The increased prevalence of online meetings has significantly enhanced the practicality of a model that can automatically generate the summary of a given meeting. This paper introduces a novel and effective approach to automate the generation of meeting summaries. Current approaches to this problem generate general and basic summaries, considering the meeting simply as a long dialogue. However, our novel algorithms can generate abstractive meeting summaries that are driven by the action items contained in the meeting transcript. This is done by recursively generating summaries and employing our action-item extraction algorithm for each section of the meeting in parallel. All of these sectional summaries are then combined and summarized together to create a coherent and action-item-driven summary. In addition, this paper introduces three novel methods for dividing up long transcripts into topic-based sections to improve the time efficiency of our algorithm, as well as to resolve the issue of large language models (LLMs) forgetting long-term dependencies. Our pipeline achieved a BERTScore of 64.98 across the AMI corpus, which is an approximately 4.98% increase from the current state-of-the-art result produced by a fine-tuned BART (Bidirectional and Auto-Regressive Transformers) model.
Online display advertising platforms service numerous advertisers by providing real-time bidding (RTB) for the scale of billions of ad requests every day. The bidding strategy handles ad requests cross multiple channels to maximize the number of clicks under the set financial constraints, i.e., total budget and cost-per-click (CPC), etc. Different from existing works mainly focusing on single channel bidding, we explicitly consider cross-channel constrained bidding with budget allocation. Specifically, we propose a hierarchical offline deep reinforcement learning (DRL) framework called ``HiBid'', consisted of a high-level planner equipped with auxiliary loss for non-competitive budget allocation, and a data augmentation enhanced low-level executor for adaptive bidding strategy in response to allocated budgets. Additionally, a CPC-guided action selection mechanism is introduced to satisfy the cross-channel CPC constraint. Through extensive experiments on both the large-scale log data and online A/B testing, we confirm that HiBid outperforms six baselines in terms of the number of clicks, CPC satisfactory ratio, and return-on-investment (ROI). We also deploy HiBid on Meituan advertising platform to already service tens of thousands of advertisers every day.
Occupancy prediction plays a pivotal role in the realm of autonomous driving. Previous methods typically constructs a dense 3D volume, neglecting the inherent sparsity of the scene, which results in a high computational cost. Furthermore, these methods are limited to semantic occupancy and fail to differentiate between distinct instances. To exploit the sparsity property and ensure instance-awareness, we introduce a novel fully sparse panoptic occupancy network, termed SparseOcc. SparseOcc initially reconstructs a sparse 3D representation from visual inputs. Subsequently, it employs sparse instance queries to predict each object instance from the sparse 3D representation. These instance queries interact with 2D features via mask-guided sparse sampling, thereby circumventing the need for costly dense features or global attention. Additionally, we have established the first-ever vision-centric panoptic occupancy benchmark. SparseOcc demonstrates its efficacy on the Occ3D-nus dataset by achieving a mean Intersection over Union (mIoU) of 26.0, while maintaining a real-time inference speed of 25.4 FPS. By incorporating temporal modeling from the preceding 8 frames, SparseOcc further improves its performance, achieving 30.9 mIoU without whistles and bells. Code will be made available.
Large language models (LLMs) have achieved huge success for their general knowledge and ability to solve a wide spectrum of tasks in natural language processing (NLP). Due to their impressive abilities, LLMs have shed light on potential inter-discipline applications to foster scientific discoveries of a specific domain by using artificial intelligence (AI for science, AI4S). In the meantime, utilizing NLP techniques in geoscience research and practice is wide and convoluted, contributing from knowledge extraction and document classification to question answering and knowledge discovery. In this work, we take the initial step to leverage LLM for science, through a rather straightforward approach. We try to specialize an LLM into geoscience, by further pre-training the model with a vast amount of texts in geoscience, as well as supervised fine-tuning (SFT) the resulting model with our custom collected instruction tuning dataset. These efforts result in a model GeoGalactica consisting of 30 billion parameters. To our best knowledge, it is the largest language model for the geoscience domain. More specifically, GeoGalactica is from further pre-training of Galactica. We train GeoGalactica over a geoscience-related text corpus containing 65 billion tokens curated from extensive data sources in the big science project Deep-time Digital Earth (DDE), preserving as the largest geoscience-specific text corpus. Then we fine-tune the model with 1 million pairs of instruction-tuning data consisting of questions that demand professional geoscience knowledge to answer. In this technical report, we will illustrate in detail all aspects of GeoGalactica, including data collection, data cleaning, base model selection, pre-training, SFT, and evaluation. We open-source our data curation tools and the checkpoints of GeoGalactica during the first 3/4 of pre-training.
The Coded Aperture Snapshot Spectral Compressive Imaging (CASSI) system modulates three-dimensional hyperspectral images into two-dimensional compressed images in a single exposure. Subsequently, three-dimensional hyperspectral images (HSI) can be reconstructed from the two-dimensional compressed measurements using reconstruction algorithms. Among these methods, deep unfolding techniques have demonstrated excellent performance, with RDLUF-MixS^2 achieving the best reconstruction results. However, RDLUF-MixS^2 requires extensive training time, taking approximately 14 days to train RDLUF-MixS^2-9stg on a single RTX 3090 GPU, making it computationally expensive. Furthermore, RDLUF-MixS^2 performs poorly on real data, resulting in significant artifacts in the reconstructed images. In this study, we introduce the Dense-spatial Spectral-attention Transformer (DST) into the Proximal Gradient Descent Unfolding Framework (PGDUF), creating a novel approach called Proximal Gradient Descent Unfolding Dense-spatial Spectral-attention Transformer (PGDUDST). Compared to RDLUF-MixS^2, PGDUDST not only surpasses the network reconstruction performance limit of RDLUF-MixS^2 but also achieves faster convergence. PGDUDST requires only 58% of the training time of RDLUF-MixS^2-9stg to achieve comparable reconstruction results. Additionally, PGDUDST significantly alleviates the artifact issues caused by RDLUF-MixS^2 in real experimental data, demonstrating superior performance and producing clearer reconstructed images.
