Publications | Max W.F. Ku

2026

Preprint

World Editing: Intervening on Executable Worlds at Increasing Depth

Max Ku, Nok-Kan Law, Yu-Chien Tang, Shih-Ying Yeh, Ping Nie, Andy Zheng, Tat Hei Lai, Fei-Yueh Chen, Nikko Yu, Wei-Chieh Sun, Suzy Huang, Chiao-Wei Hsu, Chih-Chuan Huang, Chak-Wing Mak, Ho Yin Sam Ng, Edisy Kin Wai Chan, Min-Hung Chen, and Ho Kei Cheng

In arXiv , 2026

arXiv Bib Code Website

@inproceedings{ku2026worldeditinginterveningexecutable,
  title = {World Editing: Intervening on Executable Worlds at Increasing Depth},
  booktitle = {arXiv},
  author = {Ku, Max and Law, Nok-Kan and Tang, Yu-Chien and Yeh, Shih-Ying and Nie, Ping and Zheng, Andy and Lai, Tat Hei and Chen, Fei-Yueh and Yu, Nikko and Sun, Wei-Chieh and Huang, Suzy and Hsu, Chiao-Wei and Huang, Chih-Chuan and Mak, Chak-Wing and Ng, Ho Yin Sam and Chan, Edisy Kin Wai and Chen, Min-Hung and Cheng, Ho Kei},
  year = {2026},
  selected = true,
  bibtex_show = false
}

Preprint

VIEScore2: Unified Image Evaluation with Spatially Grounded Explanations

Xianda Du*, Max Ku*, Weiming Ren, Zhi Rui Tam, Chunlin Ren, Ping Nie, Min-Hung Chen, and Wenhu Chen

In arXiv , 2026

arXiv Bib Code Website

@inproceedings{du2026viescore2unifiedimageevaluation,
  title = {VIEScore2: Unified Image Evaluation with Spatially Grounded Explanations},
  booktitle = {arXiv},
  author = {Du*, Xianda and Ku*, Max and Ren, Weiming and Tam, Zhi Rui and Ren, Chunlin and Nie, Ping and Chen, Min-Hung and Chen, Wenhu},
  year = {2026},
  selected = true,
  bibtex_show = false
}

NeurIPS 2026

PhyProbe: Rethinking Physical Consistency Evaluation in Generated Videos

Max Ku, Jiaojiao Fan, Zekun Hao, Francesco Ferroni, Heng Wang, Wenhu Chen, Ming-Yu Liu, and Prithvijit Chattopadhyay

In The Fortieth Annual Conference on Neural Information Processing Systems , 2026

arXiv Bib Website

@inproceedings{ku2026phyproberethinkingphysicalconsistency,
  title = {PhyProbe: Rethinking Physical Consistency Evaluation in Generated Videos},
  booktitle = {The Fortieth Annual Conference on Neural Information Processing Systems},
  author = {Ku, Max and Fan, Jiaojiao and Hao, Zekun and Ferroni, Francesco and Wang, Heng and Chen, Wenhu and Liu, Ming-Yu and Chattopadhyay, Prithvijit},
  year = {2026},
  selected = true,
  bibtex_show = false
}

Preprint

VisPhyWorld: Probing Physical Reasoning via Code-Driven Video Reconstruction

Jiarong Liang*, Max Ku*, Ka-Hei Hui, Ping Nie, and Wenhu Chen

In arXiv , 2026

arXiv Bib Code Website

@inproceedings{liang2026visphyworldprobingphysicalreasoning,
  title = {VisPhyWorld: Probing Physical Reasoning via Code-Driven Video Reconstruction},
  booktitle = {arXiv},
  author = {Liang*, Jiarong and Ku*, Max and Hui, Ka-Hei and Nie, Ping and Chen, Wenhu},
  year = {2026},
  selected = true,
  bibtex_show = false
}

ICLR 2026

ImagenWorld: Stress-Testing Image Generation Models with Explainable Human Evaluation on Open-ended Real-World Tasks

