I am a Ph.D. candidate at the University of Hong Kong (HKU) and a researcher passionate about making AI models smarter through better data.
- π Ph.D. Candidate: @HKU (ECE Dept).
- π¬ Remote Collaboration: @Stanford University.
- π» Research Intern: Alibaba Qwen Team (Tongyi, ATH).
My work sits at the intersection of Data-centric AI, LLMs, and Computer Vision. I am particularly interested in:
- Data-Centric AI: Understanding data influence, dataset distillation, and data pruning.
- LLM Reasoning: Reinforcement fine-tuning, Chain-of-Thought (CoT) reasoning, and reward attribution.
- Multimodal Learning: Vision-Language pre-training and robust image-text data quality.
- Publications: Published in top-tier conferences like ICLR, NeurIPS, ICML, CVPR/ICCV/ACL, and journals like TPAMI and IJCV.
- Awards: Recipient of the NeurIPS Outstanding Reviewer (2025) and ICML Gold Reviewer (2026).
* Equal Contribution, ^#^ Corresponding Author
Full list on Google Scholar.
-
Dynamic Important Example Mining for Reinforcement Finetuning
Haoru Tan, Sitong Wu, Yanfeng Chen, Yang-Tian Sun, Chirui Chang, Samm Sun, Ruobing Xie, Xiaojuan Qi
CVPR 2026 -
Dataset Distillation via Influence Matching
Haoru Tan, Wang Wang, Sitong Wu, Xiuzhe Wu, Yang-Tian Sun, Chirui Chang, Shaofeng Zhang, Xiaojuan Qi
CVPR 2026 -
Fast Data Mixture Optimization via Gradient Descent
Haoru Tan, Sitong Wu, Yanfeng Chen, Jun Xia, Ruobing Xie, Bin Xia, Summ Sun, Xiaojuan Qi
ICLR 2026 -
Understanding Data Influence with Differential Approximation
Haoru Tan, Sitong Wu, Xiuzhe Wu, Wang Wang, Bo Zhao, Zeke Xie, Gui-Song Xia, Xiaojuan Qi
IEEE T-PAMI 2026 -
Unlocking Token Rewards via Training-Free Reward Attribution
Sitong Wu, Haoru Tan#, Bin Xia, Xichen Zhang, Jingyao Li, Shaofeng Zhang, Xiaojuan Qi, Bei Yu, Jiaya Jia
CVPR 2026 -
Teacher-Guided Token Reward with Adaptive Calibration for Robust Policy Optimization in LLM Reasoning
Sitong Wu, Haoru Tan#, Xichen Zhang, Bin Xia, Wenhu Zhang, Xiaojuan Qi, Bei Yu, Jiaya Jia
ACL 2026 -
MedVES: Visual Evidence Scaling at Test Time for VLMs in Medical VQA
Xiuzhe Wu, Haoru Tan*, Barathi Subramanian, Handi Chen, Mitchell Peterson, Terry Guo, Amirhossein Kiani, Songmi Noh, Xiaojuan Qi, Jeanne Shen
ACM-MM 2026 -
Understanding Data Influence in Reinforcement Finetuning
Haoru Tan, Xiuzhe Wu, Sitong Wu, Yanfeng Chen, Xingwu Sun, Jeanne Shen, Xiaojuan Qi
NeurIPS 2025 -
Gradient-Decoupled Fine-Tuning for Generalizable Long Chain-of-Thought Reasoning
Sitong Wu*, Haoru Tan*, Jingyao Li, Shaofeng Zhang, Xiaojuan Qi, Bei Yu, Jiaya Jia
NeurIPS 2025 -
Robust Image-Text Data Quality Score via Three Lines of Code
Sitong Wu*, Haoru Tan*, Yukang Chen, Shaofeng Zhang, Jingyao Li, Xiaojuan Qi, Jiaya Jia
ICCV 2025 -
Data Pruning by Information Maximization
Haoru Tan, Sitong Wu, Wei Huang, Shizhen Zhao, Xiaojuan Qi
ICLR 2024 -
Ensemble Quadratic Assignment Network for Graph Matching