Machine learning and data mining techniques are utiized for enhancement of the security of any network. Researchers used machine learning for pattern detection, anomaly detection, dynamic policy setting, etc. The methods allow the program to learn from data and make decisions without human intervention, consuming a huge training period and computation power. This paper discusses a novel technique to predict an upcoming attack in a network based on several data parameters. The dataset is continuous in real-time implementation. The proposed model comprises dataset pre-processing, and training, followed by the testing phase. Based on the results of the testing phase, the best model is selected using which, event class which may lead to an attack is extracted. The event statistics are used for attack
Cross-modal medical image-report retrieval task plays a significant role in clinical diagnosis and various medical generative tasks. Eliminating heterogeneity between different modalities to enhance semantic consistency is the key challenge of this task. The current Vision-Language Pretraining (VLP) models, with cross-modal contrastive learning and masked reconstruction as joint training tasks, can effectively enhance the performance of cross-modal retrieval. This framework typically employs dual-stream inputs, using unmasked data for cross-modal contrastive learning and masked data for reconstruction. However, due to task competition and information interference caused by significant differences between the inputs of the two proxy tasks, the effectiveness of representation learning for intra-modal and cross-modal features is limited. In this paper, we propose an efficient VLP framework named Masked Contrastive and Reconstruction (MCR), which takes masked data as the sole input for both tasks. This enhances task connections, reducing information interference and competition between them, while also substantially decreasing the required GPU memory and training time. Moreover, we introduce a new modality alignment strategy named Mapping before Aggregation (MbA). Unlike previous methods, MbA maps different modalities to a common feature space before conducting local feature aggregation, thereby reducing the loss of fine-grained semantic information necessary for improved modality alignment. Additionally, due to using only masked input, our method significantly reduces the gpu memory and time required for training. Qualitative and quantitative experiments conducted on the MIMIC-CXR dataset validate the effectiveness of our approach, demonstrating state-of-the-art performance in medical cross-modal retrieval tasks.
Wind turbines are subjected to continuous rotational stresses and unusual external forces such as storms, lightning, strikes by flying objects, etc., which may cause defects in turbine blades. Hence, it requires a periodical inspection to ensure proper functionality and avoid catastrophic failure. The task of inspection is challenging due to the remote location and inconvenient reachability by human inspection. Researchers used images with cropped defects from the wind turbine in the literature. They neglected possible background biases, which may hinder real-time and autonomous defect detection using aerial vehicles such as drones or others. To overcome such challenges, in this paper, we experiment with defect detection accuracy by having the defects with the background using a two-step deep-learning methodology. In the first step, we develop virtual models of wind turbines to synthesize the near-reality images for four types of common defects - cracks, leading edge erosion, bending, and light striking damage. The Unity perception package is used to generate wind turbine blade defects images with variations in background, randomness, camera angle, and light effects. In the second step, a customized U-Net architecture is trained to classify and segment the defect in turbine blades. The outcomes of U-Net architecture have been thoroughly tested and compared with 5-fold validation datasets. The proposed methodology provides reasonable defect detection accuracy, making it suitable for autonomous and remote inspection through aerial vehicles.
This study delves into the radiation pattern synthesis of reconfigurable intelligent surfaces (RIS) / reflection metasurfaces. Through superimposing multiple single-reflection profiles, which comprise the amplitude and/or phase settings of all constituent elements, a single incident wave can be effectively reflected in multiple asymmetric directions. However, some mismatch and interference between adjacent reflection beams may be caused by this superposition as well. Additionally, it is constrained by the inherent limitation that achieving linear and continuous amplitude adjustments and phase shifts in real-world designs is challenging. Consequently, the reconfigurable amplitude and phase must be approximated to discrete values, necessitating the arrangement of reflection profile before and after optimization based on integer. Therefore, in this paper, we adapt the traditional particle swarm optimization (PSO) algorithm to discretized integer-based PSO by proposing the concepts of 'discard rate' and 'knowledge.' With the enhancement of the integer-based programming, the multiple asymmetric reflection pattern can be synthesized with suppressed sidelobe levels within limited iterations and time cost.
Existing LiDAR-inertial-visual odometry and mapping (LIV-SLAM) systems mainly utilize the LiDAR-inertial odometry (LIO) module for structure reconstruction and the visual-inertial odometry (VIO) module for color rendering. However, the accuracy of VIO is often compromised by photometric changes, weak textures and motion blur, unlike the more robust LIO. This paper introduces SR-LIVO, an advanced and novel LIV-SLAM system employing sweep reconstruction to align reconstructed sweeps with image timestamps. This allows the LIO module to accurately determine states at all imaging moments, enhancing pose accuracy and processing efficiency. Experimental results on two public datasets demonstrate that: 1) our SRLIVO outperforms existing state-of-the-art LIV-SLAM systems in both pose accuracy and time efficiency; 2) our LIO-based pose estimation prove more accurate than VIO-based ones in several mainstream LIV-SLAM systems (including ours). We have released our source code to contribute to the community development in this field.