👋 Hi, I’m Teo Wu (officially Wu Haoning 吴昊宁), working on LMMs in Moonshot AI, working with Xinyu Zhou. Prior to this, I have been a PhD candidate (preparing thesis defense) in Nanyang Technological University 🇸🇬, supervised by Prof. Weisi Lin. I obtained by B.S. degree of computer science in Peking University (北京大学).

I am currently focusing on LMM pre-training, long-prefill, and long-decode extensions.

• [General LMMs]: I co-lead Kimi-VL, an open-source MoE LMM that is excellent at OS-agent, long-context, with long-thinking abilities, and lead its evoluted version 🤔👀Kimi-VL-Thinking-2506, the first open multimodal thinking model that can handle OS-agent grounding, long video and PDF analysis, and high-resolution image understanding; and previously 💬Aria-Chat, an open-source MoE LMM optimized for multimodal everyday dialogs, matching GPT-4o on WildVision-Bench.

• [Video LMMs]: I have designed 🎬LongVideoBench, the first video benchmark for LMMs proven improvable given more input frames (>=256); I have also led video and long-context training of Aria (Model, Paper, GitHub), an excellent open-source native MoE LMM with abilities matching GPT-4o-mini/Gemini-1.5-Flash in only 3.9B activated parameters.

🌱 I have also been the lead of project Q-Future: Visual Evaluation with LMMs📹, on which 7 first-authored papers accepted in top conferences and journels including ICML, ICLR, NeurIPS, TPAMI, CVPR, ECCV and ACMMM. The flagship scorer, OneAlign has been downloaded more than 600K times (until April, 2025) on HuggingFace.

📫 Reach me by e-mail: realtimothyhwu@gmail.com/haoning001@e.ntu.edu.sg, Twitter: Twitter

Google Scholar