hku

Researchers at the University of Hong Kong developed an analogue content-addressable memory (CAM) chip that performs search tasks about 100 million times faster than a standard CPU, achieving high accuracy in machine learning classification. The design uses only two transistors per cell and was published in Nature Nanotechnology.

The HKU team open-sourced DeepTutor, a personalized AI learning companion with long-term memory, multiple knowledge base retrieval methods, and a skill ecosystem, capable of tutoring, problem solving, question generation, research, visualization, and learning path planning.

Vibe-Trading is a personal AI trading agent from the HKUDS team at HKU, supporting natural language generation of quantitative strategies, one-click backtesting, and multi-agent collaboration. It comes with an embedded library of 456 alpha factors and is open-sourced.

HKU has open-sourced an AI personalized tutoring tool called DeepTutor, which supports multiple modes, a memory system, and local model deployment, and has already earned 25k stars on GitHub.

HKU open-sourced ViMax, a multi-agent collaborative long video generation tool that can generate a coherent video with script, storyboard, voiceover, and consistent characters from a single sentence, solving issues like short video fragmentation and character inconsistency. The developer also introduced Taste-Skill, a frontend framework that improves the aesthetics of AI-generated interfaces.

The University of Hong Kong Data Intelligence Lab has open-sourced the lightweight agent framework OpenHarness and its built-in agent Ohmo, providing core features like tool calling, memory, multi-agent coordination, and support for platforms like Feishu and Slack.

Yanzhe Zhang announced he will join the University of Hong Kong as an Assistant Professor in January 2027, focusing on AI agents, human-AI interaction, and safety. Houjun Liu congratulated him on the hire.