Haotian Wu
Haotian Wu is a Research Associate for INFORMED AI Hub, based in the Department of Electrical and Electronic Engineering, Imperial College London. He works with Prof. Pier Luigi Dragotti and Prof. Deniz Gündüz on research at the intersection of machine learning, information theory, and signal processing.
Haotian obtained his PhD from Imperial College London, where he was supervised by Prof. Deniz Gündüz and Prof. Krystian Mikolajczyk. Before that, he earned his Bachelor’s and Master’s degrees in Electrical Engineering from Zhejiang University and was also awarded a Master’s degree in Control Systems from Imperial College London.

Research
His primary research interests revolve around information-theoretic machine learning, with applications in communication, control, and computer vision. His work focuses on representation learning, implicit neural representations (INR), and efficient communication and compression. He is particularly interested in developing methods for generative models in image transmission, novel compression for robotics, and DeepJSCC for edge inference.
Selected works
- Actions Speak Louder Than Words: Rate-Reward Trade-off in Markov Decision Processes, International Conference on Learning Representations (ICLR),
- 2025MIMO Channel as a Neural Function: Implicit Neural Representations for Extreme CSI Compression, International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2025
- DiffCP: Ultra-Low Bit Collaborative Perception via Diffusion Model, IEEE International Conference on Robotics and Automation (ICRA) 2025
- Process-and-forward: Deep joint source-channel coding over cooperative relay networks, IEEE Journal on Selected Areas in Communications (JSAC) 2025.
- Deep joint source-channel coding for adaptive image transmission over MIMO channels, IEEE Transactions on Wireless Communications, 2024
- Transformer-aided wireless image transmission with channel feedback, IEEE Transactions on Wireless Communications, 2024
- Vision Transformer for Adaptive Image Transmission over MIMO Channels, ICC 2023-IEEE International Conference on Communications. Best paper awarded.
- Channel-Adaptive Wireless Image Transmission with OFDM, IEEE Wireless Communications Letters, 2023
Contact
- Email: haotian.wu17@imperial.ac.uk