Xili Dai

Xili(Daley) Dai

daixili_cs AT 163.com; daixili.cs AT gmail.com

I got my Ph.D. degree from HKUST(GZ), advised by Prof. Harry Shum (former vice president of Microsoft) and Prof. Lionel Ni (president of HKUST-gz) of HKUST(GZ). I also spent three years as visiting PhD student at UC Berkeley advised by Prof.Yi Ma. My research interests lying on the intersection among 3D Generation/Reconstruction, video Generation/Reconstruction, Sparse Coding/Low-rank decomposition.

I am glad to chat about research, advising, collaborations. If you are interested in doing research with me, feel free to contact me.

Google Scholar / Github

Selected Publication (* means equal contribution)

	Training-Free Text-Guided Color Editing with Multi-Modal Diffusion Transformer Zixin Yin, Xili Dai, Ling-Hao Chen, Deyu Zhou, Jianan Wang, Duomin Wang, Gang Yu, Lionel M. Ni, Lei Zhang, Heung-Yeung Shum ICLR 2026 [Project Page] [paper]
	LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit Correspondence Zixin Yin, Xili Dai, Duomin Wang, Xianfang Zeng, Lionel M. Ni, Gang Yu, Heung-Yeung Shum ICLR 2026 [Project Page] [paper]
	UniVerse-1: Unified Audio-Video Generation via Stitching of Experts Duomin Wang, Wei Zuo, Aojie Li, Ling-Hao Chen, Xinyao Liao, Deyu Zhou, Zixin Yin, Xili Dai, Daxin Jiang, Gang Yu arXiv, 2509.06155, [PDF] [Project] [Code] [Model weights] [Verse-Bench] We introduce UniVerse-1, a unified, Veo-3-like model capable of simultaneously generating coordinated audio and video. To enhance training efficiency, we bypass training from scratch and instead employ a stitching of expertise technique.
	SpeakerVid-5M: A Large-Scale High-Quality Dataset for audio-visual Dyadic Interactive Human Generation Youliang Zhang, Zhaoyang Li, Duomin Wang, Jiahe Zhang, Deyu Zhou, Zixin Yin, Xili Dai, Gang Yu, Xiu Li ICLR 2026 [Project Page] [paper]
	ConsistEdit: Highly Consistent and Precise Training-free Visual Editing Zixin Yin, Ling-Hao Chen, Lionel M. Ni, Xili Dai SIGGRAPH Asia 2025 [Project Page] [paper]
	Unposed Sparse Views Room Layout Reconstruction in the Age of Pretrain Model Yaxuan Huang, Xili Dai, Jianan Wang, Xianbiao Qi, Yixing Yuan, Xiangyu Yue ICLR 2025 [code] [paper]
	Taming Transformer Without Using Learning Rate Warmup Xianbiao Qi, Yelin He, Jiaquan Ye, ChunGuang Li, Bojia Zi, Xili Dai, Qin Zou, Rong Xiao ICLR 2025 [code] [paper]
	Bifrost: 3D-Aware Image compositing with Language Instructions Lingxiao Li, Kaixiong Gong, Weihong Li, Tao Chen, Xili Dai, Xiaojun Yuan, Xiangyu Yue NeurIPS 2024 [code] [paper]
	Ctrl123: Consistent Novel View Synthesis via Closed-Loop Transcription Hongxiang Zhao, Xili Dai, Jianan Wang, Shengbang Tong, Jingyuan Zhang, Weida Wang, Lei Zhang, Yi Ma Tech Report [code] [paper]
	Anti-Collapse Loss for Deep Metric Learning Based on Coding Rate Metric Xiruo Jiang, Yazhou Yao, Xili Dai, Fumin Shen, Liqiang Nie, Heng-Tao Shen IEEE Transactions on Multimedia 2024 [code] [paper]
	Image Clustering via the Principle of Rate Reduction in the Age of Pretrained Models Tianzhe Chu, Shengbang Tong, Tianjiao Ding, Xili Dai, Benjamin David Haeffele, Rene Vidal, Yi Ma ICLR 2024 [code] [paper]
	Unsupervised Learning of Structured Representation via Closed-Loop Transcription Shengbang Tong, Xili Dai, Yubei Chen, Mingyang Li, Zengyi Li, Brent Yi, Yann Lecun, Yi Ma CPAL 2024 [code] [paper]
	Closed-Loop Transcription Via Convolutional Sparse Coding Xili Dai, Ke Chen, Shengbang Tong, Jingyuan Zhang, Xingjian Gao, Mingyang Li, Druv Pai, Yuexiang Zhai, Xiaojun Yuan, Heung Yeung Shum, Lionel M.Ni, Yi Ma CPAL 2024 [code] [paper]
	Incremental Learning of Structured Memory via Closed-Loop Transcription Peter(Shengbang) Tong, Xili Dai, Ziyang Wu, Mingyang Li, Brent Yi, Yi Ma ICLR 2023 [code] [paper]
	Unsupervised Manifold Linearizing and Clustering Tianjiao Ding, Shengbang Tong, Kwan Ho Ryan Chan, Xili Dai, Yi Ma, Benjamin David Haeffele ICCV 2023 [code] [paper]
	Revisiting Sparse Convolutional Model for Visual Recognition Xili Dai, Mingyang Li, Pengyuan Zhai, Peter(Shengbang) Tong, Xingjian Gao, Shao-Lun Huang, Zhihui Zhu, Chong You, Yi Ma NeurIPS 2022 [code] [paper]
	Deep Metric Learning with Meta-Mining Strategy With Semiglobal Information Xiruo Jiang, Sheng Liu, Xili Dai, Guosheng Hu, Xingguo Huang, Yazhou Yao, Guo-Sen Xie, Ling Shao IEEE Transactions on Neural Networks and Learning Systems 2022 [code] [paper]
	Closed-Loop Data Transcription to an LDR via Minimaxing Rate Reduction Xili Dai, Peter(Shengbang) Tong, Mingyang Li, Ziyang Wu, Kwan Ho Ryan Chan, Pengyuan Zhai, Yaodong Yu, Michael Psenka, Xiaojun Yuan, Heung Yeung Shum, Yi Ma Entropy Journal 2022 [code] [paper]
	Learning to Reconstruct 3D Non-Cuboid Room Layout from a Single RGB Image Cheng Yang, Jia Zheng, Xili Dai, Rui Tang, Yi Ma, Xiaojun Yuan WACV 2022 [code] [paper]
	Fully Convolutional Line Parsing Xili Dai, Haigang Gong, Shuai Wu, Xiaojun, Yuan, Yi Ma NeuroComputing 2022 [code] [paper]
	HoliCity: A City-Scale Data Platform for Learning Holistic 3D Structures Yichao Zhou, Jingwei Huang, Xili Dai, Linjie Luo, Zhili Chen, Yi Ma [code] [paper] [Project Page]
	Understanding pictograph with facial features: End-to-end sentence-level lip reading of chinese Xiaobing Zhang, Haigang Gong, Xili Dai, Fan Yang, Nianbo Liu, Ming Liu AAAI 2019 [paper]
	DrivingSense: Dangerous Driving Behavior Identification Based on Smartphone Autocalibration Chunmei Ma, Xili Dai, Jinqi Zhu, Nianbo Liu, Huazhi Sun, Ming Liu Mobile Information System 2017 [paper]