Samin Mahdizadeh Sani*, Max Ku*, Nima Jamali, Matina Mahdizadeh Sani, Paria Khoshtab, Wei-Chieh Sun, Parnian Fazel, Zhi Rui Tam, Thomas Chong, Edisy Kin Wai Chan, Donald Wai Tong Tsang, Chiao-Wei Hsu, Ting Wai Lam, Ho Yin Sam Ng, Chiafeng Chu, Chak-Wing Mak, Keming Wu, Hiu Tung Wong, Yik Chun Ho, Chi Ruan, Zhuofeng Li, I-Sheng Fang, Shih-Ying Yeh, Ho Kei Cheng, Ping Nie, and 1 more author

In The 14th International Conference on Learning Representations , 2026

arXiv Bib Code Website

@inproceedings{sani2025imagenworld,
  title = {ImagenWorld: Stress-Testing Image Generation Models with Explainable Human Evaluation on Open-ended Real-World Tasks},
  booktitle = {The 14th International Conference on Learning Representations},
  author = {Sani*, Samin Mahdizadeh and Ku*, Max and Jamali, Nima and Sani, Matina Mahdizadeh and Khoshtab, Paria and Sun, Wei-Chieh and Fazel, Parnian and Tam, Zhi Rui and Chong, Thomas and Chan, Edisy Kin Wai and Tsang, Donald Wai Tong and Hsu, Chiao-Wei and Lam, Ting Wai and Ng, Ho Yin Sam and Chu, Chiafeng and Mak, Chak-Wing and Wu, Keming and Wong, Hiu Tung and Ho, Yik Chun and Ruan, Chi and Li, Zhuofeng and Fang, I-Sheng and Yeh, Shih-Ying and Cheng, Ho Kei and Nie, Ping and Chen, Wenhu},
  year = {2026},
  selected = true,
  bibtex_show = false
}

ICLR 2026

EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editing

Keming Wu*, Sicong Jiang*, Max Ku, Ping Nie, Minghao Liu, and Wenhu Chen

In The 14th International Conference on Learning Representations , 2026

Bib Code Website

@inproceedings{wu2025editrewardhumanalignedrewardmodel,
  title = {EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editing},
  author = {Wu*, Keming and Jiang*, Sicong and Ku, Max and Nie, Ping and Liu, Minghao and Chen, Wenhu},
  booktitle = {The 14th International Conference on Learning Representations},
  year = {2026},
  eprint = {2509.26346},
  archiveprefix = {arXiv},
  primaryclass = {cs.CV},
  url = {https://arxiv.org/abs/2509.26346},
  selected = false,
  bibtex_show = false
}

2025

ICMLW 2025

DisProtEdit: Exploring Disentangled Representations for Multi-Attribute Protein Editing

Max Ku, Sun Sun, Hongyu Guo, and Wenhu Chen

In The 2nd ICML Workshop on Generative AI and Biology (GenBio) , 2025

Bib Code Website

@inproceedings{ku2025disproteditexploringdisentangledrepresentations,
  title = {DisProtEdit: Exploring Disentangled Representations for Multi-Attribute Protein Editing},
  author = {Ku, Max and Sun, Sun and Guo, Hongyu and Chen, Wenhu},
  year = {2025},
  booktitle = {The 2nd ICML Workshop on Generative AI and Biology (GenBio)},
  eprint = {2506.14853},
  archiveprefix = {arXiv},
  primaryclass = {q-bio.QM},
  url = {https://arxiv.org/abs/2506.14853},
  selected = false,
  bibtex_show = false
}

ACL 2025 Oral

TheoremExplainAgent: Towards Multimodal Explanations for LLM Theorem Understanding

Max Ku*, Thomas Chong*, Jonathan Leung, Krish Shah, Alvin Yu, and Wenhu Chen

In The 63rd Annual Meeting of the Association for Computational Linguistics , 2025

arXiv Bib Code Website

@inproceedings{ku2025theoremexplainagentmultimodalexplanationsllm,
  title = {TheoremExplainAgent: Towards Multimodal Explanations for LLM Theorem Understanding},
  booktitle = {The 63rd Annual Meeting of the Association for Computational Linguistics},
  author = {Ku*, Max and Chong*, Thomas and Leung, Jonathan and Shah, Krish and Yu, Alvin and Chen, Wenhu},
  year = {2025},
  selected = true,
  bibtex_show = false
}

