My research interests span AI agents, wearable/wireless sensing, and human-computer interaction.
God does not play dice.
Yet, in the age of LLMs, we expect exactly that: deterministic guarantees from inherently probabilistic systems navigating ambiguous human inputs.
My research is driven by this very paradox.
I am interested in building trustworthy AI agents designed to partner with humans, enabling mutual verification and joint problem-solving.
Because true human-computer synergy goes beyond text, my work also encompasses building intelligent systems that infer human activities and intentions via wearable and wireless sensing.
Through these interconnected efforts, I aim to pioneer HCI techniques that profoundly enhance the user experience.
With the tsunami of GenAI on the horizon, people should find the irreplaceability while embracing it, and research is no exception. In the meantime, do not forget the meta-learning of humans, nor give up the critical thinking ability.
I am open to collaboration and happy to discuss. If you're interested in my research, feel free to contact me.
RF-LEGO: Modularized Signal Processing-Deep Learning Co-Design for RF Sensing via Deep Unrolling Luca Jiang-Tao Yu, Chenshu Wu ACM MobiCom, 2026, Austin, TX, USA 🇺🇸
"Take Me Home, Wi-Fi Drone": A Drone-Based Wireless System for Wilderness Search and Rescue Weiying Hou, Luca Jiang-Tao Yu, Chenshu Wu ACM MobiCom, 2026, Austin, TX, USA 🇺🇸
OctoNet: A Large-Scale Multi-Modal Dataset for Human Activity Understanding Grounded in Motion-Captured 3D Pose Labels Dongsheng Yuan*, Xie Zhang*, Weiying Hou, Sheng Lyu, Yuemin Yu, Luca Jiang-Tao Yu, Chengxiao Li, Chenshu Wu NeurIPS, 2025, San Diego, CA, USA 🇺🇸
Radio2Speech: High Quality Speech Recovery from Radio Frequency Signals Running Zhao, Luca Jiang-Tao Yu, Tingle Li, Hang Zhao, Edith C.H. Ngai ISCA Interspeech, 2022, Incheon, South Korea 🇰🇷