Jiahao Li

Principal Researcher

Microsoft Research Asia

About

I am a Principal Researcher in the Media Computing Group at Microsoft Research Asia. I received my B.S. in Computer Science and Technology from Harbin Institute of Technology in 2014, and my Ph.D. in Computer Application Technology from Peking University in 2019.

My early work focused on traditional video codecs, where several of my techniques were adopted into international standards including H.266/VVC and AOM AV1. I then turned to neural image and video codecs, aiming to push the frontier of compression research. My interests now extend further to visual generation, video understanding, agentic video systems, and long-horizon video memory and context.

I have contributed several technique transfers to Microsoft real-time communication product Teams.

Research Interests

Education

Publications

Here is my Google Scholar.

Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model
Senqiao Yang, Kaichen Zhang, Zhaoyang Jia, Jinghao Guo, Yifei Shen, Xinjie Zhang, Xiaoyi Zhang, Haoqing Wang, Xiao Li, Peng Zhang, Xiang An, Yin Xie, Zhening Liu, Xun Guo, Jiahao Li, Shicheng Zheng, Jinglu Wang, Zongyu Guo, Wenxuan Xie, Zihan Zheng, Yuxuan Luo, Bin Li, Yan Lu
arXiv 2026 · Paper · Code · Project

Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing
Xinjie Zhang, Peng Zhang, Shicheng Zheng, Jinghao Guo, Zhaoyang Jia, Yifei Shen, Xun Guo, Yuxuan Luo, Jiahao Li, Wenxuan Xie, Fanyi Pu, Xiaoyi Zhang, Kaichen Zhang, Zongyu Guo, Tianci Bi, Dongnan Gui, Zhening Liu, Zimo Wen, Zihan Zheng, Senqiao Yang, Xiao Li, Jinglu Wang, Bin Li, Yan Lu
arXiv 2026 · Paper · Code · Project

Generative Video Compression with Adaptive Score Distillation
Naifu Xue, Zhaoyang Jia, Haosen Li, Zihan Zheng, Jiahao Li, Bin Li, Xiaoyi Zhang, Qi Meng, Yuan Zhang, Yan Lu
arXiv 2026 · Paper

An Efficient Streaming Video Understanding Framework with Agentic Control
Jinming Liu, Jianguo Huang, Zhaoyang Jia, Jiahao Li, Xiaoyi Zhang, Zongyu Guo, Bin Li, Wenjun Zeng, Yan Lu, Xin Jin
arXiv 2026 · Paper

Efficient Autoregressive Video Diffusion with Dummy Head
Hang Guo, Zhaoyang Jia, Jiahao Li, Bin Li, Yuanhao Cai, Jiangshan Wang, Yawei Li, Yan Lu
arXiv 2026 · Paper · Code · Project

Ultra-Fast Neural Video Compression
Jiahao Li, Wenxuan Xie, Zhaoyang Jia, Bin Li, Zongyu Guo, Xiaoyi Zhang, Yan Lu
CVPR 2026 · Paper · Code

CoD: A Diffusion Foundation Model for Image Compression
Zhaoyang Jia, Zihan Zheng, Naifu Xue, Jiahao Li, Bin Li, Zongyu Guo, Xiaoyi Zhang, Houqiang Li, Yan Lu
CVPR 2026 · Paper · Code

Generative Video Compression with One-Dimensional Latent Representation
Zihan Zheng, Zhaoyang Jia, Naifu Xue, Jiahao Li, Bin Li, Zongyu Guo, Xiaoyi Zhang, Zhenghao Chen, Houqiang Li, Yan Lu
CVPR 2026 · Paper · Code · Project

Single-step Diffusion-based Video Coding with Semantic-Temporal Guidance
Naifu Xue, Zhaoyang Jia, Jiahao Li, Bin Li, Zihan Zheng, Yuan Zhang, Yan Lu
CVPR 2026 · Paper · Project

Bringing Your Portrait to 3D Presence
Jiawei Zhang, Lei Chu, Jiahao Li, Zhenyu Zang, Chong Li, Xiao Li, Xun Cao, Hao Zhu, Yan Lu
CVPR 2026 · Paper · Code · Project

Divide, then Ground: Adapting Frame Selection to Query Types for Long-Form Video Understanding
Jialuo Li, Bin Li, Jiahao Li, Yan Lu
CVPR 2026 · Paper · Code

