 |
 |
Jun ZhangProfessor, IEEE Fellow, Highly Cited Researcher Associate Director Office: Room 2430 |
What's new
Student Awards: Congratulations to Jiawei, Xinran, Zhening, Hongze, Zifan!
(August 2025) Jiawei received the IEEE Communications Society Katherine Johnson Young Author Best Paper Award for paper “Learning Task-Oriented Communication for Edge Inference: An Information Bottleneck Approach”. [Paper] [Award Information]
(August 2025) Zhening received The ECE Best TA Award 2024/25.
(August 2025) Xinran, Zhening, Hongze, and Zifan received the HKUST RedBird Academic Excellence Award for Continuing PhD Students.
Call for Papers
IEEE Journal on Selected Topics in Signal Processing, special issue on “Wireless Foundation Models for AI-native 6G and Beyond,” deadline: May 15, 2026. [Call for Papers]
Special Collection on “AI-Driven Wireless Channel Modeling and Prediction,” npj Wireless Technology, submission deadline: 31 March 2026. [Website]
Recent Research Results
(Mon3tr) “Mon3tr: Monocular 3D Telepresence with Pre-built Gaussian Avatars as Amortization,” preprint. [Paper]
(WorldPlay) “WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling,” preprint. [Paper] [Demo]
(MoDES) “MoDES: Accelerating mixture-of-experts multimodal large language models via dynamic expert skipping,” preprint. [Paper]
(LinVideo) “LinVideo: A Post-training framework towards O(n) attention in efficient video generation,” preprint. [Paper]
(Forge4D) “Forge4D: Feed-forward 4D human reconstruction and interpolation from uncalibrated sparse-view videos,” preprint. [Paper] [Project Page]
(ICLR 26) 9 papers accepted by ICLR 2026.
(npj Wireless Technology) “Towards Reasoning-Empowered Task-Oriented Communication for Agent Networks,” accepted by npj Wireless Technology.
(npj Artificial Intelligence) “Learning design-score manifold to guide diffusion models for offline optimization,” published by npj Artificial Intelligence. [Paper]
(NeurIPS 25) “CAS-Spec: Cascade adaptive self-speculative decoding for on-the-fly lossless inference acceleration of LLMs,” accepted by NeurIPS 25. [Paper]
(ICCV 25) Two papers accepted by ICCV 2025.
“DimensionX: Create any 3D and 4D scenes from a single image with decoupled video diffusion” [Paper] [Code] [Project Page]
“MEGA: Memory-efficient 4D Gaussian splatting for dynamic scenes” (Highlight) [Paper]
(ICML 25) Three papers accepted by ICML 2025.
“AdaWorld: Learning adaptable world models with latent actions” [Project Page]
“HarmoniCa: Harmonizing training and inference for better feature cache in diffusion transformer acceleration” [Paper]
“C2IQL: Constraint-conditioned implicit Q-learning for safe offline reinforcement learning”
(Nature Communications) Paper “Selective knowledge sharing for privacy-preserving federated distillation without a good teacher” was published by Nature Communications, 2024. [Paper]
Research Interests
At iComAI Lab, we pursue cutting-edge research at the intersection of communications technology and AI, with a particular focus on intelligent decision making and spatial perception. We are deeply passionate about advancing the frontiers of two rapidly evolving fields:
AI Agents: to explore the design and deployment of intelligent agents—ranging from virtual and wearable agents to robotic systems—that can perceive, reason, and act autonomously in complex environments;
Spatial AI: to reconstruct and create immersive 3D environments, enabling richer human–machine interaction and groundbreaking applications in augmented reality, robotics, and digital twins.
Together, these two areas form the foundation of our vision: building intelligent systems that not only understand the world—but bring it to life.
