| CARVIEW |
Bio
I am currently a Research Fellow at the LV-Lab, National University of Singapore, working under the supervision of Prof. Shuicheng Yan. Prior to this, I spent a wonderful year as a Postdoctoral Fellow at MMLab, The Chinese University of Hong Kong, under the guidance of Prof. Hongsheng Li. I completed my PhD at Beihang University (BUAA) in 2023, where I was supervised by Prof. Si Liu. Prior to my PhD, I gained valuable industry experience as a Research Intern at Alibaba Group and SenseTime Ltd. I pursued my Master's degree at the University of Chinese Academy of Sciences (UCAS), under the guidance of Prof. Si Liu. I obtained my Bachelor's degree from Northeastern University, China.
My research interests include Multi-modality understanding and Embodied AI.
Latest News
- 2025/09 Three papers were accepted to NeurIPS 2025.
- 2025/09 We release SAIL-VL2, a efficient yet powerful MLLM.
- 2025/08 We release Genie-Envisioner, a unified world foundation platform for robotic manipulation.
- 2025/06 Two papers were accepted to ICCV 2025.
- 2025/05 Two co-authored papers were accepted by Advanced Science and IEEE RAL, respectively.
- 2025/02 One paper for Video CoT accepted to CVPR 2025 selected as Oral
- 2025/01 Three papers accepted to ICLR 2025
- 2022/06 A paper on Visual Grounding was accepted to TIP
- 2022/03 A paper on HOI Detection was accepted to CVPR 2022
- 2021/09 A paper on HOI Detection was accepted to NeurIPS 2021
- 2021/06 1st place in the CVPR2021 ActivityNet Homage challenge
- 2021/03 A paper on HOI Detection was accepted to CVPR 2021
- 2021/02 The 3rd Person in Context (PIC) Workshop will be held at CVPR 2021
- 2020/02 Three papers were accepted to CVPR 2020
- 2019/10 I am co-organizing the 2nd Person in Context (PIC) Workshop at ICCV 2019
- 2018/09 I am a co-organizer of the Person in Context (PIC) Workshop at ECCV 2018
Technical Report
Publications
Instruction-Oriented Preference Alignment for Enhancing Multi-Modal Comprehension Capability of MLLMs
Zitian Wang, Yue Liao†, Kang Rong, Fengyun Rao, Yibo Yang†, Si Liu
ICCV 2025
From reflection to perfection: Scaling inference-time optimization for text-to-image diffusion models via reflection tuning
Le Zhuo, Liangbing Zhao, Sayak Paul, Yue Liao, Renrui Zhang, Yi Xin, Peng Gao, Mohamed Elhoseiny, Hongsheng Li
ICCV 2025
Perovskite Neuromorphic Engine for Transformer Architectures
Zhenye Zhan, Yulu Gao, Yue Liao, Weiguang Xie, Si Liu, Xiaomu Wang
Advanced Science 2025
Contrastive Learning-Based Secure Unsupervised Domain Adaptation Framework and Its Application in Cross-Factory Intelligent Manufacturing
Zeyi Liu, Weihua Gui, Keke Huang, Dehao Wu, Yue Liao, Chunhua Yang
IEEE RA-L 2025
VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection
Songhao Han, Wei Huang, Hairong Shi, Le Zhuo, Xiu Su, Shifeng Zhang, Xu Zhou, Xiaojuan Qi, Yue Liao†, Si Liu†
CVPR 2025
LLaVA-MoD: Making LLaVA Tiny via MoE Knowledge Distillation
Fangxun Shu*, Yue Liao*, Le Zhuo, Chenning Xu, Lei Zhang, Guanghao Zhang, Haonan Shi, Long Chen, Tao Zhong, Wanggui He, Siming Fu, Haoyuan Li, Bolin Li, Zhelun Yu, Si Liu, Hongsheng Li, Hao Jiang
ICLR 2025
MC-MoE: Mixture Compressor for Mixture-of-Experts LLMs Gains More
Wei Huang*, Yue Liao*, Jianhui Liu, Ruifei He, Haoru Tan, Shiming Zhang, Hongsheng Li, Si Liu, Xiaojuan Qi
ICLR 2025
Towards Realistic UAV Vision-Language Navigation: Platform, Benchmark, and Methodology
Xiangyu Wang, Donglin Yang, Ziqin Wang, Hohin Kwan, Jinyu Chen, Wenjun Wu, Hongsheng Li, Yue Liao†, Si Liu†
ICLR 2025
Anchor3DLane++: 3D Lane Detection via Sample-Adaptive Sparse 3D Anchor Regression
Shaofei Huang, Zhenwei Shen, Zehao Huang, Yue Liao, Jizhong Han, Naiyan Wang, Si Liu
IEEE TPAMI 2025
LaMI-DETR: Open-Vocabulary Detection with Language Model Instruction
Penghui Du, Yu Wang, Yifan Sun, Luting Wang, Yue Liao, Gang Zhang, Errui Ding, Yan Wang, Jingdong Wang, Si Liu
ECCV 2024
Mask-Enhanced Segment Anything Model for Tumor Lesion Semantic Segmentation
Hairong Shi, Songhao Han, Shaofei Huang, Yue Liao, Guanbin Li, Xiangxing Kong, Hua Zhu, Xiaomu Wang, Si Liu
