In this paper, we propose a highly parameter-efficient approach to scaling pre-trained language models (PLMs) to a deeper model depth. Unlike prior work that shares all parameters or uses extra blocks, we design a more capable parameter-sharing architecture based on matrix product operator (MPO). MPO decomposition can reorganize and factorize the information of a parameter matrix into two parts: the major part that contains the major information (central tensor) and the supplementary part that only has a small proportion of parameters (auxiliary tensors). Based on such a decomposition, our architecture shares the central tensor across all layers for reducing the model size and meanwhile keeps layer-specific auxiliary tensors (also using adapters) for enhancing the adaptation flexibility. To improve the model training, we further propose a stable initialization algorithm tailored for the MPO-based architecture. Extensive experiments have demonstrated the effectiveness of our proposed model in reducing the model size and achieving highly competitive performance.

With the rising emergence of decentralized and opportunistic approaches to machine learning, end devices are increasingly tasked with training deep learning models on-devices using crowd-sourced data that they collect themselves. These approaches are desirable from a resource consumption perspective and also from a privacy preservation perspective. When the devices benefit directly from the trained models, the incentives are implicit - contributing devices' resources are incentivized by the availability of the higher-accuracy model that results from collaboration. However, explicit incentive mechanisms must be provided when end-user devices are asked to contribute their resources (e.g., computation, communication, and data) to a task performed primarily for the benefit of others, e.g., training a model for a task that a neighbor device needs but the device owner is uninterested in. In this project, we propose a novel blockchain-based incentive mechanism for completely decentralized and opportunistic learning architectures. We leverage a smart contract not only for providing explicit incentives to end devices to participate in decentralized learning but also to create a fully decentralized mechanism to inspect and reflect on the behavior of the learning architecture.

Accurate estimation of the relative pose between an object and a robot hand is critical for many manipulation tasks. However, most of the existing object-in-hand pose datasets use two-finger grippers and also assume that the object remains fixed in the hand without any relative movements, which is not representative of real-world scenarios. To address this issue, a 6D object-in-hand pose dataset is proposed using a teleoperation method with an anthropomorphic Shadow Dexterous hand. Our dataset comprises RGB-D images, proprioception and tactile data, covering diverse grasping poses, finger contact states, and object occlusions. To overcome the significant hand occlusion and limited tactile sensor contact in real-world scenarios, we propose PoseFusion, a hybrid multi-modal fusion approach that integrates the information from visual and tactile perception channels. PoseFusion generates three candidate object poses from three estimators (tactile only, visual only, and visuo-tactile fusion), which are then filtered by a SelectLSTM network to select the optimal pose, avoiding inferior fusion poses resulting from modality collapse. Extensive experiments demonstrate the robustness and advantages of our framework. All data and codes are available on the project website: https://elevenjiang1.github.io/ObjectInHand-Dataset/

Unmanned Aerial Vehicles (UAVs) have become increasingly popular in recent years due to their versatility and affordability. This article provides an overview of the history and development of UAVs, as well as their current and potential applications in various fields. In particular, the article highlights the use of UAVs in aerial photography and videography, surveying and mapping, agriculture and forestry, infrastructure inspection and maintenance, search and rescue operations, disaster management and humanitarian aid, and military applications such as reconnaissance, surveillance, and combat. The article also explores potential advancements in UAV technology and new applications that could emerge in the future, as well as concerns about the impact of UAVs on society, such as privacy, safety, security, job displacement, and environmental impact. Overall, the article aims to provide a comprehensive overview of the current state and future potential of UAV technology, and the benefits and challenges associated with its use in various industries and fields.

News media is one of the most effective mechanisms for spreading information internationally, and many events from different areas are internationally relevant. However, news coverage for some news events is limited to a specific geographical region because of information spreading barriers, which can be political, geographical, economic, cultural, or linguistic. In this paper, we propose an approach to barrier classification where we infer the semantics of news articles through Wikipedia concepts. To that end, we collected news articles and annotated them for different kinds of barriers using the metadata of news publishers. Then, we utilize the Wikipedia concepts along with the body text of news articles as features to infer the news-spreading barriers. We compare our approach to the classical text classification methods, deep learning, and transformer-based methods. The results show that the proposed approach using Wikipedia concepts based semantic knowledge offers better performance than the usual for classifying the news-spreading barriers.

