Rotatable Antennas for Integrated Sensing and Communications

In this letter, we propose to deploy rotatable antennas (RAs) at the base station (BS) to enhance both communication and sensing (C&S) performances, by exploiting a new spatial degree-of-freedom (DoF) offered by array rotation. Specifically, we formulate a multi-objective optimization problem to simultaneously maximize the sum-rate of multiple communication users and minimize the Cram\'er-Rao bound (CRB) for target angle estimation, by jointly optimizing the transmit beamforming vectors and the array rotation angle at the BS. To solve this problem, we first equivalently decompose it into two subproblems, corresponding to an inner problem for beamforming optimization and an outer problem for array rotation optimization. Although these two subproblems are non-convex, we obtain their high-quality solutions by applying the block coordinate descent (BCD) technique and one-dimensional exhaustive search, respectively. Moreover, we show that for the communication-only case, RAs provide an additional rotation gain to improve communication performance; while for the sensing-only case, the equivalent spatial aperture can be enlarged by RAs for achieving higher sensing accuracy. Finally, numerical results are presented to showcase the performance gains of RAs over fixed-rotation antennas in integrated sensing and communications (ISAC).

KVQ: Boosting Video Quality Assessment via Saliency-guided Local Perception

Video Quality Assessment (VQA), which intends to predict the perceptual quality of videos, has attracted increasing attention. Due to factors like motion blur or specific distortions, the quality of different regions in a video varies. Recognizing the region-wise local quality within a video is beneficial for assessing global quality and can guide us in adopting fine-grained enhancement or transcoding strategies. Due to the heavy cost of annotating region-wise quality, the lack of ground truth constraints from relevant datasets further complicates the utilization of local perception. Inspired by the Human Visual System (HVS) that links global quality to the local texture of different regions and their visual saliency, we propose a Kaleidoscope Video Quality Assessment (KVQ) framework, which aims to effectively assess both saliency and local texture, thereby facilitating the assessment of global quality. Our framework extracts visual saliency and allocates attention using Fusion-Window Attention (FWA) while incorporating a Local Perception Constraint (LPC) to mitigate the reliance of regional texture perception on neighboring areas. KVQ obtains significant improvements across multiple scenarios on five VQA benchmarks compared to SOTA methods. Furthermore, to assess local perception, we establish a new Local Perception Visual Quality (LPVQ) dataset with region-wise annotations. Experimental results demonstrate the capability of KVQ in perceiving local distortions. KVQ models and the LPVQ dataset will be available at https://github.com/qyp2000/KVQ.

Neural Network for Blind Unmixing: a novel MatrixConv Unmixing (MCU) Approach

Hyperspectral image (HSI) unmixing is a challenging research problem that tries to identify the constituent components, known as endmembers, and their corresponding proportions, known as abundances, in the scene by analysing images captured by hyperspectral cameras. Recently, many deep learning based unmixing approaches have been proposed with the surge of machine learning techniques, especially convolutional neural networks (CNN). However, these methods face two notable challenges: 1. They frequently yield results lacking physical significance, such as signatures corresponding to unknown or non-existent materials. 2. CNNs, as general-purpose network structures, are not explicitly tailored for unmixing tasks. In response to these concerns, our work draws inspiration from double deep image prior (DIP) techniques and algorithm unrolling, presenting a novel network structure that effectively addresses both issues. Specifically, we first propose a MatrixConv Unmixing (MCU) approach for endmember and abundance estimation, respectively, which can be solved via certain iterative solvers. We then unroll these solvers to build two sub-networks, endmember estimation DIP (UEDIP) and abundance estimation DIP (UADIP), to generate the estimation of endmember and abundance, respectively. The overall network is constructed by assembling these two sub-networks. In order to generate meaningful unmixing results, we also propose a composite loss function. To further improve the unmixing quality, we also add explicitly a regularizer for endmember and abundance estimation, respectively. The proposed methods are tested for effectiveness on both synthetic and real datasets.

