Jincheng Dai

Ke Yang, Sixian Wang, Jincheng Dai et al.

In this paper, we aim to redesign the vision Transformer (ViT) as a new backbone to realize semantic image transmission, termed wireless image transmission transformer (WITT). Previous works build upon convolutional neural networks (CNNs), which are inefficient in capturing global dependencies, resulting in degraded end-to-end transmission performance especially for high-resolution images. To tackle this, the proposed WITT employs Swin Transformers as a more capable backbone to extract long-range information. Different from ViTs in image classification tasks, WITT is highly optimized for image transmission while considering the effect of the wireless channel. Specifically, we propose a spatial modulation module to scale the latent representations according to channel state information, which enhances the ability of a single model to deal with various channel conditions. As a result, extensive experiments verify that our WITT attains better performance for different image resolutions, distortion metrics, and channel conditions. The code is available at https://github.com/KeYang8/WITT.

Sixian Wang, Jincheng Dai, Zijian Liang et al.

In this paper, we design a new class of high-efficiency deep joint source-channel coding methods to achieve end-to-end video transmission over wireless channels. The proposed methods exploit nonlinear transform and conditional coding architecture to adaptively extract semantic features across video frames, and transmit semantic feature domain representations over wireless channels via deep joint source-channel coding. Our framework is collected under the name deep video semantic transmission (DVST). In particular, benefiting from the strong temporal prior provided by the feature domain context, the learned nonlinear transform function becomes temporally adaptive, resulting in a richer and more accurate entropy model guiding the transmission of current frame. Accordingly, a novel rate adaptive transmission mechanism is developed to customize deep joint source-channel coding for video sources. It learns to allocate the limited channel bandwidth within and among video frames to maximize the overall transmission performance. The whole DVST design is formulated as an optimization problem whose goal is to minimize the end-to-end transmission rate-distortion performance under perceptual quality metrics or machine vision task performance metrics. Across standard video source test sequences and various communication scenarios, experiments show that our DVST can generally surpass traditional wireless video coded transmission schemes. The proposed DVST framework can well support future semantic communications due to its video content-aware and machine vision task integration abilities.

Jincheng Dai, Ping Zhang, Kai Niu et al.

Classical communication paradigms focus on accurately transmitting bits over a noisy channel, and Shannon theory provides a fundamental theoretical limit on the rate of reliable communications. In this approach, bits are treated equally, and the communication system is oblivious to what meaning these bits convey or how they would be used. Future communications towards intelligence and conciseness will predictably play a dominant role, and the proliferation of connected intelligent agents requires a radical rethinking of coded transmission paradigm to support the new communication morphology on the horizon. The recent concept of "semantic communications" offers a promising research direction. Injecting semantic guidance into the coded transmission design to achieve semantics-aware communications shows great potential for further breakthrough in effectiveness and reliability. This article sheds light on semantics-guided source and channel coding as a transmission paradigm of semantic communications, which exploits both data semantics diversity and wireless channel diversity together to boost the whole system performance. We present the general system architecture and key techniques, and indicate some open issues on this topic.

Jun Wang, Sixian Wang, Jincheng Dai et al.

As one novel approach to realize end-to-end wireless image semantic transmission, deep learning-based joint source-channel coding (deep JSCC) method is emerging in both deep learning and communication communities. However, current deep JSCC image transmission systems are typically optimized for traditional distortion metrics such as peak signal-to-noise ratio (PSNR) or multi-scale structural similarity (MS-SSIM). But for low transmission rates, due to the imperfect wireless channel, these distortion metrics lose significance as they favor pixel-wise preservation. To account for human visual perception in semantic communications, it is of great importance to develop new deep JSCC systems optimized beyond traditional PSNR and MS-SSIM metrics. In this paper, we introduce adversarial losses to optimize deep JSCC, which tends to preserve global semantic information and local texture. Our new deep JSCC architecture combines encoder, wireless channel, decoder/generator, and discriminator, which are jointly learned under both perceptual and adversarial losses. Our method yields human visually much more pleasing results than state-of-the-art engineered image coded transmission systems and traditional deep JSCC systems. A user study confirms that achieving the perceptually similar end-to-end image transmission quality, the proposed method can save about 50\% wireless channel bandwidth cost.

Jincheng Dai, Sixian Wang, Ke Yang et al.

