The issue of diminished spectral efficiency (SE) of the downlink (DL) transmission in distributed cell-free massive MIMO (CF-mMIMO) systems poses a significant challenge in terms of user equipment (UE) performance when compared to their centralized CF-mMIMO counterparts. The primary root cause of this issue can be attributed to the reduced efficacy of distributed precoders, which are devised using local channel state information (CSI) in distributed systems. This reduced efficacy becomes particularly pronounced in terms of interference mitigation when compared to centralized precoders. To address this issue, this paper proposes a novel architectural framework for CF-mMIMO systems, referred to herein as the "cluster-based structure." Within this innovative structure, a hybrid amalgamation of centralized and distributed configurations is employed, complemented by the introduction of a unique cluster arrangement for the access points (APs) within the network. In this design, the CSI of APs within each cluster is collectively shared within a local processor unit. Consequently, by harnessing this enhanced repository of local channel information, local precoders are formulated, which facilitate more effective interference mitigation with reduced computational complexity compared to the centralized approach. This approach ultimately results in a significantly augmented SE when contrasted with the distributed architecture. The simulation results unequivocally demonstrate that within the cluster-based framework, the optimal SE for the network is attained when utilizing four clusters in conjunction with the MMSE precoding technique, leading to a notable reduction in computational complexity exceeding 85%. Importantly, this approach surpasses the SE performance of the centralized structure.
Pre-trained Vision-Language Models (VLMs), such as CLIP, have shown enhanced performance across a range of tasks that involve the integration of visual and linguistic modalities. When CLIP is used for depth estimation tasks, the patches, divided from the input images, can be combined with a series of semantic descriptions of the depth information to obtain similarity results. The coarse estimation of depth is then achieved by weighting and summing the depth values, called depth bins, corresponding to the predefined semantic descriptions. The zero-shot approach circumvents the computational and time-intensive nature of traditional fully-supervised depth estimation methods. However, this method, utilizing fixed depth bins, may not effectively generalize as images from different scenes may exhibit distinct depth distributions. To address this challenge, we propose a few-shot-based method which learns to adapt the VLMs for monocular depth estimation to balance training costs and generalization capabilities. Specifically, it assigns different depth bins for different scenes, which can be selected by the model during inference. Additionally, we incorporate learnable prompts to preprocess the input text to convert the easily human-understood text into easily model-understood vectors and further enhance the performance. With only one image per scene for training, our extensive experiment results on the NYU V2 and KITTI dataset demonstrate that our method outperforms the previous state-of-the-art method by up to 10.6\% in terms of MARE.
Clinical texts, such as admission notes, discharge summaries, and progress notes, contain rich and valuable information that can be used for various clinical outcome prediction tasks. However, applying large language models, such as BERT-based models, to clinical texts poses two major challenges: the limitation of input length and the diversity of data sources. This paper proposes a novel method to preserve the knowledge of long clinical texts using aggregated ensembles of large language models. Unlike previous studies which use model ensembling or text aggregation methods separately, we combine ensemble learning with text aggregation and train multiple large language models on two clinical outcome tasks: mortality prediction and length of stay prediction. We show that our method can achieve better results than baselines, ensembling, and aggregation individually, and can improve the performance of large language models while handling long inputs and diverse datasets. We conduct extensive experiments on the admission notes from the MIMIC-III clinical database by combining multiple unstructured and high-dimensional datasets, demonstrating our method's effectiveness and superiority over existing approaches. We also provide a comprehensive analysis and discussion of our results, highlighting our method's applications and limitations for future research in the domain of clinical healthcare. The results and analysis of this study is supportive of our method assisting in clinical healthcare systems by enabling clinical decision-making with robust performance overcoming the challenges of long text inputs and varied datasets.
During the development of large language models (LLMs), the scale and quality of the pre-training data play a crucial role in shaping LLMs' capabilities. To accelerate the research of LLMs, several large-scale datasets, such as C4 [1], Pile [2], RefinedWeb [3] and WanJuan [4], have been released to the public. However, most of the released corpus focus mainly on English, and there is still lack of complete tool-chain for extracting clean texts from web data. Furthermore, fine-grained information of the corpus, e.g. the quality of each text, is missing. To address these challenges, we propose in this paper a new complete tool-chain EvalWeb to extract Chinese clean texts from noisy web data. First, similar to previous work, manually crafted rules are employed to discard explicit noisy texts from the raw crawled web contents. Second, a well-designed evaluation model is leveraged to assess the remaining relatively clean data, and each text is assigned a specific quality score. Finally, we can easily utilize an appropriate threshold to select the high-quality pre-training data for Chinese. Using our proposed approach, we release the largest and latest large-scale high-quality Chinese web text ChineseWebText, which consists of 1.42 TB and each text is associated with a quality score, facilitating the LLM researchers to choose the data according to the desired quality thresholds. We also release a much cleaner subset of 600 GB Chinese data with the quality exceeding 90%.