Our work bridges theoretical foundations with practical applications, addressing fundamental challenges in:
LLM/MLLM Reasonging and Understanding
Generative AI, World Models
Efficient and Safe AI
3D/4D Representation, Reconstruction, Compression
Immersive Communication, Telepresence
O-RAN, Edge AI Systems
|
|
Group WeChat Account of iComAI Lab (in Chineses) |
Selected Publications
GenAI, World Models
W. Sun, H. Zhang, H. Wang, J. Wu, Z. Wang, Z. Wang, Y. Wang, J. Zhang, T. Wang, and C. Guo, “WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling,” preprint. [Paper] [Demo]
S. Gao, S. Zhou, Y. Du, J. Zhang, and C. Gan, “AdaWorld: Learning adaptable world models with latent actions,” International Conference on Machine Learning (ICML), Vancouver, Canada, July 2025. (Acceptance Rate: 26.9%) [Project Page]
T. Zhou, Z. Chen, W. Lyu, Z. Chen, D. Tsang, and J. Zhang, “Learning design-score manifold to guide diffusion models for offline optimization,” npj Artificial Intelligence, vol. 2, no. 4, pp. 1-12, January 2026. [Paper]
W. Sun, S. Chen, F. Liu, Z. Chen, Y. Duan, J. Zhang, and Y. Wang, “DimensionX: Create any 3D and 4D scenes from a single image with decoupled video diffusion,” International Conference on Computer Vision (ICCV), Honolulu, Hawai'i, USA, Oct. 2025. (Acceptance Rate: 24%) [Paper] [Code] [Project Page]
S. Gao, J. Yang, L. Chen, K. Chitta, Y. Qiu, A. Geiger, J. Zhang, and H. Li, “Vista: A generalizable driving world model with high fidelity and versatile controllability,” The Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS), Vancouver, Canada, Dec. 2024. [Paper] [Code] [Demo] (Acceptance Rate: 25.8%)
AI Agent, LLM/MLLM Reasonging
X. Li, G. Huzhang, S. Shen, Q.-G. Chen, Z. Xu, W. Luo, K. Zhang, and J. Zhang, “Getting Your LLMs Ready for Reinforcement Learning with Lightweight SFT,” International Conference on Learning Representations (ICLR), Rio de Janeiro, Brazil, April 2026. (Acceptance Rate: 28%)
S. Zhang, Z. Li, Y. Zhang, J. Fu, L. Song, J. Bian, J. Zhang, Y. Yang, and R. Wang, “PixelCraft: A multi-agent system for high-fidelity visual reasoning on structured images,” International Conference on Learning Representations (ICLR), Rio de Janeiro, Brazil, April 2026. (Acceptance Rate: 28%) [Paper] [GitHub]
Z. Li, X. Guan, B. Zhang, S. Huang, H. Zhou, S. Lai, M. Yan, Y. Jiang, P. Xie, F. Huang, J. Zhang, and J. Zhou, “WebWeaver: Structuring web-scale evidence with dynamic outlines for open-ended deep research,” International Conference on Learning Representations (ICLR), Rio de Janeiro, Brazil, April 2026. (Acceptance Rate: 28%) [Paper]
Z. Li, J. Fu, L. Song, J. Bian, J. Zhang, and R. Wang, “Chain of Functions: A programmatic pipeline for fine-grained chart reasoning data generation,” International Joint Conference on Natural Language Processing & Asia-Pacific Chapter of the Association for Computational Linguistics (IJCNLP & AACL), Mumbai, India, December 2025. [Paper]
Z. Li, Q. Guo, J. Shao, L. Song, J. Bian, J. Zhang, and R. Wang, “Graph neural network enhanced retrieval for question answering of large language models,” The Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL), Albuquerque, New Mexico, USA, April-May 2025. [Paper]
3D/4D Representation, Reconstruction, Compression