MICCAI 2024
PPDM++: Parallel Point Detection and Matching for Fast and Accurate HOI Detection
Yue Liao, Si Liu, Yulu Gao, Aixi Zhang, Zhimin Li, Fei Wang, Bo Li
IEEE TPAMI 2024
MAC: Masked Contrastive Pre-Training for Efficient Video-Text Retrieval
Fangxun Shu, Biaolong Chen, Yue Liao†, Jinqiao Wang, Si Liu
IEEE TMM 2024
DiffDance: Cascaded Human Motion Diffusion Model for Dance Generation
Qiaosong Qi, Le Zhuo, Aixi Zhang, Yue Liao, Fei Fang, Si Liu, Shuicheng Yan
ACM MM 2023
Video Background Music Generation: Dataset, Method and Evaluation
Le Zhuo, Zhaokai Wang, Baisen Wang, Yue Liao†, Chenxi Bao, Stanley Peng, Songhao Han, Aixi Zhang, Fei Fang, Si Liu
ICCV 2023
Object-Aware Distillation Pyramid for Open-Vocabulary Object Detection
Luting Wang, Yi Liu, Penghui Du, Zihan Ding, Yue Liao†, Qiaosong Qi, Biaolong Chen, Si Liu
CVPR 2023
Simultaneously Training and Compressing Vision-and-Language Pre-Training Model
Qiaosong Qi, Aixi Zhang, Yue Liao†, Wenyu Sun, Yongliang Wang, Xiaobo Li, Si Liu
IEEE TMM 2023
HEAD: Hetero-Assists Distillation for Heterogeneous Object Detectors
Luting Wang, Xiaojie Li, Yue Liao†, Zeren Jiang, Jianlong Wu, Fei Wang, Chen Qian, Si Liu
ECCV 2022
GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detection
Yue Liao, Aixi Zhang, Miao Lu, Yongliang Wang, Xiaobo Li, Si Liu
CVPR 2022
Human-Centric Relation Segmentation: Dataset and Solution
Si Liu, Zitian Wang, Yulu Gao, Lejian Ren, Yue Liao, Guanghui Ren, Bo Li, Shuicheng Yan
IEEE TPAMI 2022
Mining the Benefits of Two-stage and One-stage HOI Detection
Aixi Zhang*, Yue Liao*, Si Liu, Miao Lu, Yongliang Wang, Chen Gao, Xiaobo Li
NeurIPS 2021
Progressive Language-Customized Visual Feature Learning for One-Stage Visual Grounding
Yue Liao, Aixi Zhang, Zhiyuan Chen, Tianrui Hui, Si Liu
IEEE TIP 2022
Reformulating HOI Detection as Adaptive Set Prediction
Mingfei Chen*, Yue Liao*, Si Liu, Zhiyuan Chen, Fei Wang, Chen Qian
CVPR 2021
Human-Centric Spatio-Temporal Video Grounding With Visual Transformers
Zongheng Tang, Yue Liao, Si Liu, Guanbin Li, Xiaojie Jin, Hongxu Jiang, Qian Yu, Dong Xu
IEEE TCSVT 2021
Scene Graph Generation With Hierarchical Context
Guanghui Ren, Lejian Ren, Yue Liao, Si Liu, Bo Li, Jizhong Han, Shuicheng Yan
IEEE TNNLS 2021
Cross-Modal Omni Interaction Modeling for Phrase Grounding
Tianyu Yu, Tianrui Hui, Zhihao Yu, Yue Liao, Sansi Yu, Faxi Zhang, Si Liu
ACM MM 2020
Local Correlation Consistency for Knowledge Distillation
Xiaojie Li, Jianlong Wu, Hongyu Fang, Yue Liao, Fei Wang, Chen Qian
ECCV 2020
PPDM: Parallel Point Detection and Matching for Real-time Human-Object Interaction Detection
Yue Liao, Si Liu, Fei Wang, Yanjie Chen, Chen Qian, Jiashi Feng
CVPR 2020
A Real-Time Cross-modality Correlation Filtering Method for Referring Expression Comprehension
Yue Liao, Si Liu, Guanbin Li, Fei Wang, Yanjie Chen, Chen Qian, Bo Li
CVPR 2020
CentripetalNet: Pursuing High-quality Keypoint Pairs for Object Detection
Zhiwei Dong, Guoxuan Li, Yue Liao, Fei Wang, Pengju Ren, Chen Qian
CVPR 2020
GPS: Group People Segmentation with Detailed Part Inference
Yue Liao, Si Liu, Tianrui Hui, Chen Gao, Yao Sun, Hefei Ling, Bo Li
ICME 2019
Academic Services
- Workshop Organizer: Person in Context (PIC) workshops at ECCV 2018, ICCV 2019, and CVPR 2021
- Conference Reviewer: CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR, AAAI, IJCAI, ACM MM
- Journal Reviewer: TPAMI, TIP, TMM, TNNLS, TCSTV, ACM CSUR
Awards
- The First Prize of the Natural Science Award of the China Society for Image and Graphics (CSIG) 2023
- The Huawei Scholarship of Beihang University 2023
- National Scholarship 2022
- Alibaba 'Outstanding Academic Cooperation and Research Intern' Award 2022
- The Champion of ActivityNet Homage challenge (CVPR) 2021
- Sensetime Co., Ltd. 'Future Star' Award 2020
Personal Interests
I avidly pursue sports, particularly tennis, basketball, and hiking, with a special admiration for iconic figures like Roger Federer and Kobe Bryant. Traveling is another passion of mine, as it broadens my horizons and deepens my understanding of diverse cultures and lifestyles.