CoD-Lite: Real-Time Diffusion-Based Generative Image Compression
Zhaoyang Jia, Naifu Xue, Zihan Zheng, Jiahao Li, Bin Li, Xiaoyi Zhang, Zongyu Guo, Yuan Zhang, Houqiang Li, Yan Lu
ICML 2026 · Paper · Code

Compression as Adaptation: Implicit Visual Representation with Diffusion Foundation Models
Zongyu Guo, Jiajun He, Zhaoyang Jia, Xiaoyi Zhang, Jiahao Li, Xiao Li, Bin Li, José Miguel Hernández-Lobato, Yan Lu
ICML 2026 · Paper · Code · Project

InfiniteWeb: Scalable Web Environment Synthesis for GUI Agent Training
Ziyun Zhang, Zezhou Wang, Xiaoyi Zhang, Zongyu Guo, Jiahao Li, Bin Li, Yan Lu
ACL 2026 · Paper · Code · Project

When MLLMs Meet Compression Distortion: A Coding Paradigm Tailored to MLLMs
Jinming Liu, Zhaoyang Jia, Jiahao Li, Bin Li, Xin Jin, Wenjun Zeng, Yan Lu
ICLR 2026 · Paper · Code

One-Step Diffusion-Based Image Compression with Semantic Distillation
Naifu Xue, Zhaoyang Jia, Jiahao Li, Bin Li, Yuan Zhang, Yan Lu
NeurIPS 2025 · Paper · Code · Project

Deep Video Discovery: Agentic Search with Tool Use for Long-form Video Understanding
Xiaoyi Zhang, Zhaoyang Jia, Zongyu Guo, Jiahao Li, Bin Li, Houqiang Li, Yan Lu
NeurIPS 2025 · Paper · Code

Omnidirectional 3D Scene Reconstruction from Single Image
Ren Yang, Jiahao Li, Yan Lu
NeurIPS 2025 · Paper · Project

Generative Latent Video Compression
Zongyu Guo, Zhaoyang Jia, Jiahao Li, Xiaoyi Zhang, Bin Li, Yan Lu
arXiv 2025 · Paper

UniMIC: Token-Based Multimodal Interactive Coding for Human-AI Collaboration
Qi Mao, Tinghan Yang, Jiahao Li, Bin Li, Libiao Jin, Yan Lu
arXiv 2025 · Paper

DLF: Extreme Image Compression with Dual-generative Latent Fusion
Naifu Xue, Zhaoyang Jia, Jiahao Li, Bin Li, Yuan Zhang, Yan Lu
ICCV 2025 · Paper · Code · Project

Towards Practical Real-Time Neural Video Compression
Zhaoyang Jia, Bin Li, Jiahao Li, Wenxuan Xie, Linfeng Qi, Houqiang Li, Yan Lu
CVPR 2025 · Paper · Code · Project

PICD: Versatile Perceptual Image Compression with Diffusion Rendering
Tongda Xu, Jiahao Li, Bin Li, Yan Wang, Ya-Qin Zhang, Yan Lu
CVPR 2025 · Paper

Generative Latent Coding for Ultra-Low Bitrate Image and Video Compression
Linfeng Qi, Zhaoyang Jia, Jiahao Li, Bin Li, Houqiang Li, Yan Lu
IEEE TCSVT 2025 · Paper · Code

Neural Video Compression with Feature Modulation
Jiahao Li, Bin Li, Yan Lu
CVPR 2024 · Paper · Code

Generative Latent Coding for Ultra-Low Bitrate Image Compression
Zhaoyang Jia, Jiahao Li, Bin Li, Houqiang Li, Yan Lu
CVPR 2024 · Paper · Code

Implicit Motion Function
Yue Gao, Jiahao Li, Lei Chu, Yan Lu
CVPR 2024 · Paper · Project

Hierarchical Intra-modal Correlation Learning for Label-free 3D Semantic Segmentation
Xin Kang, Lei Chu, Jiahao Li, Xuejin Chen, Yan Lu
CVPR 2024 · Paper

Long-term Temporal Context Gathering for Neural Video Compression
Linfeng Qi, Zhaoyang Jia, Jiahao Li, Bin Li, Houqiang Li, Yan Lu
ECCV 2024 · Paper

