Survey of different Large Language Model Architectures: Trends, Benchmarks, and Challenges

Large Language Models (LLMs) represent a class of deep learning models adept at understanding natural language and generating coherent responses to various prompts or queries. These models far exceed the complexity of conventional neural networks, often encompassing dozens of neural network layers and containing billions to trillions of parameters. They are typically trained on vast datasets, utilizing architectures based on transformer blocks. Present-day LLMs are multi-functional, capable of performing a range of tasks from text generation and language translation to question answering, as well as code generation and analysis. An advanced subset of these models, known as Multimodal Large Language Models (MLLMs), extends LLM capabilities to process and interpret multiple data modalities, including images, audio, and video. This enhancement empowers MLLMs with capabilities like video editing, image comprehension, and captioning for visual content. This survey provides a comprehensive overview of the recent advancements in LLMs. We begin by tracing the evolution of LLMs and subsequently delve into the advent and nuances of MLLMs. We analyze emerging state-of-the-art MLLMs, exploring their technical features, strengths, and limitations. Additionally, we present a comparative analysis of these models and discuss their challenges, potential limitations, and prospects for future development.

MindArm: Mechanized Intelligent Non-Invasive Neuro-Driven Prosthetic Arm System

Currently, people with disability or difficulty to move their arms (referred to as "patients") have very limited technological solutions to efficiently address their physiological limitations. It is mainly due to two reasons: (1) the non-invasive solutions like mind-controlled prosthetic devices are typically very costly and require expensive maintenance; and (2) other solutions require costly invasive brain surgery, which is high risk to perform, expensive, and difficult to maintain. Therefore, current technological solutions are not accessible for all patients with different financial backgrounds. Toward this, we propose a low-cost technological solution called MindArm, a mechanized intelligent non-invasive neuro-driven prosthetic arm system. Our MindArm system employs a deep neural network (DNN) engine to translate brain signals into the intended prosthetic arm motion, thereby helping patients to perform many activities despite their physiological limitations. Here, our MindArm system utilizes widely accessible and low-cost surface electroencephalogram (EEG) electrodes coupled with an Open Brain Computer Interface and UDP networking for acquiring brain signals and transmitting them to the compute module for signal processing. In the compute module, we run a trained DNN model to interpret normalized micro-voltage of the brain signals, and then translate them into a prosthetic arm action via serial communication seamlessly. The experimental results on a fully working prototype demonstrate that, from the three defined actions, our MindArm system achieves positive success rates, i.e., 91\% for idle/stationary, 85\% for shake hand, and 84\% for pick-up cup. This demonstrates that our MindArm provides a novel approach for an alternate low-cost mind-controlled prosthetic devices for all patients.

Borrowing Treasures from Neighbors: In-Context Learning for Multimodal Learning with Missing Modalities and Data Scarcity

Multimodal machine learning with missing modalities is an increasingly relevant challenge arising in various applications such as healthcare. This paper extends the current research into missing modalities to the low-data regime, i.e., a downstream task has both missing modalities and limited sample size issues. This problem setting is particularly challenging and also practical as it is often expensive to get full-modality data and sufficient annotated training samples. We propose to use retrieval-augmented in-context learning to address these two crucial issues by unleashing the potential of a transformer's in-context learning ability. Diverging from existing methods, which primarily belong to the parametric paradigm and often require sufficient training samples, our work exploits the value of the available full-modality data, offering a novel perspective on resolving the challenge. The proposed data-dependent framework exhibits a higher degree of sample efficiency and is empirically demonstrated to enhance the classification model's performance on both full- and missing-modality data in the low-data regime across various multimodal learning tasks. When only 1% of the training data are available, our proposed method demonstrates an average improvement of 6.1% over a recent strong baseline across various datasets and missing states. Notably, our method also reduces the performance gap between full-modality and missing-modality data compared with the baseline.

MedAide: Leveraging Large Language Models for On-Premise Medical Assistance on Edge Devices

Large language models (LLMs) are revolutionizing various domains with their remarkable natural language processing (NLP) abilities. However, deploying LLMs in resource-constrained edge computing and embedded systems presents significant challenges. Another challenge lies in delivering medical assistance in remote areas with limited healthcare facilities and infrastructure. To address this, we introduce MedAide, an on-premise healthcare chatbot. It leverages tiny-LLMs integrated with LangChain, providing efficient edge-based preliminary medical diagnostics and support. MedAide employs model optimizations for minimal memory footprint and latency on embedded edge devices without server infrastructure. The training process is optimized using low-rank adaptation (LoRA). Additionally, the model is trained on diverse medical datasets, employing reinforcement learning from human feedback (RLHF) to enhance its domain-specific capabilities. The system is implemented on various consumer GPUs and Nvidia Jetson development board. MedAide achieves 77\% accuracy in medical consultations and scores 56 in USMLE benchmark, enabling an energy-efficient healthcare assistance platform that alleviates privacy concerns due to edge-based deployment, thereby empowering the community.

DRL-Based Dynamic Channel Access and SCLAR Maximization for Networks Under Jamming

This paper investigates a deep reinforcement learning (DRL)-based approach for managing channel access in wireless networks. Specifically, we consider a scenario in which an intelligent user device (iUD) shares a time-varying uplink wireless channel with several fixed transmission schedule user devices (fUDs) and an unknown-schedule malicious jammer. The iUD aims to harmoniously coexist with the fUDs, avoid the jammer, and adaptively learn an optimal channel access strategy in the face of dynamic channel conditions, to maximize the network's sum cross-layer achievable rate (SCLAR). Through extensive simulations, we demonstrate that when we appropriately define the state space, action space, and rewards within the DRL framework, the iUD can effectively coexist with other UDs and optimize the network's SCLAR. We show that the proposed algorithm outperforms the tabular Q-learning and a fully connected deep neural network approach.