F. Lin, Y. Hu, Z. Liu, Y. Zhuang, Z. Lin, and J. Zhang, “Mon3tr: Monocular 3D Telepresence with Pre-built Gaussian Avatars as Amortization,” preprint. [Paper]
Z. Liu, R. Song, Y. Huang, Y. Hu, X. Zhang, J. Shao, Z. Lin, and Jun Zhang, “Feed-forward 3D Gaussian splatting compression with long-context modeling,” preprint. [Paper]
Y. Hu, Y. He, J. Chen, W. Yuan, K. Qiu, Z. Lin, S. Zhu, Z. Dong, and J. Zhang, “Forge4D: Feed-forward 4D human reconstruction and interpolation from uncalibrated sparse-view videos,” preprint. [Paper] [Project Page]
Z. Liu, Y. Hu, X. Zhang, J. Shao, Z. Lin, and J. Zhang, “Dynamics-aware Gaussian splatting streaming towards fast on-the-fly training for 4D reconstruction,” preprint. [Paper] [Project Page]
J. Bao, H. Chen, L. Zhu, C. Liu, R. Zhang, K. Luo, Z. Hu, W. Chen, Y. Yin, X. Wang, Z. Lin, J. Zhang, and X. Han, “LumiTex: Towards high-fidelity PBR texture generation with illumination context,” International Conference on Learning Representations (ICLR), Rio de Janeiro, Brazil, April 2026. (Acceptance Rate: 28%) [Paper]
X. Zhang, Z. Liu, Y. Zhang, X. Ge, D. He, T. Xu, Y. Wang, Z. Lin, S. Yan, and J. Zhang, “MEGA: Memory-efficient 4D Gaussian splatting for dynamic scenes,” International Conference on Computer Vision (ICCV), Honolulu, Hawai'i, USA, Oct. 2025. (Acceptance Rate: 24%) (Highlight) [Paper]
H. Chen, Z. Lin, and J. Zhang, “GI-GS: Global illumination decomposition on Gaussian splatting for inverse rendering,” International Conference on Learning Representations (ICLR), Singapore, April 2025. (Acceptance Rate: 32.08%) [Paper] [Project Page]
Efficient and Safe AI
Y. Huang, Z. Wang, Z. Yuan, Y. Ding, R. Gong, J. Guo, X. Liu, and J. Zhang, “MoDES: Accelerating mixture-of-experts multimodal large language models via dynamic expert skipping,” preprint. [Paper]
Y. Huang, X. Ge, R. Gong, C. Lv, J. Zhang, “LinVideo: A Post-training framework towards O(n) attention in efficient video generation,” preprint. [Paper]
Y. Li, Z. Liu, Z. Li, Z. Lin, and J. Zhang, “Token-level Data Selection for Safe LLM Fine-tuning,” International Conference on Learning Representations (ICLR), Rio de Janeiro, Brazil, April 2026. (Acceptance Rate: 28%)
Y. Huang, R. Gong, J. Liu, Y. Ding, C. Lv, H. Qin, and J. Zhang, “QVGen: Pushing the limit of quantized video generative models,” International Conference on Learning Representations (ICLR), Rio de Janeiro, Brazil, April 2026. (Acceptance Rate: 28%) [Paper]
X. Ge, X. Zhang, T. Xu, Y. Zhang, X. Zhang, Y. Wang, and J. Zhang, “SenseFlow: Scaling distribution matching for flow-based text-to-image distillation,” International Conference on Learning Representations (ICLR), Rio de Janeiro, Brazil, April 2026. (Acceptance Rate: 28%) [Paper]
Z. Ning, J. Shao, R. Xu, X. Guo, J. Zhang, C. Zhang, and X. Li, “CAS-Spec: Cascade adaptive self-speculative decoding for on-the-fly lossless inference acceleration of LLMs,” The Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS), San Diego, CA, USA, Dec. 2025. [Paper] (Acceptance Rate: 24.52%)
Y. Huang, Z. Wang, R. Gong, J. Liu, X. Zhang, J. Guo, X. Liu, and J. Zhang, “HarmoniCa: Harmonizing training and inference for better feature cache in diffusion transformer acceleration,” International Conference on Machine Learning (ICML), Vancouver, Canada, July 2025. (Acceptance Rate: 26.9%) [Paper]
