Yicheng Xiao

About Me

I will be a PhD student at The University of Hong Kong, supervised by Prof. Xiaojuan Qi. Previously, I obtained my MSc at Tsinghua University in 2026, under the supervision of Prof. Xiu Li, and my BSc at Xidian University in 2023. I am fortunate to be collaborating closely with Dr. Lin Song and Dr. Yukang Chen on Vision Language Models and Generative AI.

News

[2026.08] We are excited to release the project, JoyAI-Video-Edit

[2026.06] Obtain Outstanding Graduate Award, Tsinghua University

[2026.04] We are excited to release the project, JoyAI-Image

[2026.04] We are excited to release the project, SpatialEdit

[2026.01] The paper LongLive and QeRL are accepted by ICLR 2026 (CCF-A)

[2025.10] Obtain National Scholarship, Tsinghua University

[2025.09] The paper MindOmni is accepted by NeurIPS 2025 (CCF-A)

[2025.09] The Paper SOC++ is accepted by TPAMI 2025 (CCF-A)

[2025.06] We are excited to release the project, MindOmni

[2025.05] Two papers, LoRA-Gen and HaploVLM are accepted by ICML 2025 (CCF-A)

[2024.10] Obtain National Scholarship, Tsinghua University

[2024.06] Two papers, MambaTree (Spotlight) and COVE are accepted by NeurIPS 2025 (CCF-A)

[2024.03] The paper UVCOM is accepted by CVPR 2024 (CCF-A)

[2023.09] The paper SOC is accepted by NeurIPS 2023 (CCF-A)

[2023.09] The first prize of The 5th Large-scale Video Object Segmentation Challenge Track3: Referring Video Object Segmentation

[2023.03] The paper SemanticAC is accepted by ICASSP 2023 (CCF-B)

[2021.12] Obtain National Scholarship, Xidian University

Academic experience

2026-Present

Studying as a PhD Student at The University of Hong Kong

2023-2026

Studying as a Master Student at Tsinghua University

2019-2023

Studying as an Undergraduate Student at Xidian University

Industrial experience

	2025.12-Present I am a multimodal fundamental architecture research intern supervised by Dr. Lin Song and Dr. Nan Duan at JD Exploration Institute
	2024.06-2025.11 I am a multimodal algorithm research intern supervised by Dr. Lin Song and Dr. Ying Shan at Tencent ARC Lab
	2024.01-2024.06 I am a multimodal algorithm research intern supervised by Dr. Lin Song at Tencent AI Lab
	2022.12-2023.3 I am a multimodal algorithm research intern at OPPO Research Institute

Honors and Awards

[2026] Outstanding Graduate, Tsinghua University

[2025] National Scholarship for Master's Students, Tsinghua University

[2024] National Scholarship for Master's Students, Tsinghua University

[2022] National Scholarship for Undergraduate Students, Xidian University

Publications [full list]

JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusion

Core Contributor (First Author, Co-lead of JoyAI-Video-Edit)

Technical Report / Paper / Code

JoyAI-Image: Awakening Spatial Intelligence in Unified Multimodal Understanding and Generation

Core Contributor (Lead of JoyAI-Image-Edit)

Technical Report / Paper / Code

SpatialEdit: Benchmarking Fine-Grained Image Spatial Editing

Yicheng Xiao, Wenhu Zhang, Lin Song, Yukang Chen, Wenbo Li, Nan Jiang, Tianhe Ren, Haokun Lin, Wei Huang, Haoyang Huang, Xiu Li, Nan Duan, and Xiaojuan Qi

Under Review / Paper / Code

MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO

Yicheng Xiao, Lin Song, Yukang Chen, Yingmin Luo, Yuxin Chen, Yukang Gan, Wei Huang, Xiu Li, Xiaojuan Qi, Ying Shan

NeurIPS 2025 / Paper / Code

HaploOmni: Unified Single Transformer for Multimodal Video Understanding and Generation

Yicheng Xiao*, Lin Song*, Rui Yang, Cheng Cheng, Zunnan Xu, Zhaoyang Zhang, Yixiao Ge, Xiu Li, Ying Shan (* equal contribution)

Under Review / Paper / Code

LoRA-Gen: Specializing Language Model via Online LoRA Generation

Yicheng Xiao*, Lin Song*, Rui Yang, Cheng Cheng, Yixiao Ge, Xiu Li, Ying Shan (* equal contribution)

ICML 2025 (CCF-A) / Paper / Code

MambaTree: Tree Topology is All You Need in State Space Model

Yicheng Xiao*, Lin Song*, Shaoli Huang, Jiangshan Wang, Siyu Song, Yixiao Ge, Xiu Li, Ying Shan (* equal contribution)

NeurIPS 2024 Spotlight (CCF-A) / Paper / Code

Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight Detection

Yicheng Xiao*,Zhuoyan Luo*, Yong Liu, Yue Ma, Hengwei Bian, Yatai Ji, Yujiu Yang, Xiu Li (* equal contribution)

CVPR 2024 (CCF-A) / Paper / Code

SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation

Zhuoyan Luo*, Yicheng Xiao*, Yong Liu*, Shuyan Li, Yitong Wang, Yansong Tang, Xiu Li, Yujiu Yang (* equal contribution)

NeurIPS 2023 (CCF-A) / Paper / Code

Thanks Jon Barron for this template.