I am currently a Research Engineer at Kuaishou Technology. I received my Ph.D. in Fluid Mechanics from Peking University in 2020, advised by Prof. Yue Yang, and my B.S. in Mechanics and Economics from Peking University in 2015.

Since joining Kuaishou in 2020, my work has focused on three directions: (1) agentic coding large language models (LLMs), (2) AIGC generative video processing large models, and (3) server-side pre-processing and on-device post-processing AI algorithms. My current research focuses on LLMs, particularly agentic coding. Previously, I worked on image/video restoration and image/video generation. I have published 10+ papers at top-tier venues including CVPR, ICML, ECCV, and AAAI.

自 2020 年加入快手以来，工作聚焦于三个方向：（1）Agentic Coding 大语言模型：主导 KAT-Coder-Pro V2 模型后训练，在 Artificial Analysis Coding Index 中位列全球第六、国产第一；（2）AIGC 生成式视频处理大模型：主导研发并上线基于扩散模型的生成式视频处理大模型，在兼顾保真度的同时，显著提升视频清晰度与纹理细节丰富度，取得显著用户时长增长收益；（3）服务端前处理与移动端后处理 AI 算法：研发上线服务端视频增强修复算法，覆盖去压缩、去模糊、超分等方向；研发上线移动端 NPU/GPU 后处理算法在画质与功耗之间取得有效平衡。

News

• 2026.07: Joined Kling AI as a Research Engineer.
• 2026.07: KAT-Coder-Pro V2.5 released with improved long-horizon coding and general agentic capabilities.
• 2026.06: One paper accepted to ECCV 2026.
• 2026.05: One paper accepted to ICML 2026.
• 2026.03: KAT-Coder-Pro V2 released, ranked Top 10 on the Artificial Analysis Coding Index.
• 2026.02: Two papers accepted to CVPR 2026, one selected as Highlight.
• 2025.05: One paper accepted to ICML 2025.
• 2025.01: One paper accepted to AAAI 2025.
• 2024.07: Two papers accepted to ECCV 2024.
• 2024.02: Two papers accepted to CVPR 2024.
• 2020.07: Joined Kuaishou Technology as a Research Engineer.

Models

KAT-Coder-V2.5

KAT-Coder-V2.5 Technical Report

KwaiKAT Team, Kuaishou Technology

KAT-Coder-V2

KAT-Coder-V2 Technical Report

KwaiKAT Team, Kuaishou Technology

Publications

* denotes corresponding author; † denotes project leader.

arXiv 2026

No Time Like the Present: Agentic Test-Time Training for LLM Agents

Yanbo Wang, Jinhua Hao^*, Yuze Shi, Kun Yuan, Ming Sun

arXiv 2026

arXiv 2026

MMG2Skill: Can Agents Distill In-the-Wild Guides into Self-Evolving Skills?

Xinyu Che, Junqi Xiong, Yunfei Ge, Xinping Lei, Shihao Li, Hang Yan, Han Li, Yuanxing Zhang, Zhiqi Bai, Jinhua Hao, Ming Sun, Han Li, Jiaheng Liu

arXiv 2026

arXiv 2026

WebCompass: Towards Multimodal Web Coding Evaluation for Code Language Models

Xinping Lei, Xinyu Che, Junqi Xiong, Chenchen Zhang, Yukai Huang, Chenyu Zhou, Haoyang Huang, Minghao Liu, Letian Zhu, Hongyi Ye, Jinhua Hao, et al.

