Commercial-grade poster design demands the seamless integration of aesthetic appeal with precise, informative content delivery. Current automated poster generation systems face significant limitations, including incomplete design workflows, poor text rendering accuracy, and insufficient flexibility for commercial applications. To address these challenges, we propose PosterVerse, a full-workflow, commercial-grade poster generation method that seamlessly automates the entire design process while delivering high-density and scalable text rendering. PosterVerse replicates professional design through three key stages: (1) blueprint creation using fine-tuned LLMs to extract key design elements from user requirements, (2) graphical background generation via customized diffusion models to create visually appealing imagery, and (3) unified layout-text rendering with an MLLM-powered HTML engine to guarantee high text accuracy and flexible customization. In addition, we introduce PosterDNA, a commercial-grade, HTML-based dataset tailored for training and validating poster design models. To the best of our knowledge, PosterDNA is the first Chinese poster generation dataset to introduce HTML typography files, enabling scalable text rendering and fundamentally solving the challenges of rendering small and high-density text. Experimental results demonstrate that PosterVerse consistently produces commercial-grade posters with appealing visuals, accurate text alignment, and customizable layouts, making it a promising solution for automating commercial poster design.

Inscriptions are invaluable cultural heritage, yet centuries of degradation (e.g., fractures, erosion, oxidation) have rendered many partially illegible. Existing Historical Inscription Restoration (HIR) methods rely on task-separated pipelines with irreversible error accumulation and patch-based generation that sacrifices page-level consistency. Therefore, we present UniHIR, the first unified MLLM for end-to-end historical inscription restoration. It integrates two novel designs, Draft-Guided Localization and Hierarchical Self-Refinement, to enable accurate damage localization and illegible-content prediction via iterative reasoning and self-correction. This unified approach enables true page-level restoration with consistent typography and style. To support training under high-resolution inputs and long sequences, we design UHIRFactory and construct HIRBench, enabling step-wise, memory-efficient instruction tuning with step-aware annotations for intermediate drafts and refinements. Experiments demonstrate that UniHIR achieves superior performance in both text restoration accuracy and appearance restoration quality, validating that HIR can be effectively tackled by a standalone model in a unified manner. The model and code are available at https://github.com/ZZXF11/UniHIR.

ABSTRACT With the gradual increase in the demand for efficient monitoring of electrical equipment, the volume of multi‐mode data, such as images and voiceprints, is also growing. This situation imposes new challenges on the allocation of limited bandwidth resources. Traditional allocation methods suffer from issues such as low bandwidth utilisation and mismatch between bandwidth resources and multi‐mode data transmission demands. To address these problems, a dynamic bandwidth allocation method based on multi‐mode data prediction for application in internet of things (IoT)‐enabled electrical equipment monitoring is proposed in this paper. Firstly, a multi‐mode data transmission architecture for IoT‐enabled electrical equipment monitoring is designed, which includes models for multi‐mode data collection, compression, transmission, decoding, and fault identification. Secondly, a multi‐mode data transmission demand prediction method based on knowledge collaborative long short‐term memory (KC‐LSTM) is proposed, considering the intrinsic relationships and complementarity among multi‐mode data streams to achieve accurate prediction of multi‐mode data stream transmission demands. On this basis, a dynamic bandwidth allocation method based on multi‐mode data transmission demand‐aware deep actor critic (DAC) is proposed, which dynamically allocates transmission bandwidth according to the prediction results of multi‐mode data transmission demands. Meanwhile, by constructing a multi‐precision experience replay pool, the convergence performance of the algorithm in dynamic and challenging environments is improved. Simulation results demonstrate that the proposed algorithm achieves optimal multi‐mode data stream transmission efficiency and the highest fault identification accuracy. Compared to the three benchmark algorithms, the proposed algorithm achieves 12.35%, 17.91%, and 31.84% improvements in successfully decoded data volume and 49.04%, 56.38% and 26.53% enhancements in load balancing performance, respectively.

Feature Coding for Machines (FCM) aims to compress intermediate features effectively for remote intelligent analytics, which is crucial for future intelligent visual applications. In this article, we propose a Multiscale Feature Importance-based Bit Allocation (MFIBA) for end-to-end FCM. First, we find that the importance of features for machine vision tasks varies with the scales, object size, and image instances. Based on this finding, we propose a Multiscale Feature Importance Prediction (MFIP) module to predict the importance weight for each scale of features. Second, we propose a task loss-rate model to establish the relationship between the task accuracy losses of using compressed features and the bit rate of encoding these features. Finally, we develop an MFIBA for end-to-end FCM, which is able to assign coding bits of multiscale features more reasonably based on their importance. Experimental results demonstrate that when combined with a retained Efficient Learned Image Compression (ELIC), the proposed MFIBA achieves an average of 38.202% bit-rate savings in object detection compared to the anchor ELIC. Moreover, the proposed MFIBA achieves an average of 17.212% and 36.492% feature bit-rate savings for instance segmentation and keypoint detection, respectively. When the proposed MFIBA is applied to the LIC-TCM, it achieves an average of 18.103%, 19.866%, and 19.597% bit-rate savings on three machine vision tasks, respectively, which validates the proposed MFIBA has good generalizability and adaptability to different machine vision tasks and FCM base codecs.