Magnetic Resonance Imaging (MRI) plays a crucial role in brain disease diagnosis, but it is not always feasible for certain patients due to physical or clinical constraints. Recent studies attempt to synthesize MRI from Computed Tomography (CT) scans; however, low-dose protocols often result in highly sparse CT volumes with poor throughplane resolution, making accurate reconstruction of the full brain MRI volume particularly challenging. To address this, we propose ReBrain, a retrieval-augmented diffusion framework for brain MRI reconstruction. Given any 3D CT scan with limited slices, we first employ a Brownian Bridge Diffusion Model (BBDM) to synthesize MRI slices along the 2D dimension. Simultaneously, we retrieve structurally and pathologically similar CT slices from a comprehensive prior database via a fine-tuned retrieval model. These retrieved slices are used as references, incorporated through a ControlNet branch to guide the generation of intermediate MRI slices and ensure structural continuity. We further account for rare retrieval failures when the database lacks suitable references and apply spherical linear interpolation to provide supplementary guidance. Extensive experiments on SynthRAD2023 and BraTS demonstrate that ReBrain achieves state-of-the-art performance in cross-modal reconstruction under sparse conditions.

Emotion recognition in conversation (ERC) has been promoted with diverse approaches in the recent years. However, many studies have pointed out that emotion shift and confusing labels make it difficult for models to distinguish between different emotions. Existing ERC models suffer from these problems when the emotions are forced to be mapped into single label. In this paper, we utilize our strategies for extending single label to multi-labels. We then propose a multi-label classification framework for emotion recognition in conversation (ML-ERC). Specifically, we introduce weighted supervised contrastive learning tailored for multi-label, which can easily applied to previous ERC models. The empirical results on existing task with single label support the efficacy of our approach, which is more effective in the most challenging settings: emotion shift or confusing labels. We also evaluate ML-ERC with the multi-labels we produced to support our contrastive learning scheme.

Recent advances in large language models (LLMs) have opened new possibilities for tablebased tasks.However, most existing methods remain confined to single-table settings, limiting their applicability to real-world databases composed of multiple interrelated tables.In multi-table scenarios, LLMs face two key challenges: reasoning over relational structures beyond sequential text, and handling the input length limitations imposed by large-scale table concatenation.To address these issues, we propose Guided Relational Integration for multiple Tables (GRIT), a lightweight method that converts relational schemas into LLMfriendly textual representations.GRIT employs hashing-based techniques to efficiently infer primary-foreign key relationships and constructs prompts that explicitly encode relevant join paths and question-relevant columns.GRIT consistently improves table-column retrieval performance across diverse multi-table benchmarks while significantly reducing memory and computational overhead.

This paper studies a data detection problem for multiple-input multiple-output (MIMO) communication systems with hardware impairments. To facilitate maximum likelihood (ML) data detection without knowledge of nonlinear and unknown hardware impairments, we develop a novel likelihood function estimation method based on data augmentation and boosting. In our method, we generate multiple augmented datasets by injecting noise with various distributions into seed data consisting of online received signals. We then estimate the likelihood function (LF) using each augmented dataset based on the expectationmaximization algorithm. We linearly combine the multiple LF estimates obtained from these datasets based on their reliability levels. Simulation results demonstrate that the ML detection combined with our LF estimation method outperforms existing methods, while also highlighting the effectiveness of our data augmentation approach.

This paper addresses a data detection problem for multiple-input multiple-output (MIMO) communication systems with hardware impairments. To facilitate maximum likelihood (ML) data detection without knowledge of nonlinear and unknown hardware impairments, we develop novel likelihood function (LF) estimation methods based on data augmentation and boosting. The core idea of our methods is to generate multiple augmented datasets by injecting noise with various distributions into seed data consisting of online received signals. We then estimate the LF using each augmented dataset based on either the expectation maximization (EM) algorithm or the kernel density estimation (KDE) method. Inspired by boosting, we further refine the estimated LF by linearly combining the multiple LF estimates obtained from the augmented datasets. To determine the weights for this linear combination, we develop methods that take different approaches to measure the reliability of the estimated LFs. Simulation results demonstrate that both the EM- and KDE-based LF estimation methods offer significant performance gains over existing LF estimation methods. Our results also show that the effectiveness of the proposed methods improves as the size of the augmented data increases.

Emotion recognition in conversation (ERC) has attracted much attention due to its wide applications.While consistent improvement is being made in this area, inevitable challenge comes from the dataset.The ERC dataset exhibits significantly imbalanced emotion distribution.While the utterances with neutral emotion predominate the data, this emotion label is always treated the same as other emotion labels in current approaches.To address the problem caused by the dataset, we propose a supervised contrastive learning specifically oriented for ERC task.We employ a novel data augmentation method emulating the emotion dynamics in a conversation and formulate supervised contrastive learning method tailored for ERC addressing the predominance and the ambiguity of neutral emotion.Experimental results on four benchmark datasets demonstrate the effectiveness of our approach.

ESA's SMOS mission has been a cornerstone in passive Earth Observation, since it has provided for the first time ever with global and frequent observations of Soil Moisture and Ocean Salinity (where the mission acronym comes from). SMOS' single payload is MIRAS: the Microwave Imaging Radiometers by Aperture Synthesis in two dimensions. After SMOS' success, today, a number of instruments are planned or under study: the GeoStar instrument is the baseline payload for the Precipitation and All-weather Temperature and Humidity (PATH) mission from NASA (USA), the Geostationary Atmospheric Sounder (GAS) instrument is under study for post-MSG operational satellites observations (Europe), and the Geostationary Interferometric Microwave Sounder (GIMS) instrument from NSSC-CAS (China). The study of the instrument performance in terms of angular resolution and radiometric performance (radiometric sensitivity and accuracy), and the optimization of this new type of instruments is a complex task that requires dedicated ad-hoc tools. In this work the SAIRPS (Synthetic Aperture Interferometric Radiometer Performance Simulator) is presented. This complex simulator allows to analyze arbitrary receiver topologies, arbitrary array geometries, and includes noise injection calibration algorithms, and new external robust calibration algorithms, and image reconstruction algorithms that allow to evaluate the performance of almost any instrument. At present, the full simulator has been coded in Matlab, translated into C++, and integrated in OpenSF. This work summarizes the key aspects of the architecture of this simulator, completing the presentation made in IGARSS 2012, and presents a few examples of the simulation results using different instrument configurations.