong and Yang, Zhengyuan and Li, Linjie and Lin, Chung-Ching and Lin, Kevin and Wang, Lijuan and Zuo, Wangmeng},
  journal = {arXiv preprint arXiv:2504.02304},
  year = {2025},
}

COLING

FineRAG: Fine-Grained Retrieval-Augmented Text-to-Image Generation

Huaying Yuan, Ziliang Zhao, Shuting Wang, Shitao Xiao, Minheng Ni, Zheng Liu, and Zhicheng Dou

In Proceedings of the International Conference on Computational Linguistics, 2025

@inproceedings{yuan2025finerag,
  title = {{FineRAG: Fine-Grained Retrieval-Augmented Text-to-Image Generation}},
  author = {Yuan, Huaying and Zhao, Ziliang and Wang, Shuting and Xiao, Shitao and Ni, Minheng and Liu, Zheng and Dou, Zhicheng},
  booktitle = {Proceedings of the International Conference on Computational Linguistics},
  year = {2025},
}

2024

ECCV

Responsible Visual Editing

Minheng Ni, Yeli Shen, Lei Zhang, and Wangmeng Zuo

In European Conference on Computer Vision, 2024

Bib HTML Code Website

@inproceedings{ni2024responsible,
  title = {{Responsible Visual Editing}},
  author = {Ni, Minheng and Shen, Yeli and Zhang, Lei and Zuo, Wangmeng},
  booktitle = {European Conference on Computer Vision},
  year = {2024},
}

arXiv

AutoDirector: Online Auto-Scheduling Agents for Multi-Sensory Composition

Minheng Ni, Chenfei Wu, Huaying Yuan, Zhengyuan Yang, Ming Gong, Lijuan Wang, Zicheng Liu, Wangmeng Zuo, and Nan Duan

arXiv preprint arXiv:2408.11564, 2024

@article{ni2024autodirector,
  title = {{AutoDirector: Online Auto-Scheduling Agents for Multi-Sensory Composition}},
  author = {Ni, Minheng and Wu, Chenfei and Yuan, Huaying and Yang, Zhengyuan and Gong, Ming and Wang, Lijuan and Liu, Zicheng and Zuo, Wangmeng and Duan, Nan},
  journal = {arXiv preprint arXiv:2408.11564},
  year = {2024},
}

ICME

Multi-Attentional Distance for Zero-Shot Classification with Text-to-Image Diffusion Model

Kailai Feng, Minheng Ni, Jiaxiu Jiang, Zhilu Zhang, and Wangmeng Zuo

In IEEE International Conference on Multimedia and Expo, 2024

@inproceedings{feng2024multiattentional,
  title = {{Multi-Attentional Distance for Zero-Shot Classification with Text-to-Image Diffusion Model}},
  author = {Feng, Kailai and Ni, Minheng and Jiang, Jiaxiu and Zhang, Zhilu and Zuo, Wangmeng},
  booktitle = {IEEE International Conference on Multimedia and Expo},
  year = {2024},
  doi = {10.1109/ICME57554.2024.10687898},
}

ICML

StrokeNUWA: Tokenizing Strokes for Vector Graphic Synthesis

Zecheng Tang, Chenfei Wu, Zekai Zhang, Minheng Ni, Shengming Yin, Yu Liu, Zhengyuan Yang, Lijuan Wang, Zicheng Liu, Juntao Li, and Nan Duan

In Proceedings of the International Conference on Machine Learning, 2024

@inproceedings{tang2024strokenuwa,
  title = {{StrokeNUWA: Tokenizing Strokes for Vector Graphic Synthesis}},
  author = {Tang, Zecheng and Wu, Chenfei and Zhang, Zekai and Ni, Minheng and Yin, Shengming and Liu, Yu and Yang, Zhengyuan and Wang, Lijuan and Liu, Zicheng and Li, Juntao and Duan, Nan},
  booktitle = {Proceedings of the International Conference on Machine Learning},
  year = {2024},
}

AAAI

ORES: Open-Vocabulary Responsible Visual Synthesis

Minheng Ni, Chenfei Wu, Xiaodong Wang, Shengming Yin, Lijuan Wang, Zicheng Liu, and Nan Duan

In Proceedings of the AAAI Conference on Artificial Intelligence, 2024

@inproceedings{ni2024ores,
  title = {{ORES: Open-Vocabulary Responsible Visual Synthesis}},
  author = {Ni, Minheng and Wu, Chenfei and Wang, Xiaodong and Yin, Shengming and Wang, Lijuan and Liu, Zicheng and Duan, Nan},
  booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
}

2023

IJCAI

Learning 3D Photography Videos via Self-Supervised Diffusion on Single Images

Xiaodong Wang, Chenfei Wu, Shengming Yin, Minheng Ni, Jianfeng Wang, Linjie Li, Zhengyuan Yang, Fan Yang, Lijuan Wang, Zicheng Liu, Yuejian Fang, and Nan Duan

In Proceedings of the International Joint Conference on Artificial Intelligence, 2023

@inproceedings{wang2023photography,
  title = {{Learning 3D Photography Videos via Self-Supervised Diffusion on Single Images}},
  author = {Wang, Xiaodong and Wu, Chenfei and Yin, Shengming and Ni, Minheng and Wang, Jianfeng and Li, Linjie and Yang, Zhengyuan and Yang, Fan and Wang, Lijuan and Liu, Zicheng and Fang, Yuejian and Duan, Nan},
  booktitle = {Proceedings of the International Joint Conference on Artificial Intelligence},
  year = {2023},
}