J. Shao, F. Wu, and J. Zhang, “Selective knowledge sharing for privacy-preserving federated distillation without a good teacher,” Nature Communications, vol. 15, no. 349, Jan 2024. [Paper]
Neural Data Representation and Compression
R. Song, Y. Wang, T. Xu, Z. Liu, Z. Lin, and J. Zhang, “Low-Latency Neural LiDAR Compression with 2D Context Models,” International Conference on Learning Representations (ICLR), Rio de Janeiro, Brazil, April 2026. (Acceptance Rate: 28%)
X. Zhang*, X. Ge*, T. Xu, D. He, Y. Wang, H. Qin, G. Lu, J. Geng, and J. Zhang, “GaussianImage: 1000 FPS image representation and compression by 2D Gaussian splatting,” European Conference on Computer Vision (ECCV), Milano, Italy, Sept.-Oct. 2024. (* equal contribution) (Acceptance Rate: 27.9%) [Paper] [Code]
Z. Liu, X. Zhang, J. Shao, Z. Lin, and J. Zhang, “Bidirectional stereo image compression with cross-dimensional entropy model,” European Conference on Computer Vision (ECCV), Milano, Italy, Sept.-Oct. 2024. (Acceptance Rate: 27.9%) [Paper]
X. Zhang, R. Yang, D. He, X. Ge, T. Xu, Y. Wang, H. Qin, and J. Zhang, “Boosting neural representations for videos with a conditional decoder,” IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, USA, Jun. 2024. (Acceptance Rate: 23.6%) (Highlight, Top 2.8%) [Paper] [Code]
X. Ge, J. Luo, X. Zhang, T. Xu, G. Lu, D. He, J. Geng, Y. Wang, J. Zhang, and H. Qin, “Task-aware encoder control for deep video compression,” IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, USA, Jun. 2024. (Acceptance Rate: 23.6%) [Paper]
X. Zhang, J. Shao, and J. Zhang, “LDMIC: Learning-based distributed multi-view image coding,” International Conference on Learning Representations (ICLR), Kigali, Rwanda, May 2023. [Paper] [GitHub]
Reinforcement Learning
Z. Liu, X. Li, S. Chen, and J. Zhang, “GAS: Enhancing Reward-Cost Balance of Generative Model-assisted Offline Safe RL,” International Conference on Learning Representations (ICLR), Rio de Janeiro, Brazil, April 2026. (Acceptance Rate: 28%)
S. Li, X. Li, S. Chen, and J. Zhang, “Puzzle it Out: Local-to-Global World Model for Offline Multi-Agent Reinforcement Learning,” International Conference on Autonomous Agents and Multiagent Systems (AAMAS), Paphos, Cyprus, May 2026. (Acceptance Rate: 25%) [Paper]
Z. Liu, X. Li, and J. Zhang, “C2IQL: Constraint-conditioned implicit Q-learning for safe offline reinforcement learning,” International Conference on Machine Learning (ICML), Vancouver, Canada, July 2025. (Acceptance Rate: 26.9%)
Z. Liu, X. Li. S. Chen, G. Li, J. Jiang, and J. Zhang, “Reinforcement learning with intrinsically motivated feedback graph for lost-sales inventory control,” International Conference on Artificial Intelligence and Statistics (AISTATS), Mai Khao, Thailand, May 2025. (Acceptance Rate: 31.3%) [Paper]
X. Li, X. Wang, C. Bai, and J. Zhang, “Exponential topology-enabled scalable communication in multi-agent reinforcement learning,” International Conference on Learning Representations (ICLR), Singapore, April 2025. (Acceptance Rate: 32.08%) [Paper]
X. Li, L. Pan, and J. Zhang, “Kaleidoscope: Learnable masks for heterogeneous multi-agent reinforcement learning,” The Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS), Vancouver, Canada, Dec. 2024. (Acceptance Rate: 25.8%) [Paper] [Code]
