What's new
(New Survey) “Green edge AI: A contemporary survey,” submitted. [Paper]
(New Survey) “A survey of what to share in federated learning: Perspectives on model utility, privacy leakage, and communication efficiency,” submitted. [Paper]
(GaussianImage) “GaussianImage: 1000 FPS image representation and compression by 2D Gaussian splatting,” submitted. [Paper]
(EdgeGPT) Our EdgeGPT paper “Large language models empowered autonomous edge AI for connected intelligence” was accepted by IEEE Communications Magazine. [Paper]
(Nature Communications) Paper “Selective knowledge sharing for privacy-preserving federated distillation without a good teacher” was accepted by Nature Communications. [Paper]
(CVPR 24) Three papers accepted to CVPR 2024.
“Generalized predictive model for autonomous driving” (Highlight) [Paper]
“Boosting neural representations for videos with a conditional decoder” (Highlight) [Paper]
“Task-aware encoder control for deep video compression”
(AAMAS 24) “Context-aware communication for multi-agent reinforcement learning,” accepted by AAMAS 2024. [Paper]
(CVPR 23) “Generalized relation modeling for transformer tracking”, accepted by CVPR 2023. [Paper] [GitHub]
Research Interests
Generative AI, Foundation Models
Reinforcement Learning
Edge AI and Edge Computing
Integrated AI and Communications
Selected Publications
Reinforcement Learning
X. Li, J. Zhang, “Context-aware communication for multi-agent reinforcement learning,” International Conference on Autonomous Agents and Multiagent Systems (AAMAS), Auckland, New Zealand, May 2024. (Acceptance Rate: 25%) [Paper]
X. Wang*, X. Li*, J. Shao, and J. Zhang, “AC2C: Adaptively controlled two-hop communication for multi-agent reinforcement learning,” International Conference on Autonomous Agents and Multiagent Systems (AAMAS), London, United Kingdom, May-June 2023. (Acceptance Rate: 23.3%) (* equal contribution) [Paper]
Y. Zhang, Z. Yu, J. Zhang, L. Wang, T. Luan, B. Guo, and C. Yuen, “Learning decentralized traffic signal controllers with multi-agent graph reinforcement learning,” IEEE Trans. Mobile Computing, to appear. [Paper]
|