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.

Social platforms have revolutionized information sharing, but also accelerated the dissemination of harmful and policy-violating content. To ensure safety and compliance at scale, moderation systems must go beyond efficiency and offer accuracy and interpretability. However, current approaches largely rely on noisy, label-driven learning, lacking alignment with moderation rules and producing opaque decisions that hinder human review. Therefore, we propose Hierarchical Guard (Hi-Guard), a multimodal moderation framework that introduces a new policy-aligned decision paradigm. The term "Hierarchical" reflects two key aspects of our system design: (1) a hierarchical moderation pipeline, where a lightweight binary model first filters safe content and a stronger model handles fine-grained risk classification; and (2) a hierarchical taxonomy in the second stage, where the model performs path-based classification over a hierarchical taxonomy ranging from coarse to fine-grained levels. To ensure alignment with evolving moderation policies, Hi-Guard directly incorporates rule definitions into the model prompt. To further enhance structured prediction and reasoning, we introduce a multi-level soft-margin reward and optimize with Group Relative Policy Optimization (GRPO), penalizing semantically adjacent misclassifications and improving explanation quality. Extensive experiments and real-world deployment demonstrate that Hi-Guard achieves superior classification accuracy, generalization, and interpretability, paving the way toward scalable, transparent, and trustworthy content safety systems. Code is available at: https://github.com/lianqi1008/Hi-Guard.

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.

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.

Recent generative video codecs (GVCs) have achieved impressive reconstruction fidelity at ultra-low bitrates (< 0.02 bits per pixel) by compressing the tokens from generative tokenizers. However, existing GVCs generally require considerable computation time and model complexity, which hinder their deployment on compute-limited devices and in real-time applications. To bridge this gap, we systematically identify the computational bottlenecks and propose GVC-RT, which redesigns the generative latent coding framework to realize real-time video coding without sacrificing compression performance. Specifically, built on a pretrained lookup-free quantization (LFQ) tokenizer, GVC-RT adopts an asymmetric architecture that directly learns to match the LFQ latent distribution, while generative-space alignment is enforced via a regularization loss term only during training. In this manner, we bypass heavy tokenization and entirely remove the complex feature-alignment process at inference time. Moreover, we further introduce a lightweight de-tokenizer architecture to resolve the final latency bottleneck during decoding. Experimental results demonstrate that GVC-RT outperforms the previous SOTA model, GLC-Video, with average BD-rate savings of 12.4

The groundbreaking development of generative artificial intelligence (AI) is rapidly boosting the ability to generate content such as images and videos, reshaping communication paradigms. This article introduces generative communications (GenCom), a novel paradigm for 6G networks in which large AI models (LAMs) drive semantic understanding, reasoning, and content generation, embedding these into the communication process. Unlike traditional systems that strictly pursue accurate bit transmission, GenCom enables transmitters to convey only minimal yet sufficient information, while receivers leverage shared generative priors and knowledge bases to synthesize the intended output. Communication is thus redefined as controlled generation rather than data reproduction. We formalize the concept of GenCom, clarify its AI-native and generation-driven properties, and present its core mechanisms. A two-layer GenCom architecture supported by key enabling technologies is proposed, and analysis of four representative application scenarios demonstrates that GenCom offers ultra-efficient transmission, semantic-level robustness, and new network functions. Finally, we outline future research directions, including foundational theory and real-time processing, highlighting a promising pathway toward 6G networks.

Recent advancements in deep learning have driven significant progress in lossless image compression. With the emergence of Large Language Models (LLMs), preliminary attempts have been made to leverage the extensive prior knowledge embedded in these pretrained models to enhance lossless image compression, particularly by improving the entropy model. However, a significant challenge remains in bridging the gap between the textual prior knowledge within LLMs and lossless image compression. To tackle this challenge and unlock the potential of LLMs, this paper introduces a novel paradigm for lossless image compression that incorporates LLMs with visual prompts. Specifically, we first generate a lossy reconstruction of the input image as visual prompts, from which we extract features to serve as visual embeddings for the LLM. The residual between the original image and the lossy reconstruction is then fed into the LLM along with these visual embeddings, enabling the LLM to function as an entropy model to predict the probability distribution of the residual. Extensive experiments on multiple benchmark datasets demonstrate that our method achieves state-of-the-art compression performance, surpassing both traditional and learning-based lossless image codecs. For instance, on the DIV2K dataset, our method reduces bit consumption by 10.2% compared to the state-of-the-art DLPR. Furthermore, our approach can be readily extended to images from other domains, such as medical and screen content images, where it also delivers remarkable results. These results highlight the potential of LLMs for lossless image compression and may inspire further research in related fields.