The emerging field semantic communication is driving the research of end-to-end data transmission. By utilizing the powerful representation ability of deep learning models, learned data transmission schemes have exhibited superior performance than the established source and channel coding methods. While, so far, research efforts mainly concentrated on architecture and model improvements toward a static target domain. Despite their successes, such learned models are still suboptimal due to the limitations in model capacity and imperfect optimization and generalization, particularly when the testing data distribution or channel response is different from that adopted for model training, as is likely to be the case in real-world. To tackle this, we propose a novel online learned joint source and channel coding approach that leverages the deep learning model's overfitting property. Specifically, we update the off-the-shelf pre-trained models after deployment in a lightweight online fashion to adapt to the distribution shifts in source data and environment domain. We take the overfitting concept to the extreme, proposing a series of implementation-friendly methods to adapt the codec model or representations to an individual data or channel state instance, which can further lead to substantial gains in terms of the bandwidth ratio-distortion performance. The proposed methods enable the communication-efficient adaptation for all parameters in the network without sacrificing decoding speed. Our experiments, including user study, on continually changing target source data and wireless channel environments, demonstrate the effectiveness and efficiency of our approach, on which we outperform existing state-of-the-art engineered transmission scheme (VVC combined with 5G LDPC coded transmission).

Huanxiong Liang, Yunuo Chen, Yicheng Pan et al.

Recent advances in 2D Gaussian Splatting (2DGS) have demonstrated its potential as a compact image representation with millisecond-level decoding. However, existing 2DGS-based pipelines allocate representation capacity and parameter precision largely oblivious to image structure, limiting their rate-distortion (RD) efficiency at low bitrates. To address this, we propose a structure-guided allocation principle for 2DGS, which explicitly couples image structure with both representation capacity and quantization precision, while preserving native decoding speed. First, we introduce a structure-guided initialization that assigns 2D Gaussians according to spatial structural priors inherent in natural images, yielding a localized and semantically meaningful distribution. Second, during quantization-aware fine-tuning, we propose adaptive bitwidth quantization of covariance parameters, which grants higher precision to small-scale Gaussians in complex regions and lower precision elsewhere, enabling RD-aware optimization, thereby reducing redundancy without degrading edge quality. Third, we impose a geometry-consistent regularization that aligns Gaussian orientations with local gradient directions to better preserve structural details. Extensive experiments demonstrate that our approach substantially improves both the representational power and the RD performance of 2DGS while maintaining over 1000 FPS decoding. Compared with the baseline GSImage, we reduce BD-rate by 43.44% on Kodak and 29.91% on DIV2K.

Hai-Long Qin, Jincheng Dai, Guo Lu et al.

Semantic communications mark a paradigm shift from bit-accurate transmission toward meaning-centric communication, essential as wireless systems approach theoretical capacity limits. The emergence of generative AI has catalyzed generative semantic communications, where receivers reconstruct content from minimal semantic cues by leveraging learned priors. Among generative approaches, diffusion models stand out for their superior generation quality, stable training dynamics, and rigorous theoretical foundations. However, the field currently lacks systematic guidance connecting diffusion techniques to communication system design, forcing researchers to navigate disparate literatures. This article provides the first comprehensive tutorial on diffusion models for generative semantic communications. We present score-based diffusion foundations and systematically review three technical pillars: conditional diffusion for controllable generation, efficient diffusion for accelerated inference, and generalized diffusion for cross-domain adaptation. In addition, we introduce an inverse problem perspective that reformulates semantic decoding as posterior inference, bridging semantic communications with computational imaging. Through analysis of human-centric, machine-centric, and agent-centric scenarios, we illustrate how diffusion models enable extreme compression while maintaining semantic fidelity and robustness. By bridging generative AI innovations with communication system design, this article aims to establish diffusion models as foundational components of next-generation wireless networks and beyond.

Weixuan Chen, Qianqian Yang, Yuanyuan Jia et al.

Semantic communication (SemCom) has emerged as a promising paradigm for future wireless networks by prioritizing task-relevant meaning over raw data delivery, thereby reducing communication overhead and improving efficiency. However, shifting from bit-accurate transmission to task-oriented delivery introduces new security and privacy risks. These include semantic leakage, semantic manipulation, knowledge base vulnerabilities, model-related attacks, and threats to authenticity and availability. Most existing secure SemCom studies focus on analog SemCom, where semantic features are mapped to continuous channel inputs. In contrast, digital SemCom transmits semantic information through discrete bits or symbols within practical transceiver pipelines, offering stronger compatibility with realworld systems while exposing a distinct and underexplored attack surface. In particular, digital SemCom typically represents semantic information over a finite alphabet through explicit digital modulation, following two main routes: probabilistic modulation and deterministic modulation. These discrete mechanisms and practical transmission procedures introduce additional vulnerabilities affecting bit- or symbol-level semantic information, the modulation stage, and packet-based delivery and protocol operations. Motivated by these challenges and the lack of a systematic analysis of secure digital SemCom, this paper provides a structured review of the area. Specifically, we review SemCom fundamentals and clarify the architectural differences between analog and digital SemCom. We then summarize threats shared by both paradigms and organize the threat landscape specific to digital SemCom, followed by a discussion of potential defenses. Finally, we outline open research directions toward secure and deployable digital SemCom systems.