X. Li, Z. Liu, S. Chen, and J. Zhang, “Individual contributions as intrinsic exploration scaffolds for multi-agent reinforcement learning,” International Conference on Machine Learning (ICML), Vienna, Austria, July 2024. (Acceptance Rate: 27.5%) [Paper] [Code] [Video]
O-RAN, Edge AI
B. Liu, Y. Lu, J. Zhao, Q. Yang, W. Wu, L. Chen, J. Chauhan, and Jun Zhang, “WiLLM: an open framework for LLM services over wireless systems,” preprint. [Paper]
B. Liu, J. Tong, and J. Zhang, “LLM-Slice: Dedicated wireless network slicing for large language models,” The 22nd ACM Conference on Embedded Networked Sensor Systems - Posters and Demos, Hangzhou, China, Nov. 2024. [Paper]
Y. Mao, X. Yu, K. Huang, A.-Y. Zhang, and J. Zhang, “Green edge AI: A contemporary survey,” Proc. IEEE, vol. 112, no. 7, pp. 880-911, July 2024. [Paper]
J. Shao, X. Zhang, and J. Zhang, “Task-oriented communication for edge video analytics,” IEEE Trans. Wireless Commun., vol. 23, no. 5, pp. 4141-4154, May 2024. [Paper] [GitHub]
J. Shao, Y. Mao, and J. Zhang, “Task-oriented communication for multidevice cooperative edge inference,” IEEE Trans. Wireless Commun., vol. 11, no. 1, pp. 73-87, Jan. 2023. [Paper]
J. Shao, Y. Mao, and J. Zhang, “Learning task-oriented communication for edge inference: An information bottleneck approach,” IEEE J. Select. Areas Commun, vol. 40, no. 1, pp. 197-211, Jan. 2022. (The 2025 IEEE Communications Society Katherine Johnson Young Author Best Paper Award) [Paper] [GitHub]
AI for Communications
S. Xie, H. Li, Z. Wang, S.H. Song, J. Zhang, and K. B. Letaief, “Towards Reasoning-Empowered Task-Oriented Communication for Agent Networks,” npj Wireless Technology, to appear.
K. Zhang, W. Yu, H. He, S. Song, J. Zhang, and K. B. Letaief, “Multimodal Mixture-of-Experts for ISAC in Low-Altitude Wireless Networks,” preprint. [Paper]
W. Yu, H. He, S. Song, J. Zhang, L. Dai, L. Zheng, and K. B. Letaief, “AI and deep learning for Terahertz ultra-massive MIMO: From model-driven approaches to foundation models,” Engineering, to appear. [Paper]
C. Wen, J. Tong, Z. Lin, and J. Zhang, “Neural representation for wireless radiation field reconstruction: A 3D Gaussian splatting approach,” IEEE Trans. Wireless Commun., to appear. [Paper]
C. Wen, J. Tong, Z. Lin, and J. Zhang, “WRF-GS: Wireless radiation field reconstruction with 3D Gaussian splatting,” Proc. IEEE INFOCOM, London, United Kingdom, May 2025. (Acceptance Rate: 18.7%) [Paper] [Code]
J. Tong, J. Shao, Q. Wu, W. Guo, Z. Li, Z. Lin, and J. Zhang, “WirelessAgent: Large language model agents for intelligent wireless networks,” China Communications, to appear. [Paper]
J. Shao, J. Tong, Q. Wu, W. Guo, Z. Li, Z. Lin, and Jun Zhang, “WirelessLLM: Empowering large language models towards wireless intelligence,” Journal of Communications and Information Networks, vol. 9, no. 2, pp. 99-112, June 2024. [Paper]
W. Yu, Y. Shen, H. He, X. Yu, S.H. Song, J. Zhang, and K. B. Letaief, “An adaptive and robust deep learning framework for THz ultra-massive MIMO channel estimation,” IEEE J. Sel. Topics Signal Process., vol. 17, no. 4, pp. 761-776, July 2023. [Paper] [GitHub]
Y. Shen, Y. Shi, J. Zhang, and K. B. Letaief, “Graph neural networks for scalable radio resource management: architecture design and theoretical analysis,” IEEE J. Select. Areas Commun, vol. 39, no. 1, pp. 101–115, Jan. 2021. [Paper]