Location: Beijing, China
Scholar: 
Github: 
Email: 
WeChat: M.Eng. Beihang University
Beijing, China
Computer Technology, School of Computer Science
Supervisor: Richong Zhang
GPA: 3.84/4.00 Rank: 16/148
2022.09 - 2025.06
Hailang Huang
I am Hailang Huang (黄海浪 in Chinese). I am currently working at AMAP (Alibaba Group), co-advised by Senior Director Xiangxiang Chu and Senior Algorithm Expert Yong Wang, focusing on research and development on multimodal large language models (MLLMs) and agent systems.
Previously, I conducted research at Beihang University, supervised by Prof. Richong Zhang. I received my M.Eng. degree in Computer Technology from Beihang University in 2025, and obtained my B.Eng. degree in Intelligent Science and Technology from Nanjing University of Science and Technology in 2022.
My research interests include multi-modal understanding and generation with MLLMs, as well as agent systems. I am working toward becoming a full-stack MLLM researcher and algorithm expert.
News (2026-03-09)
- ICLR 2026 | GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning Paper | Code
- AAAI 2026 | Adacurl: Adaptive curriculum reinforcement learning with invalid sample mitigation and historical revisiting Paper
- Preprint | Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalization Paper | Code
Status:
Spring in the air...
Education
B.Eng. Nanjing University of Science and Technology
Nanjing, China
Intelligent Science and Technology, School of Computer Science and Engineering
GPA: 3.72/4.00 Rank: 7/95
2018.09 - 2022.06
Work Experience
Algorithm Engineer AMAP-Alibaba Group
APP Platform - Machine Learning Group
Research and development work related to MLLM and Agent.
2025.06 - Present
Algorithm Intern AMAP-Alibaba Group
APP Platform - Machine Learning Group
BResearch and development work related to MLLM.
2024.07 - 2025.06
Honors and Awards
- (2024) National Scholarship
- (2023) Outstanding Graduate Student of Beihang University
- (2023, 2022) Beihang University Academic Scholarship (twice)
- (2022) Suzhou Industrial Park Scholarship
- (2021) First Prize (Highest Award) of the National Computer Design Competition for Chinese University Students
- (2018-2022) 3 Software Copyrights (All First Author)
Papers
GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning
Xiangxiang Chu, Hailang Huang, Xiao Zhang, Fei Wei, Yong Wang
ICLR 2026, The Fourteenth International Conference on Learning Representations
Adacurl: Adaptive curriculum reinforcement learning with invalid sample mitigation and historical revisiting
Renda Li, Hailang Huang, Fei Wei, Feng Xiong, Yong Wang, Xiangxiang Chu
AAAI 2026, The 40th Annual AAAI Conference on Artificial Intelligence
MMGenBench: Fully Automatically Evaluating LMMs from the Text-to-Image Generation Perspective
Hailang Huang, Yong Wang, Zixuan Huang, Huaqiu Li, Tongwen Huang, Xiangxiang Chu, Richong Zhang
Preprint: https://arxiv.org/abs/2411.14062
Cross-Modal and Uni-Modal Soft-Label Alignment for Image-Text Retrieval
Hailang Huang, Zhijie Nie, Ziqiao Wang, Ziyu Shang
AAAI 2024, The 38th Annual AAAI Conference on Artificial Intelligence
LD-RPS: Zero-Shot Unified Image Restoration via Latent Diffusion Recurrent Posterior Sampling
Huaqiu Li, Yong Wang, Tongwen Huang, Hailang Huang, Haoqian Wang, Xiangxiang Chu
ICCV 2025, International Conference on Computer Vision
Learning Multi-Granularity and Adaptive Representation for Knowledge Graph Reasoning
Ziyu Shang, Peng Wang, Wenjun Ke, Jiajun Liu, Hailang Huang, Guozheng Li, Chenxiao Wu, Jianghan Liu, Xiye Chen, Li Yining
IJCAI 2024, The 33rd International Joint Conference on Artificial Intelligence
Improving the Consistency in Cross-Lingual Cross-Modal Retrieval with 1-to-K Contrastive Learning
Zhijie Nie, Richong Zhang, Zhangchi Feng, Hailang Huang, Xudong Liu
KDD 2024, 30th SIGKDD Conference on Knowledge Discovery and Data Mining
Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalization
Yuxiang Ji, Yong Wang, Ziyu Ma, Yiming Hu, Hailang Huang, Xuecai Hu, Guanhua Chen, Liaoni Wu, Xiangxiang Chu
Preprint: https://arxiv.org/abs/2601.05432