We consider a relay system empowered by an unmanned aerial vehicle (UAV) that facilitates downlink information delivery while adhering to finite blocklength requirements. The setup involves a remote controller transmitting information to both a UAV and an industrial Internet of Things (IIoT) or remote device, employing the non-orthogonal multiple access (NOMA) technique in the first phase. Subsequently, the UAV decodes and forwards this information to the remote device in the second phase. Our primary objective is to minimize the decoding error probability (DEP) at the remote device, which is influenced by the DEP at the UAV. To achieve this goal, we optimize the blocklength, transmission power, and location of the UAV. However, the underlying problem is highly non-convex and generally intractable to be solved directly. To overcome this challenge, we adopt an alternative optimization (AO) approach and decompose the original problem into three sub-problems. This approach leads to a sub-optimal solution, which effectively mitigates the non-convexity issue. In our simulations, we compare the performance of our proposed algorithm with baseline schemes. The results reveal that the proposed framework outperforms the baseline schemes, demonstrating its superiority in achieving lower DEP at the remote device. Furthermore, the simulation results illustrate the rapid convergence of our proposed algorithm, indicating its efficiency and effectiveness in solving the optimization problem.
Diffuse Large B-cell Lymphoma (DLBCL) is a lymphatic cancer involving one or more lymph nodes and extranodal sites. Its diagnostic and follow-up rely on Positron Emission Tomography (PET) and Computed Tomography (CT). After diagnosis, the number of nonresponding patients to standard front-line therapy remains significant (30-40%). This work aims to develop a computer-aided approach to identify high-risk patients requiring adapted treatment by efficiently exploiting all the information available for each patient, including both clinical and image data. We propose a method based on recent graph neural networks that combine imaging information from multiple lesions, and a cross-attention module to integrate different data modalities efficiently. The model is trained and evaluated on a private prospective multicentric dataset of 583 patients. Experimental results show that our proposed method outperforms classical supervised methods based on either clinical, imaging or both clinical and imaging data for the 2-year progression-free survival (PFS) classification accuracy.
Detecting humans from airborne visual and thermal imagery is a fundamental challenge for Wilderness Search-and-Rescue (WiSAR) teams, who must perform this function accurately in the face of immense pressure. The ability to fuse these two sensor modalities can potentially reduce the cognitive load on human operators and/or improve the effectiveness of computer vision object detection models. However, the fusion task is particularly challenging in the context of WiSAR due to hardware limitations and extreme environmental factors. This work presents Misaligned Image Synthesis and Fusion using Information from Thermal and Visual (MISFIT-V), a novel two-pronged unsupervised deep learning approach that utilizes a Generative Adversarial Network (GAN) and a cross-attention mechanism to capture the most relevant features from each modality. Experimental results show MISFIT-V offers enhanced robustness against misalignment and poor lighting/thermal environmental conditions compared to existing visual-thermal image fusion methods.
This letter proposes a novel anti-interference technique, semantic interference cancellation (SemantIC), for enhancing information quality towards the sixth-generation (6G) wireless networks. SemantIC only requires the receiver to concatenate the channel decoder with a semantic auto-encoder. This constructs a turbo loop which iteratively and alternately eliminates noise in the signal domain and the semantic domain. From the viewpoint of network information theory, the neural network of the semantic auto-encoder stores side information by training, and provides side information in iterative decoding, as an implementation of the Wyner-Ziv theorem. Simulation results verify the performance improvement by SemantIC without extra channel resource cost.
Emotion recognition in conversations (ERC), the task of recognizing the emotion of each utterance in a conversation, is crucial for building empathetic machines. Existing studies focus mainly on capturing context- and speaker-sensitive dependencies on the textual modality but ignore the significance of multimodal information. Different from emotion recognition in textual conversations, capturing intra- and inter-modal interactions between utterances, learning weights between different modalities, and enhancing modal representations play important roles in multimodal ERC. In this paper, we propose a transformer-based model with self-distillation (SDT) for the task. The transformer-based model captures intra- and inter-modal interactions by utilizing intra- and inter-modal transformers, and learns weights between modalities dynamically by designing a hierarchical gated fusion strategy. Furthermore, to learn more expressive modal representations, we treat soft labels of the proposed model as extra training supervision. Specifically, we introduce self-distillation to transfer knowledge of hard and soft labels from the proposed model to each modality. Experiments on IEMOCAP and MELD datasets demonstrate that SDT outperforms previous state-of-the-art baselines.
Space-based gravitational wave detection is one of the most anticipated gravitational wave (GW) detection projects in the next decade, which will detect abundant compact binary systems. However, the precise prediction of space GW waveforms remains unexplored. To solve the data processing difficulty in the increasing waveform complexity caused by detectors' response and second-generation time-delay interferometry (TDI 2.0), an interpretable pre-trained large model named CBS-GPT (Compact Binary Systems Waveform Generation with Generative Pre-trained Transformer) is proposed. For compact binary system waveforms, three models were trained to predict the waveforms of massive black hole binary (MBHB), extreme mass-ratio inspirals (EMRIs), and galactic binary (GB), achieving prediction accuracies of 98%, 91%, and 99%, respectively. The CBS-GPT model exhibits notable interpretability, with its hidden parameters effectively capturing the intricate information of waveforms, even with complex instrument response and a wide parameter range. Our research demonstrates the potential of large pre-trained models in gravitational wave data processing, opening up new opportunities for future tasks such as gap completion, GW signal detection, and signal noise reduction.