Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- Book Chapter: Deep Joint Source and Channel Coding, co-authors: Chenghong Bian, Yulin Shao, Deniz Gündüz, 2025
- Journal Papers:
- Multiple papers in IEEE Transactions on Wireless Communications, including Transformer-aided wireless image transmission with channel feedback
- Multiple papers in IEEE Wireless Communications Letters, including Collaborative Semantic Communication for Edge Inference
- Conference Papers:
- LotteryCodec: Searching the Implicit Representation in a Random Network for Low-Complexity Image Compression, ICML 2025, Spotlight (top 2.6%)
- MoRIC: A Modular Region-based Implicit Codec for Image Compression, NeurIPS 2025
- Actions Speak Louder Than Words: Rate-Reward Trade-off in Markov Decision Processes, ICLR 2025 (Top 3.27%)
- MIMO Channel as a Neural Function: Implicit Neural Representations for Extreme CSI Compression, ICASSP 2025
- Realism and Fidelity: Two Sides of a Coin in Deep Joint Source-Channel Coding, NeurIPS AI4NextG 2025
- DiffCP: Ultra-Low Bit Collaborative Perception via Diffusion Model, ICRA 2025
- Vision Transformer for Adaptive Image Transmission over MIMO Channels, ICC 2023, Best Paper Award
Research Experience
- Postdoctoral Research Associate at the INFORMED AI Hub, Department of Electrical and Electronic Engineering, Imperial College London, supervised by Prof. Pier Luigi Dragotti and Prof. Deniz Gunduz
Education
- PhD, Imperial College London, supervised by Prof. Deniz Gunduz and Prof. Krystian Mikolajczyk
- Master's Degree (with distinction), Imperial College London, supervised by Prof. Richard Vinter and Prof. Alessandro Astolfi
- Bachelor's and Master's Degrees, Zhejiang University
Background
Research Interests: Information-theoretic machine learning with applications in communication, control, and computer vision.