Zicheng Liu is a senior director of GenAI at AMD. His team develops large foundation models using AMD GPUs. Here is his team's webpage:
​
AMD GenAI​
Recent work:
​
Latent Visual Reasoning, Bangzheng Li, Ximeng Sun, Jiang Liu, Ze Wang, Jialian Wu, Xiaodong Yu, Hao Chen, Emad Barsoum, Muhao Chen, Zicheng Liu, ICLR 2026
​
XModBench: Benchmarking Cross-Modal Capabilities and Consistency in Omni-Language Models, Xingrui Wang, Jiang Liu, Chao Huang, Xiaodong Yu, Ze Wang, Ximeng Sun, Jialian Wu, Alan Yuille, Emad Barsoum, Zicheng Liu, ICLR2026
​
ImageDoctor: Diagnosing Text-to-Image Generation via Grounded Image Reasoning, Yuxiang Guo, Jiang Liu, Ze Wang, Hao Chen, Ximeng Sun, Yang Zhao, Jialian Wu, Xiaodong Yu, Zicheng Liu, Emad Barsoum, ICLR2026
​
Learning from Online Videos at Inference Time for Computer-Use Agents, Yujian Liu, Ze Wang, Hao Chen, Ximeng Sun, Xiaodong Yu, Jialian Wu, Jiang Liu, Emad Barsoum, Zicheng Liu, Shiyu Chang, TMLR 2026
​
Unleashing Hour-Scale Video Training for Long Video-Language Understanding, Jingyang Lin, Jialian Wu, Ximeng Sun, Ze Wang, Jiang Liu, Yusheng Su, Xiaodong Yu, Hao Chen, Jiebo Luo, Zicheng Liu, Emad Barsoum, Neurips 2025
​
​
Instella-T2I: Open-Source Text-to-Image with 1D Tokenizer and 32× Token Reduction on AMD GPUs
​​
Introducing Instella-Long: A fully Open Language Model with Long-Context Capability
​
TTT-Bench: A Benchmark for Evaluating Reasoning Ability with Simple and Novel Tic-Tac-Toe Style Games, arXiv:2506.10209
​
Introducing Instella: New State-of-the-art Fully Open 3B Language Models​
​
Instella-VL-1B: First AMD Vision Language Model
​
Agent Laboratory: Using LLM Agents as Research Assistants
​
SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer, CVPR 2025
​
Introducing the First AMD 1B Language Models: AMD-OLMo
​
His team is hiring scientists and engineers at all levels. His team is also hiring research interns.
​
​
​
​
​
Prior to joining AMD, he was a partner research manager at Microsoft Azure AI. Zicheng Liu joined Microsoft Research in 1997. Prior to that, he worked at Silicon Graphics where where he developed the trimmed NURBS tessellator shipped in both OpenGL and the OpenGL Optimizer.
​
Zicheng Liu has served in the technical committee for many international conferences. He was a member of the Audio and Electroacoustics Committee of IEEE Signal Processing Society. He is the chair of the Multimedia Systems and Applications Technical Committee of IEEE CAS society. He is a steering committee member of IEEE Transactions on Multimedia. He is the Editor-in-Chief of Journal of Visual Communications and Image Representation, and an associate editor of Machine Vision and Applications. He served as a guest editor of IEEE Transactions on Multimedia, and a guest editor of IEEE Multimedia Magazine. He is an affiliate professor in the department of Electrical Engineering, University of Washington. He was an IEEE distinguished lecturer from 2015-2016. He won APSIPA Industrial Distinguished Leader award. He is a fellow of IEEE.
​