Artificial intelligence (AI) has received significant attention in recent years, primarily due to breakthroughs in game playing, computer vision, and natural language processing that captured the imagination of the scientific community and the public at large. Many businesses, industries, and academic disciplines are now contemplating the application of AI to their own challenges. The federal government in the US and other countries have also invested significantly in advancing AI research and created funding initiatives and programs to promote greater collaboration across multiple communities. Some of the investment examples in the US include the establishment of the National AI Initiative Office, the launch of the National AI Research Resource Task Force, and more recently, the establishment of the National AI Advisory Committee. In 2021 INFORMS and ACM SIGAI joined together with the Computing Community Consortium (CCC) to organize a series of three workshops. The objective for this workshop series is to explore ways to exploit the synergies of the AI and Operations Research (OR) communities to transform decision making.

Queries with similar information needs tend to have similar document clicks, especially in biomedical literature search engines where queries are generally short and top documents account for most of the total clicks. Motivated by this, we present a novel architecture for biomedical literature search, namely Log-Augmented DEnse Retrieval (LADER), which is a simple plug-in module that augments a dense retriever with the click logs retrieved from similar training queries. Specifically, LADER finds both similar documents and queries to the given query by a dense retriever. Then, LADER scores relevant (clicked) documents of similar queries weighted by their similarity to the input query. The final document scores by LADER are the average of (1) the document similarity scores from the dense retriever and (2) the aggregated document scores from the click logs of similar queries. Despite its simplicity, LADER achieves new state-of-the-art (SOTA) performance on TripClick, a recently released benchmark for biomedical literature retrieval. On the frequent (HEAD) queries, LADER largely outperforms the best retrieval model by 39% relative NDCG@10 (0.338 v.s. 0.243). LADER also achieves better performance on the less frequent (TORSO) queries with 11% relative NDCG@10 improvement over the previous SOTA (0.303 v.s. 0.272). On the rare (TAIL) queries where similar queries are scarce, LADER still compares favorably to the previous SOTA method (NDCG@10: 0.310 v.s. 0.295). On all queries, LADER can improve the performance of a dense retriever by 24%-37% relative NDCG@10 while not requiring additional training, and further performance improvement is expected from more logs. Our regression analysis has shown that queries that are more frequent, have higher entropy of query similarity and lower entropy of document similarity, tend to benefit more from log augmentation.

The most deadly and life-threatening disease in the world is lung cancer. Though early diagnosis and accurate treatment are necessary for lowering the lung cancer mortality rate. A computerized tomography (CT) scan-based image is one of the most effective imaging techniques for lung cancer detection using deep learning models. In this article, we proposed a deep learning model-based Convolutional Neural Network (CNN) framework for the early detection of lung cancer using CT scan images. We also have analyzed other models for instance Inception V3, Xception, and ResNet-50 models to compare with our proposed model. We compared our models with each other considering the metrics of accuracy, Area Under Curve (AUC), recall, and loss. After evaluating the model's performance, we observed that CNN outperformed other models and has been shown to be promising compared to traditional methods. It achieved an accuracy of 92%, AUC of 98.21%, recall of 91.72%, and loss of 0.328.

Startups are key to solving today's biggest challenges and a huge driver of innovation -- and artificial intelligence is one of their sharpest tools. Virtual assistants, customized content, traffic apps, spell check, mobile check deposit and live captioning constitute just a small fraction of the everyday solutions using AI -- and many of these technologies were first developed by startups. AI learns from those who build it, so it is critical to have people of all backgrounds helping shape the technology to ensure its effectiveness, reduce bias and create better solutions for everyone. As Director of Product Inclusion and Equity at Google, I love to see Black founders tap into the power of our Google AI tech to help their communities and transform the way our products work and operate. In honor of Black History Month in the U.S., I asked four Google for Startups Black Founders Fund recipients from around the world and across different industries how they're using Google AI technology to address societal challenges.

As part of that job, he's planned a round-the-world goodwill tour to talk with politicians and people using OpenAI's technology. The month-long campaign -- which will take him to Canada, Brazil, Nigeria, Europe, Singapore, Japan, Indonesia and Australia, among other stops -- comes as debate over AI's impact on the world is heating up. The Italian government temporarily banned OpenAI in March, citing concerns about privacy and data collection.