Recent Learned image compression (LIC) leverages Mamba-style state-space models (SSMs) for global receptive fields with linear complexity. However, the standard Mamba adopts content-agnostic, predefined raster (or multi-directional) scans under strict causality. This rigidity hinders its ability to effectively eliminate redundancy between tokens that are content-correlated but spatially distant. We introduce Content-Aware Mamba (CAM), an SSM that dynamically adapts its processing to the image content. Specifically, CAM overcomes prior limitations with two novel mechanisms. First, it replaces the rigid scan with a content-adaptive token permutation strategy to prioritize interactions between content-similar tokens regardless of their location. Second, it overcomes the sequential dependency by injecting sample-specific global priors into the state-space model, which effectively mitigates the strict causality without multi-directional scans. These innovations enable CAM to better capture global redundancy while preserving computational efficiency. Our Content-Aware Mamba-based LIC model (CMIC) achieves state-of-the-art rate-distortion performance, surpassing VTM-21.0 by -15.91\%, -21.34\%, and -17.58\% BD-rate on Kodak, Tecnick, and CLIC benchmarks, respectively.

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

Recently, diffusion models have made great progress in video generation. However, most existing video diffusion models are trained with short videos, and degrade when extrapolated to long videos, struggling to maintain long-range temporal coherence while retaining diverse motions. To generate consistent, high-quality and dynamic long videos, we propose Diff-VF, a training-free, plug-and-play and model-agnostic framework that converts existing short-video diffusion backbones into long-video generators without modifying or fine-tuning the base model. Diff-VF couples three complementary strategies: Hybrid Noise Initialization (HNI) to constrain global semantics, Weighted Window Sampling (WWS) to remove inter-window discontinuities, and Temporal Extended Sampling (TES) to establish long-range dependencies with a timestep-varying fusion. We further extend Diff-VF to long-video enhancement via Skip Residual Guidance that balances fidelity and realism through timestep-dependent guidance. VBench-Long evaluation results show that Diff-VF achieves a more favorable balance between temporal coherence and motion diversity than base models and recent training-free long video generation baselines, including FreeNoise, FreeLong, and RIFLEx, while maintaining competitive frame-wise quality. Experiments on two base models demonstrate the applicability to video diffusion models with different spatial-temporal modeling strategies. Extensive ablations validate the contribution of each component and hyperparameters.

Recently, ultra-low bitrate video compression has become a key research field. However, existing video compression methods struggle to maintain adequate performance at ultra-low bitrates. This often manifests itself as compromised perceptual quality, including detail loss, texture blurring, and artifacts, and inconsistency between reconstructed and original videos. To address these challenges, we propose a Large Multimodal Model (LMM) powered Video Semantic Compression (LMM-VSC) method. The framework consists of: (1) a semantic information extractor, which extracts semantics from the input video, (2) a video encoder, which compresses the input video at ultra-low bitrates, and (3) a hybrid decoder, which integrates semantic information with highly compressed bitstreams. Experimental results demonstrate that under ultra-low bitrate conditions, the proposed method reduces the bitrate by 68.4% while maintaining perceptual quality comparable to the H.265 reference software.

Conventional communication systems, including both separation-based coding and learning-based joint source-channel coding (JSCC), are typically designed under Shannon's rate-distortion theory. However, relying on generic distortion metrics fails to capture complex human visual perception, often resulting in blurred or unrealistic reconstructions. In this paper, we propose Joint Source-Channel-Generation Coding (JSCGC), a generative communication paradigm that replaces the conventional decoder with a generative model at the receiver. The received signal is treated as a condition that controls the sampling process into the learned conditional distribution, reformulating communication from deterministic reconstruction for distortion minimization to controlled generation for mutual information maximization under perceptual constraints. Based on this formulation, we develop a unified joint training and efficient stochastic sampling framework, and provide theoretical analysis of its effectiveness in both learning and inference stages. Extensive experiments on latent-space image transmission demonstrate that the JSCGC consistently improves feature-based, semantic-level, and distributional quality across diverse channel conditions, while exhibiting a distinct error behavior characterized by semantic inconsistency rather than distortion.