Haoru Tan, Chuang Wang, Sitong Wu, Xuyao Zhang, Fei Yin, Chenglin Liu
IJCV 2024 -
Sample-wise Affinity Consistency for Vision-Language Pre-training
Haoru Tan*, Sitong Wu*, Zhuotao Tian, Yukang Chen, Xiaojuan Qi, Jiaya Jia
CVPR 2024 -
Data Pruning via Moving-one-Sample-out
Haoru Tan, Sitong Wu, Fei Du, Zhibin Wang, Fan Wang, Xiaojuan Qi
NeurIPS 2023 -
Semantic Difference Convolution for Semantic Segmentation
Haoru Tan, Sitong Wu, Jimin Pi
NeurIPS 2022 -
Proxy Graph Matching with Proximal Matching Networks
Haoru Tan, Chuang Wang, Sitong Wu, Tieqiang Wang, Chenglin Liu
AAAI 2021
-
Historical Relative Policy Optimization for Bootstrapping LLM Reasoning
Sitong Wu, Haoru Tan, Bei Yu, Xiaojuan Qi, Jiaya Jia
NeurIPS 2026 -
Accelerating Reinforcement Learning for LongCoT Reasoning Models
Sitong Wu, Haoru Tan, Bin Xia, Bei Yu, Xiaojuan Qi, Jiaya Jia
NeurIPS 2026 -
Self-Reflective Test-Time Reinforcement Learning for LLM Reasoning
Sitong Wu, Haoru Tan, Xichen Zhang, Bin Xia, Xiaojuan Qi, Bei Yu, Jiaya Jia
ICML 2026 -
DreamOmni2: Multimodal Instruction-based Editing and Generation
Bin Xia, Bohao Peng, Yuechen Zhang, Junjia Huang, Jiyang Liu, Jingyao Li, Haoru Tan, Sitong Wu, Chengyao Wang, Yitong Wang, Xinglong Wu, Bei Yu, Jiaya Jia
CVPR 2026 -
Scaffolded Group Relative Policy Optimization for Enhancing LLM Reasoning
Xichen Zhang, Sitong Wu, Yinghao Zhu, Haoru Tan, Shaozuo Yu, Ziyi He, Jiaya Jia
ICLR 2026 -
Geometry-Instructed Video Editing
Chirui Chang, Xiaoyang Lyu, Yi-Hua Huang, Haoru Tan, Shizhen Zhao, Yikang Ding, Jianmin Bao, Xin Tao, Pengfei Wan, Xiaojuan Qi
SIGGRAPH Asia 2026 -
Bootstrapping Search Agents via High-Fidelity Environment Simulation
Xichen Zhang, Ziyi He, Yinghao Zhu, Sitong Wu, Shaozuo Yu, Meng Chu, Wenhu Zhang, Haoru Tan, Jiaya Jia
ACL 2026 -
Equipping Vision Foundation Model with Mixture of Experts for OOD Detection
Shizhen Zhao, Jiahui Liu, Xin Wen, Haoru Tan, Xiaojuan Qi
ICCV 2025 -
MC#: Mixture Compressor for Mixture-of-Experts Large Models
Wei Huang, Yue Liao, Yukang Chen, Jianhui Liu, Haoru Tan, Si Liu, Shiming Zhang, Shuicheng Yan, Xiaojuan Qi
IEEE T-PAMI 2025 -
Continuous Relative Rotary Positional Query for Dense Visual Representation Learning
Shaofeng Zhang, Qiang Zhou, Sitong Wu, Haoru Tan, Zhibin Wang, Jinfa Huang, Junchi Yan
ICLR 2025 -
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 -
Debiasing Text-to-Image Diffusion Models
Ruifei He, Chuhui Xue, Haoru Tan, Wenqing Zhang, Yingchen Yu, Song Bai, Xiaojuan Qi
ACM-MM 2024 -
Vertical Layering of Quantized Neural Networks for Heterogeneous Inference
Hai Wu, Ruifei He*, Haoru Tan*, Xiaojuan Qi, Kaibin Huang
IEEE T-PAMI 2023 -
Pale Transformer: A General Vision Transformer Backbone with Pale-Shaped Attention
Sitong Wu, Tianyi Wu, Haoru Tan, Guodong Guo
AAAI 2021 (Oral)
- Email: hrtan@eee.hku.hk
- Google Scholar: https://scholar.google.com/citations?user=H-q83SwAAAAJ&hl=zh-CN