2024

EMNLP 2024

VideoScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generation

Xuan He, Dongfu Jiang, Ge Zhang, Max Ku, Achint Soni, Sherman Siu, Haonan Chen, Abhranil Chandra, Ziyan Jiang, Aaran Arulraj, Kai Wang, Quy Duc Do, Yuansheng Ni, Bohan Lyu, Yaswanth Narsupalli, Rongqi Fan, Zhiheng Lyu, Yuchen Lin, and Wenhu Chen

In The Conference on Empirical Methods in Natural Language Processing , 2024

arXiv Bib Code Website

@inproceedings{he2024videoscorebuildingautomaticmetrics,
  title = {VideoScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generation},
  author = {He, Xuan and Jiang, Dongfu and Zhang, Ge and Ku, Max and Soni, Achint and Siu, Sherman and Chen, Haonan and Chandra, Abhranil and Jiang, Ziyan and Arulraj, Aaran and Wang, Kai and Do, Quy Duc and Ni, Yuansheng and Lyu, Bohan and Narsupalli, Yaswanth and Fan, Rongqi and Lyu, Zhiheng and Lin, Yuchen and Chen, Wenhu},
  booktitle = {The Conference on Empirical Methods in Natural Language Processing},
  year = {2024},
  selected = false,
  bibtex_show = false
}

NeurIPS 2024

MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark

Yubo Wang, Xueguang Ma, Ge Zhang, Yuansheng Ni, Abhranil Chandra, Shiguang Guo, Weiming Ren, Aaran Arulraj, Xuan He, Ziyan Jiang, Tianle Li, Max Ku, Kai Wang, Alex Zhuang, Rongqi Fan, Xiang Yue, and Wenhu Chen

In The Conference on Neural Information Processing Systems , 2024

arXiv Bib Code

@inproceedings{wang2024mmlupro,
  title = {MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark},
  author = {Wang, Yubo and Ma, Xueguang and Zhang, Ge and Ni, Yuansheng and Chandra, Abhranil and Guo, Shiguang and Ren, Weiming and Arulraj, Aaran and He, Xuan and Jiang, Ziyan and Li, Tianle and Ku, Max and Wang, Kai and Zhuang, Alex and Fan, Rongqi and Yue, Xiang and Chen, Wenhu},
  year = {2024},
  booktitle = {The Conference on Neural Information Processing Systems},
  selected = false,
  bibtex_show = false
}

NeurIPS 2024

GenAI Arena: An Open Evaluation Platform for Generative Models

Dongfu Jiang*, Max Ku*, Tianle Li*, Yuansheng Ni, Shizhuo Sun, Rongqi Fan, and Wenhu Chen

In The Conference on Neural Information Processing Systems , 2024

arXiv Bib Website

@inproceedings{jiang2024genai,
  title = {GenAI Arena: An Open Evaluation Platform for Generative Models},
  author = {Jiang*, Dongfu and Ku*, Max and Li*, Tianle and Ni, Yuansheng and Sun, Shizhuo and Fan, Rongqi and Chen, Wenhu},
  year = {2024},
  booktitle = {The Conference on Neural Information Processing Systems},
  selected = true,
  bibtex_show = false
}

TMLR 2024

MANTIS: Interleaved Multi-Image Instruction Tuning

Dongfu Jiang, Xuan He, Huaye Zeng, Cong Wei, Max Ku, Qian Liu, and Wenhu Chen

Transactions on Machine Learning Research, 2024

arXiv Bib Code Website

@article{jiang2024mantis,
  title = {MANTIS: Interleaved Multi-Image Instruction Tuning},
  author = {Jiang, Dongfu and He, Xuan and Zeng, Huaye and Wei, Cong and Ku, Max and Liu, Qian and Chen, Wenhu},
  journal = {Transactions on Machine Learning Research},
  year = {2024},
  selected = false,
  bibtex_show = false
}