Conventional communication systems, including both separation-based coding and AI-driven joint source-channel coding (JSCC), are largely guided by Shannon's rate-distortion theory. However, relying on generic distortion metrics fails to capture complex human visual perception, often resulting in blurred or unrealistic reconstructions. In this paper, we propose Joint Source-Channel-Generation Coding (JSCGC), a novel paradigm that shifts the focus from deterministic reconstruction to probabilistic generation. JSCGC leverages a generative model at the receiver as a generator rather than a conventional decoder to parameterize the data distribution, enabling direct maximization of mutual information under channel constraints while controlling stochastic sampling to produce outputs residing on the authentic data manifold with high fidelity. We further derive a theoretical lower bound on the maximum semantic inconsistency with given transmitted mutual information, elucidating the fundamental limits of communication in controlling the generative process. Extensive experiments on image transmission demonstrate that JSCGC substantially improves perceptual quality and semantic fidelity, significantly outperforming conventional distortion-oriented JSCC methods.

Efficient image compression relies on the accurate detection and elimination of both local and global redundancy. While most state-of-the-art (SOTA) learned image compression (LIC) methods are built on Convolutional Neural Networks (CNNs) or Transformer architectures, these frameworks are inherently rigid. Standard CNN kernels and window-based attention mechanisms impose fixed receptive fields and static connectivity patterns, which potentially couple non-redundant pixels simply due to their proximity in Euclidean space. This rigidity limits the model’s ability to adaptively capture spatially varying redundancy across the image, particularly at the global level.To overcome these limitations, we propose a content-adaptive image compression framework based on Graph Neural Networks (GNNs). Specifically, our approach constructs dual-scale graphs that enable flexible, data-driven receptive fields. Furthermore, we introduce adaptive connectivity by dynamically adjusting the number of neighbors for each node based on local content complexity. These innovations empower our Graph-based Learned Image Compression (GLIC) model to effectively model diverse redundancy patterns across images, leading to more efficient and adaptive compression.Experiments demonstrate that GLIC achieves SOTA performance, outperforming VTM-9.1 by-19.29\%, -21.69\%, -18.71\% in BD-rate on Kodak, Tecnick, and CLIC datasets, respectively. Code will be released.

In extreme-low bandwidth network scenarios, generative semantic codecs have emerged as promising solutions to reduce bandwidth cost for visual communications. However, these learned codecs are usually optimized solely for compression efficiency and thus not robust against transmission errors. Corruptions due to packet-loss among these highly compact generative latent representations often cause more critical degradation in fidelity and realism, intensified by the severe error propagation across the latent contexts and multi-step decoding process. In this paper, we propose ResiGLC, a novel loss-resilient generative latent coding framework designed for robust semantic communication over extreme-low bandwidth packet-loss networks. Motivated by the inherent goal-consistency between generation and compression, we sufficiently exploit the impressive in-context predictive capabilities of language models. Integrated with the masked learning strategy, our model supports arbitrary context modeling of latent codes, which could mitigate the error propagation and handle unpredictable packet loss patterns. At the receiver, a progressive resilient decoding pipeline is presented, which leverages both the contextual relationship of the latent codes and the multi-modal semantic prior in the generative latent space, separately. By jointly optimizing toward both compression efficiency and packet-loss resilience, our proposed progressive decoding mechanism offers graceful performance when dealing with dynamic packet losses. Through extensive experimental evaluations, we establish that under packet-loss network conditions, ResiGLC can effectively improve the loss-resilience in terms of perceptual fidelity and realism qualities with extreme-low bandwidth cost.

Building on recent advances in video generation, generative video compression has emerged as a new paradigm for achieving visually pleasing reconstructions. However, existing methods exhibit limited exploitation of temporal correlations, causing noticeable flicker and degraded temporal coherence at ultra-low bitrates. In this paper, we propose Free-GVC, a training-free generative video compression framework that reformulates video coding as latent trajectory compression guided by a video diffusion prior. Our method operates at the group-of-pictures (GOP) level, encoding video segments into a compact latent space and progressively compressing them along the diffusion trajectory. To ensure perceptually consistent reconstruction across GOPs, we introduce an Adaptive Quality Control module that dynamically constructs an online rate-perception surrogate model to predict the optimal diffusion step for each GOP. In addition, an Inter-GOP Alignment module establishes frame overlap and performs latent fusion between adjacent groups, thereby mitigating flicker and enhancing temporal coherence. Experiments show that Free-GVC achieves an average of 93.29