Junhao Du, Jialong Xue, Anqi Li et al.

Video large language models (Video-LLMs) face high computational costs due to large volumes of visual tokens. Existing token compression methods typically adopt a two-stage spatiotemporal compression strategy, relying on stage-specific metrics and an implicit assumption of spatiotemporal separability. Under extremely low retention ratios, however, such approaches often result in unbalanced allocation and loss of visual evidence essential for question answering. We reformulate token compression as a spatiotemporal allocation task within a global token retention pool. We propose a unified selection mechanism that integrates attention weights and semantic similarity to globally select tokens with high contribution and low redundancy. Unselected tokens are merged via clustering and refilled, preserving information integrity. Inside the LLM, we further introduce text-aware merging to perform secondary compression based on query relevance. Without requiring retraining, our method serves as a plug-and-play module compatible with existing Video-LLMs. Experiments show that retaining only about 2% of visual tokens preserves 90.1% of baseline performance across multiple benchmarks, while reducing FLOPs to roughly 2.6%. These benefits generalize across diverse backbones, decreasing end-to-end inference latency and memory consumption. Our unified spatiotemporal token compression strategy establishes the state-of-the-art in video understanding under ultra-low token retention.

Chuqin Zhou, Xiaoyue Ling, Yunuo Chen et al.

While recent neural codecs achieve strong performance at low bitrates when optimized for perceptual quality, their effectiveness deteriorates significantly under ultra-low bitrate conditions. To mitigate this, generative compression methods leveraging semantic priors from pretrained models have emerged as a promising paradigm. However, existing approaches are fundamentally constrained by a tradeoff between semantic faithfulness and perceptual realism. Methods based on explicit representations preserve content structure but often lack fine-grained textures, whereas implicit methods can synthesize visually plausible details at the cost of semantic drift. In this work, we propose a unified framework that bridges this gap by coherently integrating explicit and implicit representations in a training-free manner. Specifically, We condition a diffusion model on explicit high-level semantics while employing reverse-channel coding to implicitly convey fine-grained details. Moreover, we introduce a plug-in encoder that enables flexible control of the distortion-perception tradeoff by modulating the implicit information. Extensive experiments demonstrate that the proposed framework achieves state-of-the-art rate-perception performance, outperforming existing methods and surpassing DiffC by 29.92%, 19.33%, and 20.89% in DISTS BD-Rate on the Kodak, DIV2K, and CLIC2020 datasets, respectively.

Yunuo Chen, Chuqin Zhou, Jiangchuan Li et al.

We present a novel paradigm for ultra-low-bitrate image compression (ULB-IC) that exploits the ``temporal'' evolution in generative image compression. Specifically, we define an explicit intermediate state during decoding: a compact anchor frame, which preserves the scene geometry and semantic layout while discarding high-frequency details. We then reinterpret generative decoding as a virtual temporal transition from this anchor to the final reconstructed image.To model this progression, we leverage a pretrained video diffusion model (VDM) as temporal priors: the anchor frame serves as the initial frame and the original image as the target frame, transforming the decoding process into a next-frame prediction task.In contrast to image diffusion-based ULB-IC models, our decoding proceeds from a visible, semantically faithful anchor, which improves both fidelity and realism for perceptual image compression. Extensive experiments demonstrate that our method achieves superior objective and subjective performance. On the CLIC2020 test set, our method achieves over \textbf{50\% bitrate savings} across LPIPS, DISTS, FID, and KID compared to DiffC, while also delivering a significant decoding speedup of up to $\times$5. Code will be released later.

Shuo Shao, Chao Qi, Jincheng Dai

In this paper we study the nonasymptotic bounds of a special Joint Source-Channel Coding system with hierarchical source, where an observable source and an unobservable indirect source are required to be reconstructed. Namely, we focus on the achievable and converse bounds of the excess distortion probability in the finite blocklength regime. The main challenge arises from the hierarchical source structure, which requires simultaneous reconstruction of both sources. This setup demands a coding scheme which satisfy the demand of encoding both source for the achievability bound, and a method to characterize the joint excess-distortion probability of two correlated events for the converse bound.

Jincheng Dai, Zhuowei Huang, Haiyun Jiang et al.

