Publications

2025

  1. The Mechanistic Emergence of Symbol Grounding in Language Models
    Wu, Shuyu, Ma, Ziqiao, Luo, Xiaoxi, Huang, Yidong, Torres-Fonseca, Josue, Shi, Freda, and Chai, Joyce
    arXiv preprint arXiv:2510.13796, 2025
  2. Planning with Sketch-Guided Verification for Physics-Aware Video Generation
    Huang, Yidong, Wang, Zun, Lin, Han, Kim, Dong-Ki, Omidshafiei, Shayegan, Yoon, Jaehong, Zhang, Yue, and Bansal, Mohit
    arXiv preprint arXiv:2511.17450, 2025

2024

  1. Inversion-free image editing with language-guided diffusion models
    Xu, Sihan, Huang, Yidong, Pan, Jiayi, Ma, Ziqiao, and Chai, Joyce
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9452–9461, 2024
  2. Drivlme: Enhancing llm-based autonomous driving agents with embodied and social experiences
    Huang, Yidong, Sansom, Jacob, Ma, Ziqiao, Gervits, Felix, and Chai, Joyce
    In 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3153–3160, 2024

2023

  1. A-ESRGAN: Training real-world blind super-resolution with attention U-Net Discriminators
    Wei, Zihao, Huang, Yidong, Chen, Yuang, Zheng, Chenhao, and Gao, Jingnan
    In Pacific Rim International Conference on Artificial Intelligence, pp. 16–27, 2023
  2. CycleNet: Rethinking Cycle Consistency in Text-Guided Diffusion for Image Manipulation
    Xu, Sihan, Ma, Ziqiao, Huang, Yidong, Lee, Honglak, and Chai, Joyce
    In Thirty-seventh Conference on Neural Information Processing Systems, 2023

2022

  1. DOROTHIE: Spoken Dialogue for Handling Unexpected Situations in Interactive Autonomous Driving Agents
    Ma, Ziqiao, VanDerPloeg, Benjamin, Bara, Cristian-Paul, Huang, Yidong, Kim, Eui-In, Gervits, Felix, Marge, Matthew, and Chai, Joyce
    In Findings of the Association for Computational Linguistics: EMNLP 2022, pp. 4800–4822, 2022
  2. Discovering Intrinsic Reward with Contrastive Random Walk
    Pan, Zixuan, Wei, Zihao, Huang, Yidong, and Gupta, Aditya
    2022
    [URL] [DOI]