I am currently a senior engineer at Meituan LongCat Team, focusing on research related to Search Agents and Large Language Models (LLMs). My current research interests primarily lie in DeepResearch, including context management and synthesizing agent data to enhance the capabilities of long-horizon agentic search systems.

Prior to joining LongCat Team, I was a Multimodal Content Understanding Algorithm Engineer at Meituan Dianping Business Group, where my work focused on Multimodal Large Language Models (MLLMs), Automatic Model Annotation, Cross-modal Embedding Retrieval, and Weakly-supervised Learning. My historical work supported key applications including Dianping Homepage Feed Recommendation, Note Search, and AI Search, etc.

Before that, I received my Master’s degree in July 2022 from the PAttern Learning and Mining (PALM) Lab, Southeast University, where I was very fortunate to be supervised by Prof. Min-Ling Zhang. I also received my Bachelor’s degree in School of Computer Science and Engineering from Southeast University in July 2019.

🔥 News

• 2026.01:  🎉 We released LongCat-Flash-Thinking-2601, achieving new SOTA results on BrowseComp with 56.6% / 73.1% (with context management). Technical report coming soon!
• 2025.07:  🎉 One paper is accepted by ACM MM 2025!
• 2025.05:  🎉 One paper is accepted by ACL 2025!
• 2025.04:  🎉 One paper is accepted by ICMR 2025!
• 2025.03:  🎉 Two papers are accepted by ICME 2025!
• 2023.08:  🎉 One paper is accepted by TKDE!
• 2023.04:  🎉 One paper is accepted by IJCAI 2023!

📝 Publications

• LongCat-Flash-Thinking-2601 Technical Report.
  Meituan LongCat Team, Core Contributor
  [Blog] [Github] [HuggingFace] [ModelScope] [Twitter] [机器之心]

• Geometric Gradient Divergence Modulation for Imbalanced Multimodal Learning.
  Di-Sen Hu, Xun Jiang, Zhe Sun, Hao Yang, Chong Peng, Peng Yan, Heng Tao Shen, Xing Xu
  Proceedings of the 33rd ACM International Conference on Multimedia (ACM MM), 2025
  [Paper]

• From Observation to Understanding: Front-Door Adjustments with Uncertainty Calibration for Enhancing Egocentric Reasoning in LVLMs.
  Shen-Shen Li, Wen-Xin Meng, Lei Wang, Hao Yang, Chong Peng, Peng Yan, Fu-Min Shen, Jing-Kuan Song, Heng Tao Shen, Xing Xu
  Findings of the Association for Computational Linguistics (ACL), 2025
  [Paper] [Blog]

• Composed Query-Based Event Retrieval in Video Corpus with Multimodal Episodic Perceptron.
  Fan Ni, Xun Jiang, Hao Yang, Chong Peng, Peng Yan, Zheng Wang, Fu-Min Shen, Xing Xu
  Proceedings of the 2025 International Conference on Multimedia Retrieval (ICMR), 2025
  [Paper]

• Social Optimum Assisted Gradient Modulation for Imbalanced Multimodal Learning.
  Di-Sen Hu, Xun Jiang, Zhe Sun, Hao Yang, Chong Peng, Peng Yan, Xing Xu
  Proceedings of the IEEE International Conference on Multimedia and Expo (ICME), 2025
  [Paper]

• Causal Intervention with Active Learning for Large Vision-Language Models in Egocentric Contexts.
  Wen-Xin Meng, Shen-Shen Li, Lei Wang, Hao Yang, Chong Peng, Peng Yan, Xing Xu
  Proceedings of the IEEE International Conference on Multimedia and Expo (ICME), 2025
  [Paper]

• Learning from noisy labels via dynamic loss thresholding.
  Hao Yang*, You-Zhi Jin*, Zi-Yin Li, Deng-Bao Wang, Xin Geng, Min-Ling Zhang
  IEEE Transactions on Knowledge and Data Engineering, 2023
  [Paper] [Code]

• Stochastic Feature Averaging for Learning with Long-Tailed Noisy Labels.
  Hao-Tian Li, Tong Wei, Hao Yang, Kun Hu, Chong Peng, Li-Bo Sun, Xun-Liang Cai, Min-Ling Zhang
  Proceedings of the 32nd International Joint Conference on Artificial Intelligence (IJCAI), 2023
  [Paper] [Code]

• Towards class-imbalance aware multi-label learning.
  Min-Ling Zhang, Yu-Kun Li, Hao Yang, Xu-Ying Liu
  IEEE Transactions on Cybernetics, 2022
  [Paper] [Code]

🎖 Honors and Awards

• 2024.12 Outstanding Contribution Award, Meituan Dianping Business Group
• 2024.01 Outstanding Master Thesis of Jiangsu Province (10 students each year)
• 2022.05 Outstanding Graduate of Jiangsu Province (10 students each year)
• 2021.10 National Scholarship (Top1%)
• 2020.10 Espressif Scholarship (Top2%)
• 2019-2022 First-class Scholarship for 3 consecutive years
• 2017.10 Bosch Scholarship (Top2%)
• 2016.10 President Scholarship (Top1%)
• 2015-2019 Outstanding Student Leader or Merit Student for 4 consecutive years

📖 Educations

• 2019.09 - 2022.06, Master, School of Computer Science and Engineering, Southeast University.
• 2015.09 - 2019.06, Undergraduate, School of Computer Science and Engineering, Southeast University.
• 2012.09 - 2015.06, Senior High School, Harbin No.3 High School.

💻 Internships

• 2020.05 - 2020.11, Huawei, China.