Qian Cao

I am a PhD student at Gaoling School of Artificial Intelligence (GSAI), Renmin University of China (RUC). I am advised by Prof. Ruihua Song. Prior to this, I graduated from School of Information and Gaoling School of Artificial Intelligence, Renmin University of China where I obtained my bachelor’s degree and master’s degree in 2020 and 2023, respectively.

My research and long-term goal center on building AI systems that seamlessly integrate open-domain reasoning, creativity, and multimodal understanding, enabling machines not only to understand the world, but also to generate meaningful and creative content across modalities.

Main Research Interests:

Creative AI: Developing and evaluating LLMs for controllable and human-like creative text generation.
Agentic LLM Systems: Constructing efficient agentic LLM systems, from foundational models to knowledge-augmented applications.
Multimodal Understanding: Exploring vision-language interplay and building multimodal LLMs with stronger cross-modal reasoning abilities.

I will graduate in 2027 and am currently seeking full-time opportunities in both industry and academia. Please feel free to reach out at caoqian4real@ruc.edu.cn.

News

May 1, 2026	🎉🎉🎉 Our work Restoring Exploration after Post-Training: Latent Exploration Decoding for Large Reasoning Models was accepted by ICML 2026!
Apr 7, 2026	🎉🎉🎉 Our work DPWriter: Reinforcement Learning with Diverse Planning Branching for Creative Writing was accepted by ACL 2026 main conference (Oral, 4.5%)!
Jan 26, 2026	🎉🎉🎉 Our work Evaluating Text Creativity across Diverse Domains: A Dataset and Large Language Model Evaluator was accepted by ICLR 2026!
Jan 15, 2026	Our new work DPWriter: Reinforcement Learning with Diverse Planning Branching for Creative Writing is now available! Check it out on [arXiv] !
Jun 9, 2025	Joined the foundation LLM team at Kuaishou Technology as a research intern!
May 25, 2025	Our new work Evaluating Text Creativity across Diverse Domains: A Dataset and Large Language Model Evaluator is now available! Check it out on [arXiv] to explore our dataset [CreataSet] and out creativity evaluator [CrEval] !

Selected Publications

ACL 2026
(Oral, 4.5%)

DPWriter: Reinforcement Learning with Diverse Planning Branching for Creative Writing

Qian Cao, Yahui Liu, Wei Bi, Yi Zhao, Ruihua Song, Xiting Wang, Ruiming Tang, Guorui Zhou, and Han Li

In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics, 2026

Bib arXiv PDF Overview

@inproceedings{cao2026dpwriter,
  title = {DPWriter: Reinforcement Learning with Diverse Planning Branching for Creative Writing},
  author = {Cao, Qian and Liu, Yahui and Bi, Wei and Zhao, Yi and Song, Ruihua and Wang, Xiting and Tang, Ruiming and Zhou, Guorui and Li, Han},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics,},
  year = {2026},
}

ICLR 2026

Evaluating Text Creativity across Diverse Domains: A Dataset and Large Language Model Evaluator

Qian Cao, Xiting Wang, Yuzhuo Yuan, Yahui Liu, Fang Luo, and Ruihua Song

In Proceedings of the 14th International Conference on Learning Representations, Jan 2026

Bib arXiv PDF Overview Project Page

@inproceedings{cao2025evaluating,
  title = {Evaluating Text Creativity across Diverse Domains: A Dataset and Large Language Model Evaluator},
  author = {Cao, Qian and Wang, Xiting and Yuan, Yuzhuo and Liu, Yahui and Luo, Fang and Song, Ruihua},
  booktitle = {Proceedings of the 14th International Conference on Learning Representations,},
  year = {2026},
  month = jan,
}

ACM MM 2024

See or Guess: Counterfactually Regularized Image Captioning

Qian Cao, Xu Chen, Ruihua Song, Xiting Wang, Xinting Huang, and Yuchen Ren

In Proceedings of the 32th ACM international conference on Multimedia, Oct 2024

Bib arXiv PDF Overview

@inproceedings{Cao2024SeeOrGuess,
  title = {See or Guess: Counterfactually Regularized Image Captioning},
  author = {Cao, Qian and Chen, Xu and Song, Ruihua and Wang, Xiting and Huang, Xinting and Ren, Yuchen},
  booktitle = {Proceedings of the 32th ACM international conference on Multimedia,},
  year = {2024},
  month = oct,
  doi = {10.1145/3664647.3681458},
}

ACM MM 2022
(Oral, 5.1%)

Multi-Modal Experience Inspired AI Creation

Qian Cao, Xu Chen, Ruihua Song, Hao Jiang, Guang Yang, and Zhao Cao

In Proceedings of the 30th ACM international conference on Multimedia, Oct 2022

Bib arXiv PDF Overview

@inproceedings{Cao2022MultiModalEI,
  title = {Multi-Modal Experience Inspired AI Creation},
  author = {Cao, Qian and Chen, Xu and Song, Ruihua and Jiang, Hao and Yang, Guang and Cao, Zhao},
  booktitle = {Proceedings of the 30th ACM international conference on Multimedia,},
  year = {2022},
  month = oct,
  doi = {10.1145/3503161.3548189},
}

Experiences

2025.6 - 2026.1	Foundation LLM Team @ , Kuaishou	Research Intern
2022.6 - 2023.3.6	AI Lab NLP Center @ , Tencent	Research Intern
2020.9 - Now	AIMind Group @ Beijing Key Lab of Big Data Management and Analysis, RUC	Research Assistant
2021.6 - 2022.2	Bing powered Xiaoice, Software Technology Center at Asia @ , Microsoft	Research Intern
2021.9 - 2021.12	Gaoling School of Artificial Intelligence, RUC	Teaching Assistant

Services

Conference PC Member/Reviewer: ICML'26, ICLR'26, MM'24-26, ACL ARR'24-26, EMNLP'23, COLING'25
Journal Reviewer: Chinese Journal of Computers, Discover Computing