With the rapid growth of video traffic and the evolution of video formats, traditional video communication systems are encountering many challenges, such as limited data compression capacity, high energy consumption, and a narrow range of services. These challenges stem from the constraints of current systems, which rely heavily on discriminative methods for visual content reconstruction and achieve communication gains only in the information and physical domains. To address these issues, this paper introduces generative video communication, a novel paradigm that leverages generative artificial intelligence technologies to enhance video content expression. The core objective is to improve the expressive capabilities of video communication by enabling new gains in the cognitive domain (i.e., content dimension) while complementing existing frameworks. This paper presents key technical pathways for the proposed paradigm, including elastic encoding, collaborative transmission, and trustworthy evaluation, and explores its potential applications in task-oriented and immersive communication. Through this generative approach, we aim to overcome the limitations of traditional video communication systems, offering more efficient, adaptable, and immersive video services.

Learned image compression (LIC) has achieved impressive rate-distortion performance. However, existing methods remain highly vulnerable to packet loss, a common challenge in satellite and emergency communications. This vulnerability stems from non-uniform information distribution at the packetization stage and sequential decoding dependencies at the entropy coding stage. We propose an end-to-end loss-resilient image compression scheme that addresses both. Before packetization, we introduce an Inter-Channel Redistribution (ICR) mechanism to redistribute channel energy, preventing critical information concentrating in a small subset of channels. Then, an Interleaved Channel Grouping (ICG) strategy partitions latent channels in a strided manner to disperse information across packets, with each packet kept within constrained sizes. To limit cascading errors from lost packets, we adopt a two-layer dual-branch autoregressive structure to shorten the dependency chain. Extensive experiments demonstrate that our method consistently outperforms existing approaches in both reconstruction quality and stability. At 20

The rapid advancement of sixth-generation (6G) networks is accelerating the convergence of media intelligence and communication intelligence, driving media communication beyond conventional bit-level delivery toward intelligent, semantic-aware, and generative paradigms. Emerging media services require not only high data rates and low latency, but also semantic awareness, perceptual quality assurance, adaptive resource orchestration, trustworthy content processing, and personalized media generation. Meanwhile, media technologies are evolving from handcrafted signal processing and conventional coding toward artificial intelligence (AI)-driven representation learning, content understanding, and generative reconstruction. Motivated by these trends, this paper presents a systematic survey of media communication technologies for 6G vision communication by revisiting the evolution of communication and media technologies and clarifying the intrinsic relationship between media content processing and wireless transmission. We introduce a unified framework consisting of four key dimensions: AI-driven media technologies, media-aware wireless transmission, large model-enabled media communication, and intelligent network infrastructures. Specifically, AI-driven media technologies encompass media coding, content understanding, quality assessment, security and compliance detection, and AIGC-enabled media generation, while media-aware wireless transmission is examined from three complementary perspectives: semantic joint source-channel optimization, which jointly encodes task-relevant semantic information; source-aware transmission optimization, which leverages media characteristics for channel adaptation, prediction, and compensation; and channel-aware source optimization, which adapts media coding and reconstruction based on real-time channel conditions.

Generative joint source-channel coding (GenJSCC) has emerged as a new Deep JSCC paradigm for achieving highfidelity and robust image transmission under extreme wireless channel conditions, such as ultra-low bandwidth and low signal-to-noise ratio. Recent studies commonly adopt diffusion models as generative decoders, but they frequently produce visually realistic results with limited semantic consistency. This limitation stems from a fundamental mismatch between reconstruction-oriented JSCC encoders and generative decoders, as the former lack explicit semantic discriminability and fail to provide reliable conditional cues. In this paper, we propose DiT-JSCC, a novel GenJSCC backbone that can jointly learn a semantics-prioritized representation encoder and a diffusion transformer (DiT)-based generative decoder. Our open-source project aims to promote future research in GenJSCC. Specifically, we design a semantics-detail dual-branch encoder that aligns naturally with a coarse-to-fine conditional DiT decoder, prioritizing semantic consistency under extreme channel conditions. Moreover, a training-free adaptive bandwidth allocation strategy inspired by Kolmogorov complexity is introduced to further improve transmission efficiency, thereby redefining the notion of information value in the era of generative decoding. Extensive experiments demonstrate that DiT-JSCC consistently outperforms existing JSCC methods in both semantic consistency and visual quality, particularly in extreme regimes.