Yiran Guan | Huazhong University of Science and Technology

About Me

I am a Master’s student in the School of Software Engineering at Huazhong University of Science and Technology (HUST), working under the supervision of Prof. Xiang Bai. Before starting my graduate studies, I earned my Bachelor’s degree from HUST’s School of Artificial Intelligence and Automation, where I was advised by Prof. Yang Xiao.

Research Interests

LLM: reasoning, test-time-scaling, self-evolving, memory.
Multi-modal understanding: omni-modal understanding, video understanding.

News

[Jan. 2026] NEW paper VST has been released!
[Jan. 2026] Two paper about multi-modal reasoning llm has been accept by ICLR 2026.
[Mar. 2025] Start my internship at Xiaomi Inc.
[Sep. 2024] One paper about mixture of expert has been accept by NeurIPS 2024.
[Sep. 2024] I won 2nd place in Track 1 of The First Dataset Distillation Challenge @ ECCV 2024. At the same time, I was invited to give an oral presentation of my workshop paper.
[Oct. 2023] One paper about video gaze estimation has been accepted by IEEE SPL.

Publications

(*Equal contribution, †Corresponding authors)

ArXiv

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously

Yiran Guan*, Liang Yin*, Dingkang Liang, Jianzhong Ju, Zhenbo Luo, Jian Luan, Yuliang Liu, Xiang Bai†

ArXiv, 2603

Code

ICLR

ThinkOmni: Lifting Textual Reasoning to Omni-modal Scenarios via Guidance Decoding

Yiran Guan, Sifan Tu, Dingkang Liang, Linghao Zhu, Jianzhong Ju, Zhenbo Luo, Jian Luan, Yuliang Liu, Xiang Bai†

ICLR, 2026.

PDF Code

ICLR

Shuffle-R1: Efficient RL framework for Multimodal Large Language Models via Data-centric Dynamic Shuffle

Linghao Zhu, Yiran Guan, Dingkang Liang, Jianzhong Ju, Zhenbo Luo, Bin Qin, Jian Luan, Yuliang Liu, Xiang Bai†

ICLR, 2026.

PDF Code

NeurIPS

MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks

Xingkui Zhu*, Yiran Guan*, Dingkang Liang, Yuchao Chen, Yuliang Liu, Xiang Bai†

NeurIPS, 2024.

PDF Code BibTex

ECCV_DD

Well Begun is Half Done: The Importance of Initialization in Dataset Distillation

Yiran Guan, Zhu Chen, Xingkui Zhu, Dingkang Liang, Yuliang Liu, Xiang Bai†

ECCV workshop on Dataset Distillation, 2024.

PDF Oral

IEEE SPL

End-to-end Video Gaze Estimation via Capturing Head-face-eye Spatial-temporal Interaction Context

Yiran Guan*, Zhuoguang Chen*, Wenzheng Zeng†, Zhiguo Cao, Yang Xiao†

IEEE Signal Processing Letters, 2023.

PDF Code BibTex

Services

Conference Reviewers

ICLR'26, IJCAI'26, ICML'26, BMVC'26
CVPR'25, AAAI'25, IJCAI'25