Arbitrary-Scale Video Super-Resolution Guided by Dynamic Context
Cong Huang, Jiahao Li, Lei Chu, Dong Liu, Yan Lu
AAAI 2024 · Paper

Uncertainty-Aware Deep Video Compression with Ensembles
Wufei Ma, Jiahao Li, Bin Li, Yan Lu
IEEE TMM 2024 · Paper

Neural Image Compression with Regional Decoding
Yili Jin, Jiahao Li, Bin Li, Yan Lu
ACM TOMM 2024 · Paper

Neural Video Compression with Diverse Contexts
Jiahao Li, Bin Li, Yan Lu
CVPR 2023 · Paper · Code

Motion Information Propagation for Neural Video Compression
Linfeng Qi, Jiahao Li, Bin Li, Houqiang Li, Yan Lu
CVPR 2023 · Paper

VideoTrack: Learning to Track Objects via Video Transformer
Fei Xie, Lei Chu, Jiahao Li, Yan Lu, Chao Ma
CVPR 2023 · Paper · Code

EVC: Towards Real-Time Neural Image Compression with Mask Decay
Guo-Hua Wang, Jiahao Li, Bin Li, Yan Lu
ICLR 2023 · Paper · Code

Disentangle Propagation and Restoration for Efficient Video Recovery
Cong Huang, Jiahao Li, Lei Chu, Dong Liu, Yan Lu
ACM MM 2023 · Paper

Hybrid Spatial-Temporal Entropy Modelling for Neural Video Compression
Jiahao Li, Bin Li, Yan Lu
ACM MM 2022 · Paper · Code

Neural Compression-Based Feature Learning for Video Restoration
Cong Huang, Jiahao Li, Bin Li, Dong Liu, Yan Lu
CVPR 2022 · Paper

Temporal Context Mining for Learned Video Compression
Xihua Sheng, Jiahao Li, Bin Li, Li Li, Dong Liu, Yan Lu
IEEE TMM 2022 · Paper · Code

A Universal Optimization Framework for Learning-based Image Codec
Jing Zhao, Bin Li, Jiahao Li, Ruiqin Xiong, Yan Lu
ACM TOMM 2022 · Paper

Deep Contextual Video Compression
Jiahao Li, Bin Li, Yan Lu
NeurIPS 2021 · Paper · Code

A Universal Encoder Rate Distortion Optimization Framework for Learned Compression
Jing Zhao, Bin Li, Jiahao Li, Ruiqin Xiong, Yan Lu
CVPR Workshops 2021 · Paper

A Deep Reinforcement Learning Approach to Multiple Streams’ Joint Bitrate Allocation
Hang Zhang, Jiahao Li, Bin Li, Yan Lu
IEEE TCSVT 2020 · Paper

Fully Connected Network-Based Intra Prediction for Image Coding
Jiahao Li, Bin Li, Jizheng Xu, Ruiqin Xiong, Wen Gao
IEEE TIP 2018 · Paper

Intra Block Copy for Screen Content in the Emerging AV1 Video Codec
Jiahao Li, Hui Su, Alex Converse, Bin Li, Roger Zhou, Bruce Lin, Jizheng Xu, Yan Lu, Ruiqin Xiong
DCC 2018 · Paper

Diversity-Based Reference Picture Management for Low Delay Screen Content Coding
Jiahao Li, Bin Li, Jizheng Xu, Ruiqin Xiong
IEEE TCSVT 2017 · Paper

Intra Prediction Using Fully Connected Network for Video Coding
Jiahao Li, Bin Li, Jizheng Xu, Ruiqin Xiong
ICIP 2017 · Paper

Intra Prediction Using Multiple Reference Lines for Video Coding
Jiahao Li, Bin Li, Jizheng Xu, Ruiqin Xiong
DCC 2017 · Paper

Efficient Multiple-Line-Based Intra Prediction for HEVC
Jiahao Li, Bin Li, Jizheng Xu, Ruiqin Xiong
IEEE TCSVT 2016 · Paper

An Adaptive Hierarchical QP Setting for Screen Content Coding
Jiahao Li, Bin Li, Jizheng Xu, Ruiqin Xiong
VCIP 2015 · Paper

Contact

I am hiring research interns. If you are passionate about neural compression, visual generation, video understanding, or agentic visual systems, please send your CV to li.jiahao@microsoft.com.