ACL

NUWA-XL: Diffusion over Diffusion for eXtremely Long Video Generation

Shengming Yin, Chenfei Wu, Huan Yang, Jianfeng Wang, Xiaodong Wang, Minheng Ni, Zhengyuan Yang, Linjie Li, Shuguang Liu, Fan Yang, Jianlong Fu, Gong Ming, Lijuan Wang, Zicheng Liu, Houqiang Li, and Nan Duan

In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, 2023

@inproceedings{yin2023nuwaxl,
  title = {{NUWA-XL: Diffusion over Diffusion for eXtremely Long Video Generation}},
  author = {Yin, Shengming and Wu, Chenfei and Yang, Huan and Wang, Jianfeng and Wang, Xiaodong and Ni, Minheng and Yang, Zhengyuan and Li, Linjie and Liu, Shuguang and Yang, Fan and Fu, Jianlong and Ming, Gong and Wang, Lijuan and Liu, Zicheng and Li, Houqiang and Duan, Nan},
  booktitle = {Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics},
  year = {2023},
}

CVPR

NÜWA-LIP: Language Guided Image Inpainting with Defect-Free VQGAN

Minheng Ni, Xiaoming Li, and Wangmeng Zuo

In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

@inproceedings{ni2023nuwalip,
  title = {{NÜWA-LIP: Language Guided Image Inpainting with Defect-Free VQGAN}},
  author = {Ni, Minheng and Li, Xiaoming and Zuo, Wangmeng},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year = {2023},
}

ICLR

ImaginaryNet: Learning Object Detectors without Real Images and Annotations

Minheng Ni, Zitong Huang, Kailai Feng, and Wangmeng Zuo

In International Conference on Learning Representations, 2023

@inproceedings{ni2023imaginarynet,
  title = {{ImaginaryNet: Learning Object Detectors without Real Images and Annotations}},
  author = {Ni, Minheng and Huang, Zitong and Feng, Kailai and Zuo, Wangmeng},
  booktitle = {International Conference on Learning Representations},
  year = {2023},
}

2022

TALLIP

Multi-Domain Spoken Language Understanding Using Domain-and Task-Aware Parameterization

Libo Qin, Fuxuan Wei, Minheng Ni, Yue Zhang, Wanxiang Che, Yangming Li, and Ting Liu

ACM Transactions on Asian and Low-Resource Language Information Processing, 2022

@article{qin2022multidomainslu,
  title = {{Multi-Domain Spoken Language Understanding Using Domain-and Task-Aware Parameterization}},
  author = {Qin, Libo and Wei, Fuxuan and Ni, Minheng and Zhang, Yue and Che, Wanxiang and Li, Yangming and Liu, Ting},
  journal = {ACM Transactions on Asian and Low-Resource Language Information Processing},
  year = {2022},
  doi = {10.1145/3502198},
}

2021

CVPR

M3P: Learning Universal Representations via Multitask Multilingual Multimodal Pre-Training

Minheng Ni, Haoyang Huang, Lin Su, Edward Cui, Taroon Bharti, Lijuan Wang, Dongdong Zhang, and Nan Duan

In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021

@inproceedings{ni2021m3p,
  title = {{M3P: Learning Universal Representations via Multitask Multilingual Multimodal Pre-Training}},
  author = {Ni, Minheng and Huang, Haoyang and Su, Lin and Cui, Edward and Bharti, Taroon and Wang, Lijuan and Zhang, Dongdong and Duan, Nan},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year = {2021},
}

AAAI

Co-GAT: A Co-Interactive Graph Attention Network for Joint Dialog Act Recognition and Sentiment Classification

Libo Qin, Zhouyang Li, Wanxiang Che, Minheng Ni, and Ting Liu

In Proceedings of the AAAI Conference on Artificial Intelligence, 2021

@inproceedings{qin2021cogat,
  title = {{Co-GAT: A Co-Interactive Graph Attention Network for Joint Dialog Act Recognition and Sentiment Classification}},
  author = {Qin, Libo and Li, Zhouyang and Che, Wanxiang and Ni, Minheng and Liu, Ting},
  booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2021},
}

TASLP

Knowing Where to Leverage: Context-Aware Graph Convolutional Network with an Adaptive Fusion Layer for Contextual Spoken Language Understanding

Libo Qin, Wanxiang Che, Minheng Ni, Yangming Li, and Ting Liu

IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2021

@article{qin2021contextualslu,
  title = {{Knowing Where to Leverage: Context-Aware Graph Convolutional Network with an Adaptive Fusion Layer for Contextual Spoken Language Understanding}},
  author = {Qin, Libo and Che, Wanxiang and Ni, Minheng and Li, Yangming and Liu, Ting},
  journal = {IEEE/ACM Transactions on Audio, Speech, and Language Processing},
  year = {2021},
  doi = {10.1109/TASLP.2021.3053400},
}

2020

IJCAI

CoSDA-ML: Multi-Lingual Code-Switching Data Augmentation for Zero-Shot Cross-Lingual NLP

Libo Qin, Minheng Ni, Yue Zhang, and Wanxiang Che

In Proceedings of the International Joint Conference on Artificial Intelligence, 2020

@inproceedings{qin2020cosdaml,
  title = {{CoSDA-ML: Multi-Lingual Code-Switching Data Augmentation for Zero-Shot Cross-Lingual NLP}},
  author = {Qin, Libo and Ni, Minheng and Zhang, Yue and Che, Wanxiang},
  booktitle = {Proceedings of the International Joint Conference on Artificial Intelligence},
  year = {2020},
}

AAAI

DCR-Net: A Deep Co-Interactive Relation Network for Joint Dialog Act Recognition and Sentiment Classification

Libo Qin, Wanxiang Che, Yangming Li, Minheng Ni, and Ting Liu

In Proceedings of the AAAI Conference on Artificial Intelligence, 2020