HgbNet: predicting hemoglobin level/anemia degree from EHR data

Anemia is a prevalent medical condition that typically requires invasive blood tests for diagnosis and monitoring. Electronic health records (EHRs) have emerged as valuable data sources for numerous medical studies. EHR-based hemoglobin level/anemia degree prediction is non-invasive and rapid but still faces some challenges due to the fact that EHR data is typically an irregular multivariate time series containing a significant number of missing values and irregular time intervals. To address these issues, we introduce HgbNet, a machine learning-based prediction model that emulates clinicians' decision-making processes for hemoglobin level/anemia degree prediction. The model incorporates a NanDense layer with a missing indicator to handle missing values and employs attention mechanisms to account for both local irregularity and global irregularity. We evaluate the proposed method using two real-world datasets across two use cases. In our first use case, we predict hemoglobin level/anemia degree at moment T+1 by utilizing records from moments prior to T+1. In our second use case, we integrate all historical records with additional selected test results at moment T+1 to predict hemoglobin level/anemia degree at the same moment, T+1. HgbNet outperforms the best baseline results across all datasets and use cases. These findings demonstrate the feasibility of estimating hemoglobin levels and anemia degree from EHR data, positioning HgbNet as an effective non-invasive anemia diagnosis solution that could potentially enhance the quality of life for millions of affected individuals worldwide. To our knowledge, HgbNet is the first machine learning model leveraging EHR data for hemoglobin level/anemia degree prediction.

Detection and Localization of Firearm Carriers in Complex Scenes for Improved Safety Measures

Detecting firearms and accurately localizing individuals carrying them in images or videos is of paramount importance in security, surveillance, and content customization. However, this task presents significant challenges in complex environments due to clutter and the diverse shapes of firearms. To address this problem, we propose a novel approach that leverages human-firearm interaction information, which provides valuable clues for localizing firearm carriers. Our approach incorporates an attention mechanism that effectively distinguishes humans and firearms from the background by focusing on relevant areas. Additionally, we introduce a saliency-driven locality-preserving constraint to learn essential features while preserving foreground information in the input image. By combining these components, our approach achieves exceptional results on a newly proposed dataset. To handle inputs of varying sizes, we pass paired human-firearm instances with attention masks as channels through a deep network for feature computation, utilizing an adaptive average pooling layer. We extensively evaluate our approach against existing methods in human-object interaction detection and achieve significant results (AP=77.8\%) compared to the baseline approach (AP=63.1\%). This demonstrates the effectiveness of leveraging attention mechanisms and saliency-driven locality preservation for accurate human-firearm interaction detection. Our findings contribute to advancing the fields of security and surveillance, enabling more efficient firearm localization and identification in diverse scenarios.

Localizing Firearm Carriers by Identifying Human-Object Pairs

Visual identification of gunmen in a crowd is a challenging problem, that requires resolving the association of a person with an object (firearm). We present a novel approach to address this problem, by defining human-object interaction (and non-interaction) bounding boxes. In a given image, human and firearms are separately detected. Each detected human is paired with each detected firearm, allowing us to create a paired bounding box that contains both object and the human. A network is trained to classify these paired-bounding-boxes into human carrying the identified firearm or not. Extensive experiments were performed to evaluate effectiveness of the algorithm, including exploiting full pose of the human, hand key-points, and their association with the firearm. The knowledge of spatially localized features is key to success of our method by using multi-size proposals with adaptive average pooling. We have also extended a previously firearm detection dataset, by adding more images and tagging in extended dataset the human-firearm pairs (including bounding boxes for firearms and gunmen). The experimental results ($AP_{hold} = 78.5$) demonstrate effectiveness of the proposed method.

Dynamic Matrix Decomposition for Action Recognition

Designing a technique for the automatic analysis of different actions in videos in order to detect the presence of interested activities is of high significance nowadays. In this paper, we explore a robust and dynamic appearance technique for the purpose of identifying different action activities. We also exploit a low-rank and structured sparse matrix decomposition (LSMD) method to better model these activities.. Our method is effective in encoding localized spatio-temporal features which enables the analysis of local motion taking place in the video. Our proposed model use adjacent frame differences as the input to the method thereby forcing it to capture the changes occurring in the video. The performance of our model is tested on a benchmark dataset in terms of detection accuracy. Results achieved with our model showed the promising capability of our model in detecting action activities.

Transfer Learning and Meta Classification Based Deep Churn Prediction System for Telecom Industry

A churn prediction system guides telecom service providers to reduce revenue loss. Development of a churn prediction system for a telecom industry is a challenging task, mainly due to size of the data, high dimensional features, and imbalanced distribution of the data. In this paper, we focus on a novel solution to the inherent problems of churn prediction, using the concept of Transfer Learning (TL) and Ensemble-based Meta-Classification. The proposed method TL-DeepE is applied in two stages. The first stage employs TL by fine tuning multiple pre-trained Deep Convolution Neural Networks (CNNs). Telecom datasets are in vector form, which is converted into 2D images because Deep CNNs have high learning capacity on images. In the second stage, predictions from these Deep CNNs are appended to the original feature vector and thus are used to build a final feature vector for the high-level Genetic Programming and AdaBoost based ensemble classifier. Thus, the experiments are conducted using various CNNs as base classifiers with the contribution of high-level GP-AdaBoost ensemble classifier, and the results achieved are as an average of the outcomes. By using 10-fold cross-validation, the performance of the proposed TL-DeepE system is compared with existing techniques, for two standard telecommunication datasets; Orange and Cell2cell. In experimental result, the prediction accuracy for Orange and Cell2cell datasets were as 75.4% and 68.2% and a score of the area under the curve as 0.83 and 0.74, respectively.