arXiv 2026

• ICML 2026 Coloring the Noise: Adversarial Sobolev Alignment for Faithful Image Super Resolution, Hongbo Wang, Huaibo Huang, Pin Wang, Jinhua Hao^†, Chao Zhou, Ran He
• ECCV 2026 Tuning Real-World Image Restoration at Inference: A Test-Time Scaling Paradigm for Flow Matching Models, Purui Bai, Junxian Duan, Pin Wang, Jinhua Hao^†, Ming Sun, Chao Zhou, Huaibo Huang
• CVPR 2026 ShiftLUT: Spatial Shift Enhanced Look-Up Tables for Efficient Image Restoration, Xiaolong Zeng, Yitong Yu, Shiyao Xiong, Jinhua Hao, Ming Sun, Chao Zhou, Bin Wang
• CVPR 2026 Highlight InstantViR: Real-Time Video Inverse Problem Solver with Distilled Diffusion Prior, Weimin Bai, Suzhe Xu, Yiwei Ren, Jinhua Hao, Ming Sun, Wenzheng Chen, He Sun
• ICML 2025 Visual Autoregressive Modeling for Image Super-Resolution, Yunpeng Qu, Kun Yuan, Jinhua Hao, Kai Zhao, Qizhi Xie, Ming Sun, Chao Zhou
• AAAI 2025 Plug-and-Play Tri-Branch Invertible Block for Image Rescaling, Jingwei Bao, Jinhua Hao^*†, Pengcheng Xu, Ming Sun, Chao Zhou, Shuyuan Zhu
• ECCV 2024 OAPT: Offset-Aware Partition Transformer for Double JPEG Artifacts Removal, Qiao Mo, Yukang Ding, Jinhua Hao^*†, Qiang Zhu, Ming Sun, Chao Zhou, Feiyu Chen, Shuyuan Zhu
• CVPR 2024 CPGA: Coding Priors-Guided Aggregation Network for Compressed Video Quality Enhancement, Qiang Zhu, Jinhua Hao^†, Yukang Ding, Yu Liu, Qiao Mo, Ming Sun, Chao Zhou, Shuyuan Zhu
• ECCV 2024 XPSR: Cross-modal Priors for Diffusion-based Image Super-Resolution, Yunpeng Qu, Kun Yuan, Kai Zhao, Qizhi Xie, Jinhua Hao, Ming Sun, Chao Zhou
• CVPR 2024 PTM-VQA: Efficient Video Quality Assessment Leveraging Diverse PreTrained Models from the Wild, Kun Yuan, Hongbo Liu, Mading Li, Muyi Sun, Ming Sun, Jiachao Gong, Jinhua Hao, Chao Zhou, Yansong Tang
• arXiv 2024 CasSR: Activating Image Power for Real-World Image Super-Resolution, Haolan Chen, Jinhua Hao^†, Kai Zhao, Kun Yuan, Ming Sun, Chao Zhou, Wei Hu
• J. Fluid Mech. 2025 Effects of magnetic–vortical interactions on magnetic splitting, Linlin Kang, Yanru Wang, Zhongzheng Jiang, Jinhua Hao, Shiying Xiong, Dixia Fan, Weicheng Cui
• J. Fluid Mech. 2021 Magnetic knot cascade via the stepwise reconnection of helical flux tubes, Jinhua Hao, Yue Yang
• J. Fluid Mech. 2019 Tracking vortex surfaces frozen in the virtual velocity in non-ideal flows, Jinhua Hao, Shiying Xiong, Yue Yang

Competitions

• CVPR Workshop 2024 🏆 2nd Place — NTIRE 2024 Challenge on Image Super-Resolution (×4): Methods and Results, Jinhua Hao^*, Kai Zhao, Kun Yuan, Ming Sun, Chao Zhou
• CVPR Workshop 2024 🏆 5th Place — NTIRE 2024 Challenge on Blind Enhancement of Compressed Image: Methods and Results, Qiao Mo, Jingwei Bao, Jinhua Hao^*, Yukang Ding, Hantang Li, Ming Sun, Chao Zhou, Shuyuan Zhu

Projects

• 2026.03: 研发上线大语言模型 KAT-Coder V2，在 Artificial Analysis Coding Index 中位列全球第六、国产第一（截至 2026.03.31）。Researched, developed, and launched agentic coding LLM, KAT-Coder V2, which ranked 6th globally and 1st among Chinese models on the Artificial Analysis Coding Index (as of March 31, 2026).
• 2025.08: 研发上线生成式视频处理大模型 LPM，提升视频清晰度并生成纹理细节，取得了带宽收益与用户时长的双重收益。Researched, developed, and launched a diffusion-based generative large video processing model, which significantly improves video clarity and texture details while preserving fidelity and delivers substantial gains in QoE.
• 2023.01: 研发上线服务端前处理算法，对低质视频进行智能高清重塑，提升用户观看体验和大盘 QoE。Researched, developed, and launched server-side pre-processing algorithms to intelligently reconstruct low-quality videos into high-definition outputs, improving user viewing experience and overall QoE.
• 2022.07: 研发上线移动端后处理算法，提升用户播放视频清晰度，面向NPU/GPU 芯片优化算法，兼顾效果与功耗。Researched, developed, and launched on-device post-processing algorithms optimized for mobile NPU/GPU chips, balancing model quality and power efficiency while enhancing video quality during playback.
• 2021.12: 研发上线视频质量评估算法，实现对视频画质的多维度感知、理解和评估。Researched, developed, and launched video quality assessment algorithms for multi-dimensional perception, understanding, and evaluation of video quality.

Honors

• 2024, 2026, 快手优秀项目奖 (2次), Kuaishou Outstanding Project Award (twice)
• 2023, 2024, 2025, 快手音视频个人荣誉奖 (3次), Kuaishou Audio & Video Outstanding Individual Award (three times)
• 2023, 快手洛子峰奖 (2次), Kuaishou Lhotse Award (twice)
• 2022, 2023, 快手乔戈里奖 (2次), Kuaishou Chogori Award (twice)
• 2020, 快手“快Star”特别技术人才计划 (Top 1%), Kuaishou “KuaiStar” Special Technical Talent Program (Top 1%)
• 2020, 北京大学优秀毕业生 (Top 1%), Peking University Outstanding Graduate (Top 1%)
• 2015, 2016, 2017, 2019, 北京大学校长奖学金 (Top 1%), Peking University President’s Scholarship (Top 1%)

Education

• 2015.09 - 2020.06, Ph.D. in Fluid Mechanics, Peking University, Beijing.
• 2011.09 - 2015.06, B.S. in Mechanics, Peking University, Beijing.