Yi Liu (刘毅)

I am a Technical Manager at Baidu, leading the large model team at PaddlePaddle. We work across the full AI stack for large language models—from infrastructure and development tools to algorithms and applications—to power the ERNIE large model series, including ERNIE 3.5, 4.0, 4.5, and 5.0.

I have led over 10 open-source projects at Baidu that have collectively earned 150,000+ GitHub stars, such as PaddleOCR, ERNIE, PaddleFormers, and PaddleX, among others. These projects power critical AI applications worldwide—from multilingual document understanding to large language model training and deployment at scale.

My technical expertise spans computer vision, vision-language models, large language models, and autonomous driving. I hold a Ph.D. from Nanyang Technological University, Singapore (2017) and a B.Eng. from Harbin Institute of Technology, China (2013). Before joining Baidu in 2018, I was a Data Scientist at HP Labs Singapore. At Baidu, I have also collaborated extensively with the Apollo team on autonomous driving technologies, contributing to Robotaxi and AD 2.0—an experience I deeply value.

• Nov 2025 We open-sourced ERNIE-4.5-VL-28B-A3B-Thinking: a lightweight VLM (3B active) matching flagship models, excelling in visual reasoning, STEM solving, visual grounding, and video understanding with tool utilization.
• Oct 2025 We open-sourced PaddleOCR-VL: a SOTA 0.9B VLM for document parsing, supporting 109 languages and recognizing complex elements (text, tables, formulas, charts).
• Sep 2025 We open-sourced ERNIE-4.5-21B-A3B-Thinking: an enhanced reasoning model with improved performance on logical reasoning, mathematics, science, coding, featuring tool usage and 128K long-context.
• Aug 2025 I gave a talk at IJCAI Conference on "PaddlePaddle Deep Learning Framework and its Support for Large Model Training and Inference".
• Jun 2025 We open-sourced ERNIE 4.5: a family of large-scale multimodal models with 10 variants, including MoE models (47B/3B active, 424B total) and dense models (0.3B).
• May 2025 We open-sourced PaddleOCR 3.0: featuring PP-OCRv5 (high-accuracy text recognition), PP-StructureV3 (general-purpose document parsing), and PP-ChatOCRv4 (intelligent document understanding).