Large Language Models (LLMs), despite their remarkable performance across a wide range of tasks, necessitate substantial GPU memory and consume significant computational resources. Beyond the memory taken up by model weights, the memory used by the KV cache rises linearly with sequence length, becoming a primary bottleneck for inference. In this paper, we introduce an innovative method for optimizing the KV cache, which considerably minimizes its memory footprint. Upon thorough investigation, we discover that in most Transformer models, (i) there is a striking similarity between adjacent tokens' query vectors, and (ii) the attention calculation of the current query can rely exclusively on the attention information of a small fraction of preceding queries. Based on these observations, we present CORM, a KV cache eviction policy that dynamically retains essential key-value pairs for inference without the need for model fine-tuning. Our validation shows that CORM reduces the inference memory usage of KV cache by up to 70\% with negligible performance degradation across six tasks in LongBench. Furthermore, we demonstrate that CORM is compatible with GQA for further compression rate.

Weijie Yue, Zhongwei Si, Bolin Wu et al.

We introduce NeRFCom, a novel communication system designed for end-to-end 3D scene transmission. Compared to traditional systems relying on handcrafted NeRF semantic feature decomposition for compression and well-adaptive channel coding for transmission error correction, our NeRFCom employs a nonlinear transform and learned probabilistic models, enabling flexible variable-rate joint source-channel coding and efficient bandwidth allocation aligned with the NeRF semantic feature's different contribution to the 3D scene synthesis fidelity. Experimental results demonstrate that NeRFCom achieves free-view 3D scene efficient transmission while maintaining robustness under adverse channel conditions.

Jincheng Dai, Xiaoqi Qin, Sixian Wang et al.

Information theory and machine learning are inextricably linked and have even been referred to as "two sides of the same coin". One particularly elegant connection is the essential equivalence between probabilistic generative modeling and data compression or transmission. In this article, we reveal the dual-functionality of deep generative models that reshapes both data compression for efficiency and transmission error concealment for resiliency. We present how the contextual predictive capabilities of powerful generative models can be well positioned to be strong compressors and estimators. In this sense, we advocate for viewing the deep generative modeling problem through the lens of end-to-end communications, and evaluate the compression and error restoration capabilities of foundation generative models. We show that the kernel of many large generative models is powerful predictor that can capture complex relationships among semantic latent variables, and the communication viewpoints provide novel insights into semantic feature tokenization, contextual learning, and usage of deep generative models. In summary, our article highlights the essential connections of generative AI to source and channel coding techniques, and motivates researchers to make further explorations in this emerging topic.

Sixian Wang, Ke Yang, Jincheng Dai et al.

We study the problem of deep joint source-channel coding (D-JSCC) for correlated image sources, where each source is transmitted through a noisy independent channel to the common receiver. In particular, we consider a pair of images captured by two cameras with probably overlapping fields of view transmitted over wireless channels and reconstructed in the center node. The challenging problem involves designing a practical code to utilize both source and channel correlations to improve transmission efficiency without additional transmission overhead. To tackle this, we need to consider the common information across two stereo images as well as the differences between two transmission channels. In this case, we propose a deep neural networks solution that includes lightweight edge encoders and a powerful center decoder. Besides, in the decoder, we propose a novel channel state information aware cross attention module to highlight the overlapping fields and leverage the relevance between two noisy feature maps.Our results show the impressive improvement of reconstruction quality in both links by exploiting the noisy representations of the other link. Moreover, the proposed scheme shows competitive results compared to the separated schemes with capacity-achieving channel codes.

Jincheng Dai, Sixian Wang, Kailin Tan et al.

In this paper, we propose a class of high-efficiency deep joint source-channel coding methods that can closely adapt to the source distribution under the nonlinear transform, it can be collected under the name nonlinear transform source-channel coding (NTSCC). In the considered model, the transmitter first learns a nonlinear analysis transform to map the source data into latent space, then transmits the latent representation to the receiver via deep joint source-channel coding. Our model incorporates the nonlinear transform as a strong prior to effectively extract the source semantic features and provide side information for source-channel coding. Unlike existing conventional deep joint source-channel coding methods, the proposed NTSCC essentially learns both the source latent representation and an entropy model as the prior on the latent representation. Accordingly, novel adaptive rate transmission and hyperprior-aided codec refinement mechanisms are developed to upgrade deep joint source-channel coding. The whole system design is formulated as an optimization problem whose goal is to minimize the end-to-end transmission rate-distortion performance under established perceptual quality metrics. Across test image sources with various resolutions, we find that the proposed NTSCC transmission method generally outperforms both the analog transmission using the standard deep joint source-channel coding and the classical separation-based digital transmission. Notably, the proposed NTSCC method can potentially support future semantic communications due to its content-aware ability and perceptual optimization goal.