Qian Cao

曹乾 | a.k.a Aman | Be a voice, not an echo.

profile.png

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 centers on building intelligent systems that integrate multimodal understanding, creative reasoning, and open-domain generation, with a focus on advancing both the controllability and applicability of AI in real-world scenarios.

Main Research Interests:

  • Creative AI: Developing and evaluating LLMs for controllable and human-like creative text generation.

  • Multimodal Understanding & Interaction: Exploring vision-language interplay and building multimodal LLMs with stronger cross-modal reasoning abilities.

  • Applied LLM Systems: Constructing efficient and domain-specific LLM systems, from foundational models to knowledge-augmented applications.

My long-term goal is to develop AI systems that seamlessly unify perception, knowledge, and creativity, enabling machines not only to understand the world, but also to generate meaningful and creative content across modalities.

News

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] !
Oct 10, 2024 Our work Understanding the Roles of Visual Modality in Multimodal Dialogue: An Empirical Study was accepted by MMM 2025!
Sep 21, 2024 Our work BSharedRAG: Backbone Shared Retrieval-Augmented Generation for the E-commerce Domain was accepted by EMNLP 2024 Findings!
Jul 16, 2024 Our work See or Guess: Counterfactually Regularized Image Captioning was accepted by ACM MM 2024!

Selected Publications

  1. 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
    arXiv preprint arXiv:2601.09609 2026
  2. 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
    arXiv preprint arXiv:2505.19236 2025
  3. BSharedRAG: Backbone Shared Retrieval-Augmented Generation for the E-commerce Domain
    Kaisi Guan, Qian Cao, Yuchong Sun, Xiting Wang, and Ruihua Song
    In Findings of the Association for Computational Linguistics: EMNLP 2024, Nov 2024
  4. 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
  5. YuLan: An Open-source Large Language Model
    Yutao Zhu, Kun Zhou, Kelong Mao, Wentong Chen, Yiding Sun, Zhipeng Chen, Qian Cao, Yihan Wu, Yushuo Chen, Feng Wang, and  others
    arXiv preprint arXiv:2406.19853 Oct 2024
  6. 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

Experiences

2025.6 - 2026.1 Foundation LLM Team @ kuaishou PNG Image, 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_logo PNG Image 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_logo PNG Image RUC Teaching Assistant

Services

Conference Reviewer: ICLR'25, MM'24-25, ACL ARR'24-25, EMNLP'23, COLING'25
Journal Reviewer: Discover Computing