Mixed Near-field and Far-field Target Localization for Low-altitude Economy

In this paper, we study efficient mixed near-field and far-field target localization methods for low-altitude economy, by capitalizing on extremely large-scale multiple-input multiple-output (XL-MIMO) communication systems. Compared with existing works, we address three new challenges in localization, arising from 1) half-wavelength antenna spacing constraint, 2) hybrid uniform planar array (UPA) architecture, and 3) incorrect mixed-field target classification for near-field targets.To address these issues, we propose a new three-step mixed-field localization method.First, we reconstruct the signals received at UPA antennas by judiciously designing analog combining matrices over time with minimum recovery errors, thus tackling the reduced-dimensional signal-space issue in hybrid arrays.Second, based on recovered signals, we devise a modified MUSIC algorithm (catered to UPA architecture) to estimate 2D angular parameters of both far- and near-field targets. Due to half-wavelength inter-antenna spacing, there exist ambiguous angles when estimating true angles of targets.In the third step, we design an effective classification method to distinguish mixed-field targets, determine true angles of all targets, as well as estimate the ranges of near-field targets. In particular, angular ambiguity is resolved by showing an important fact that the three types of estimated angles (i.e., far-field, near-field, and ambiguous angles) exhibit significantly different patterns in the range-domain MUSIC spectrum. Furthermore, to characterize the estimation error lower-bound, we obtain a matrix closed-form Cram\'er-Rao bounds for mixed-field target localization. Finally, numerical results demonstrate the effectiveness of our proposed mixed-field localization method, which improves target-classification accuracy and achieves a lower root mean square error than various benchmark schemes.

Learning Surrogate Potential Mean Field Games via Gaussian Processes: A Data-Driven Approach to Ill-Posed Inverse Problems

Mean field games (MFGs) describe the collective behavior of large populations of interacting agents. In this work, we tackle ill-posed inverse problems in potential MFGs, aiming to recover the agents' population, momentum, and environmental setup from limited, noisy measurements and partial observations. These problems are ill-posed because multiple MFG configurations can explain the same data, or different parameters can yield nearly identical observations. Nonetheless, they remain crucial in practice for real-world scenarios where data are inherently sparse or noisy, or where the MFG structure is not fully determined. Our focus is on finding surrogate MFGs that accurately reproduce the observed data despite these challenges. We propose two Gaussian process (GP)-based frameworks: an inf-sup formulation and a bilevel approach. The choice between them depends on whether the unknown parameters introduce concavity in the objective. In the inf-sup framework, we use the linearity of GPs and their parameterization structure to maintain convex-concave properties, allowing us to apply standard convex optimization algorithms. In the bilevel framework, we employ a gradient-descent-based algorithm and introduce two methods for computing the outer gradient. The first method leverages an existing solver for the inner potential MFG and applies automatic differentiation, while the second adopts an adjoint-based strategy that computes the outer gradient independently of the inner solver. Our numerical experiments show that when sufficient prior information is available, the unknown parameters can be accurately recovered. Otherwise, if prior information is limited, the inverse problem is ill-posed, but our frameworks can still produce surrogate MFG models that closely match observed data.

Visual Autoregressive Modeling for Image Super-Resolution

Image Super-Resolution (ISR) has seen significant progress with the introduction of remarkable generative models. However, challenges such as the trade-off issues between fidelity and realism, as well as computational complexity, have also posed limitations on their application. Building upon the tremendous success of autoregressive models in the language domain, we propose \textbf{VARSR}, a novel visual autoregressive modeling for ISR framework with the form of next-scale prediction. To effectively integrate and preserve semantic information in low-resolution images, we propose using prefix tokens to incorporate the condition. Scale-aligned Rotary Positional Encodings are introduced to capture spatial structures and the diffusion refiner is utilized for modeling quantization residual loss to achieve pixel-level fidelity. Image-based Classifier-free Guidance is proposed to guide the generation of more realistic images. Furthermore, we collect large-scale data and design a training process to obtain robust generative priors. Quantitative and qualitative results show that VARSR is capable of generating high-fidelity and high-realism images with more efficiency than diffusion-based methods. Our codes will be released at https://github.com/qyp2000/VARSR.

Plug-and-Play Tri-Branch Invertible Block for Image Rescaling

High-resolution (HR) images are commonly downscaled to low-resolution (LR) to reduce bandwidth, followed by upscaling to restore their original details. Recent advancements in image rescaling algorithms have employed invertible neural networks (INNs) to create a unified framework for downscaling and upscaling, ensuring a one-to-one mapping between LR and HR images. Traditional methods, utilizing dual-branch based vanilla invertible blocks, process high-frequency and low-frequency information separately, often relying on specific distributions to model high-frequency components. However, processing the low-frequency component directly in the RGB domain introduces channel redundancy, limiting the efficiency of image reconstruction. To address these challenges, we propose a plug-and-play tri-branch invertible block (T-InvBlocks) that decomposes the low-frequency branch into luminance (Y) and chrominance (CbCr) components, reducing redundancy and enhancing feature processing. Additionally, we adopt an all-zero mapping strategy for high-frequency components during upscaling, focusing essential rescaling information within the LR image. Our T-InvBlocks can be seamlessly integrated into existing rescaling models, improving performance in both general rescaling tasks and scenarios involving lossy compression. Extensive experiments confirm that our method advances the state of the art in HR image reconstruction.