TMLR 2024

AnyV2V: A Tuning-Free Framework For Any Video-to-Video Editing Tasks

Max Ku*, Cong Wei*, Weiming Ren*, Harry Yang, and Wenhu Chen

Transactions on Machine Learning Research, 2024

arXiv Bib Code Website

@article{ku2024anyv2v,
  title = {AnyV2V: A Tuning-Free Framework For Any Video-to-Video Editing Tasks},
  author = {Ku*, Max and Wei*, Cong and Ren*, Weiming and Yang, Harry and Chen, Wenhu},
  journal = {Transactions on Machine Learning Research},
  year = {2024},
  selected = true,
  bibtex_show = false
}

ACL 2024

VIEScore: Towards Explainable Metrics for Conditional Image Synthesis Evaluation

Max Ku, Dongfu Jiang, Cong Wei, Xiang Yue, and Wenhu Chen

In The 62nd Annual Meeting of the Association for Computational Linguistics , 2024

arXiv Bib Code Website

@inproceedings{Ku2023VIEScoreTE,
  title = {VIEScore: Towards Explainable Metrics for Conditional Image Synthesis Evaluation},
  author = {Ku, Max and Jiang, Dongfu and Wei, Cong and Yue, Xiang and Chen, Wenhu},
  booktitle = {The 62nd Annual Meeting of the Association for Computational Linguistics},
  year = {2024},
  selected = true,
  bibtex_show = false
}

ICLR 2024

ImagenHub: Standardizing the evaluation of conditional image generation models

Max Ku, Tianle Li, Kai Zhang, Yujie Lu, Xingyu Fu, Wenwen Zhuang, and Wenhu Chen

In The 12th International Conference on Learning Representations , 2024

arXiv Bib Code Website

@inproceedings{ku2024imagenhub,
  title = {ImagenHub: Standardizing the evaluation of conditional image generation models},
  author = {Ku, Max and Li, Tianle and Zhang, Kai and Lu, Yujie and Fu, Xingyu and Zhuang, Wenwen and Chen, Wenhu},
  booktitle = {The 12th International Conference on Learning Representations},
  year = {2024},
  twitter = {https://twitter.com/vinesmsuic/status/1717564355212951701},
  selected = false,
  bibtex_show = false
}

2023

TMLR 2023

DreamEdit: Subject-driven Image Editing

Tianle Li, Max Ku*, Cong Wei*, and Wenhu Chen

In Transactions on Machine Learning Research , 2023

arXiv Bib Code Website

@inproceedings{li2023dreamedit,
  title = {DreamEdit: Subject-driven Image Editing},
  author = {Li, Tianle and Ku*, Max and Wei*, Cong and Chen, Wenhu},
  booktitle = {Transactions on Machine Learning Research},
  year = {2023},
  selected = false,
  bibtex_show = false
}

EMNLP 2023

TheoremQA: A Theorem-driven Question Answering dataset

Wenhu Chen, Ming Yin, Max Ku, Yixin Wan, Xueguang Ma, Jianyu Xu, Tony Xia, Xinyi Wang, and Pan Lu

In The Conference on Empirical Methods in Natural Language Processing , 2023

arXiv Bib

@inproceedings{chen2023theoremqa,
  title = {TheoremQA: A Theorem-driven Question Answering dataset},
  author = {Chen, Wenhu and Yin, Ming and Ku, Max and Wan, Yixin and Ma, Xueguang and Xu, Jianyu and Xia, Tony and Wang, Xinyi and Lu, Pan},
  booktitle = {The Conference on Empirical Methods in Natural Language Processing},
  year = {2023},
  selected = false,
  bibtex_show = false
}

ICIP 2023

Intelligent Painter: Picture Composition with Resampling Diffusion Model

Max Ku, Wan-Chi Siu, Xi Cheng, and H. Anthony Chan

In The International Conference on Image Processing , 2023

arXiv Bib Code

@inproceedings{ku2023ipainter,
  author = {Ku, Max and Siu, Wan-Chi and Cheng, Xi and Chan, H. Anthony},
  year = {2023},
  pages = {2255-2259},
  title = {Intelligent Painter: Picture Composition with Resampling Diffusion Model},
  doi = {10.1109/ICIP49359.2023.10222829},
  booktitle = {The International Conference on Image Processing},
  selected = false,
  bibtex_show = false
}