1 code implementation • 6 Dec 2024 • Chaozheng Wen, Jingwen Tong, Yingdong Hu, Zehong Lin, Jun Zhang
Nevertheless, developing an effective channel modeling approach has been a long-standing challenge.
no code implementations • 22 Nov 2024 • Zhening Liu, Yingdong Hu, Xinjie Zhang, Rui Song, Jiawei Shao, Zehong Lin, Jun Zhang
The recent development of 3D Gaussian Splatting (3DGS) has led to great interest in 4D dynamic spatial reconstruction.
no code implementations • 17 Oct 2024 • Xinjie Zhang, Zhening Liu, Yifan Zhang, Xingtong Ge, Dailan He, Tongda Xu, Yan Wang, Zehong Lin, Shuicheng Yan, Jun Zhang
Furthermore, we introduce an entropy-constrained Gaussian deformation technique that uses a deformation field to expand the action range of each Gaussian and integrates an opacity-based entropy loss to limit the number of Gaussians, thus forcing our model to use as few Gaussians as possible to fit a dynamic scene well.
no code implementations • 3 Oct 2024 • Hongze Chen, Zehong Lin, Jun Zhang
We present GI-GS, a novel inverse rendering framework that leverages 3D Gaussian Splatting (3DGS) and deferred shading to achieve photo-realistic novel view synthesis and relighting.
no code implementations • 2 Oct 2024 • Yingdong Hu, Zhening Liu, Jiawei Shao, Zehong Lin, Jun Zhang
To address this limitation, we propose a real-time pipeline named EVA-Gaussian for 3D human novel view synthesis across diverse camera settings.
1 code implementation • 12 Sep 2024 • Jingwen Tong, Jiawei Shao, Qiong Wu, Wei Guo, Zijian Li, Zehong Lin, Jun Zhang
Wireless networks are increasingly facing challenges due to their expanding scale and complexity.
1 code implementation • 15 Jul 2024 • Zhening Liu, Xinjie Zhang, Jiawei Shao, Zehong Lin, Jun Zhang
With the rapid advancement of stereo vision technologies, stereo image compression has emerged as a crucial field that continues to draw significant attention.
no code implementations • 27 May 2024 • Jiawei Shao, Jingwen Tong, Qiong Wu, Wei Guo, Zijian Li, Zehong Lin, Jun Zhang
To empower LLMs with knowledge and expertise in the wireless domain, this paper proposes WirelessLLM, a comprehensive framework for adapting and enhancing LLMs to address the unique challenges and requirements of wireless communication networks.
no code implementations • 29 Jan 2024 • Wenqiang Sun, Teng Li, Zehong Lin, Jun Zhang
Recently, text-to-image diffusion models have demonstrated impressive ability to generate high-quality images conditioned on the textual input.
no code implementations • 30 Aug 2023 • Zijian Li, Zehong Lin, Jiawei Shao, Yuyi Mao, Jun Zhang
However, devices often have non-independent and identically distributed (non-IID) data, meaning their local data distributions can vary significantly.
no code implementations • 20 Jul 2023 • Jiawei Shao, Zijian Li, Wenqiang Sun, Tailin Zhou, Yuchang Sun, Lumin Liu, Zehong Lin, Yuyi Mao, Jun Zhang
Without data centralization, FL allows clients to share local information in a privacy-preserving manner.
no code implementations • 6 Jul 2023 • Yifei Shen, Jiawei Shao, Xinjie Zhang, Zehong Lin, Hao Pan, Dongsheng Li, Jun Zhang, Khaled B. Letaief
The evolution of wireless networks gravitates towards connected intelligence, a concept that envisions seamless interconnectivity among humans, objects, and intelligence in a hyper-connected cyber-physical world.
no code implementations • 26 May 2023 • Yuchang Sun, Zehong Lin, Yuyi Mao, Shi Jin, Jun Zhang
In this paper, we propose a probabilistic device scheduling framework for over-the-air FL, named PO-FL, to mitigate the negative impact of channel noise, where each device is scheduled according to a certain probability and its model update is reweighted using this probability in aggregation.
1 code implementation • 13 May 2023 • Tailin Zhou, Zehong Lin, Jun Zhang, Danny H. K. Tsang
To gain further insights into model averaging in FL, we decompose the expected loss of the global model into five factors related to the client models.
no code implementations • 26 Jul 2022 • Zehong Lin, Hang Liu, Ying-Jun Angela Zhang
We propose a coexisting federated learning and information transfer (CFLIT) communication framework, where the FL and IT devices share the wireless spectrum in an OFDM system.
no code implementations • 6 Sep 2021 • Hang Liu, Zehong Lin, Xiaojun Yuan, Ying-Jun Angela Zhang
Federated edge learning (FEEL) has emerged as a revolutionary paradigm to develop AI services at the edge of 6G wireless networks as it supports collaborative model training at a massive number of mobile devices.
1 code implementation • 20 Jul 2021 • Zehong Lin, Hang Liu, Ying-Jun Angela Zhang
Then, we analyze the model aggregation error in a single-relay case and show that our relay-assisted scheme achieves a smaller error than the one without relays provided that the relay transmit power and the relay channel gains are sufficiently large.