Retrieval Augmented Image Harmonization

When embedding objects (foreground) into images (background), considering the influence of photography conditions like illumination, it is usually necessary to perform image harmonization to make the foreground object coordinate with the background image in terms of brightness, color, and etc. Although existing image harmonization methods have made continuous efforts toward visually pleasing results, they are still plagued by two main issues. Firstly, the image harmonization becomes highly ill-posed when there are no contents similar to the foreground object in the background, making the harmonization results unreliable. Secondly, even when similar contents are available, the harmonization process is often interfered with by irrelevant areas, mainly attributed to an insufficient understanding of image contents and inaccurate attention. As a remedy, we present a retrieval-augmented image harmonization (Raiha) framework, which seeks proper reference images to reduce the ill-posedness and restricts the attention to better utilize the useful information. Specifically, an efficient retrieval method is designed to find reference images that contain similar objects as the foreground while the illumination is consistent with the background. For training the Raiha framework to effectively utilize the reference information, a data augmentation strategy is delicately designed by leveraging existing non-reference image harmonization datasets. Besides, the image content priors are introduced to ensure reasonable attention. With the presented Raiha framework, the image harmonization performance is greatly boosted under both non-reference and retrieval-augmented settings. The source code and pre-trained models will be publicly available.

Learning Spatially Decoupled Color Representations for Facial Image Colorization

Image colorization methods have shown prominent performance on natural images. However, since humans are more sensitive to faces, existing methods are insufficient to meet the demands when applied to facial images, typically showing unnatural and uneven colorization results. In this paper, we investigate the facial image colorization task and find that the problems with facial images can be attributed to an insufficient understanding of facial components. As a remedy, by introducing facial component priors, we present a novel facial image colorization framework dubbed FCNet. Specifically, we learn a decoupled color representation for each face component (e.g., lips, skin, eyes, and hair) under the guidance of face parsing maps. A chromatic and spatial augmentation strategy is presented to facilitate the learning procedure, which requires only grayscale and color facial image pairs. After training, the presented FCNet can be naturally applied to facial image colorization with single or multiple reference images. To expand the application paradigms to scenarios with no reference images, we further train two alternative modules, which predict the color representations from the grayscale input or a random seed, respectively. Extensive experiments show that our method can perform favorably against existing methods in various application scenarios (i.e., no-, single-, and multi-reference facial image colorization). The source code and pre-trained models will be publicly available.

LEADRE: Multi-Faceted Knowledge Enhanced LLM Empowered Display Advertisement Recommender System

Display advertising provides significant value to advertisers, publishers, and users. Traditional display advertising systems utilize a multi-stage architecture consisting of retrieval, coarse ranking, and final ranking. However, conventional retrieval methods rely on ID-based learning to rank mechanisms and fail to adequately utilize the content information of ads, which hampers their ability to provide diverse recommendation lists. To address this limitation, we propose leveraging the extensive world knowledge of LLMs. However, three key challenges arise when attempting to maximize the effectiveness of LLMs: "How to capture user interests", "How to bridge the knowledge gap between LLMs and advertising system", and "How to efficiently deploy LLMs". To overcome these challenges, we introduce a novel LLM-based framework called LLM Empowered Display ADvertisement REcommender system (LEADRE). LEADRE consists of three core modules: (1) The Intent-Aware Prompt Engineering introduces multi-faceted knowledge and designs intent-aware <Prompt, Response> pairs that fine-tune LLMs to generate ads tailored to users' personal interests. (2) The Advertising-Specific Knowledge Alignment incorporates auxiliary fine-tuning tasks and Direct Preference Optimization (DPO) to align LLMs with ad semantic and business value. (3) The Efficient System Deployment deploys LEADRE in an online environment by integrating both latency-tolerant and latency-sensitive service. Extensive offline experiments demonstrate the effectiveness of LEADRE and validate the contributions of individual modules. Online A/B test shows that LEADRE leads to a 1.57% and 1.17% GMV lift for serviced users on WeChat Channels and Moments separately. LEADRE has been deployed on both platforms, serving tens of billions of requests each day.