Large language models (LLMs) are typically prompted to follow a single instruction per inference call. In this work, we analyze whether LLMs also hold the capability to handle multiple instructions simultaneously, denoted as Multi-Task Inference. For this purpose, we introduce the MTI Bench(Multi-Task Inference Benchmark), a comprehensive evaluation benchmark encompassing 5,000 instances across 25 tasks. Each task in the MTI Bench involves 2 to 3 sub-tasks. As expected, we first demonstrate that Multi-Task Inference reduces the total inference time by 1.46 times in average since it does not require multiple inference calls. Interestingly, contrary to the expectation that LLMs would perform better when tasks are divided, we find that state-of-the-art LLMs, such as Llama-2-Chat-70B and GPT-4, show up to 7.3% and 12.4% improved performance with Multi-Task Inference compared to Single-Task Inference on the MTI Bench. We release the MTI Bench dataset and our code at this link https://github.com/guijinSON/MTI-Bench.

Numerous sign language datasets exist, yet they typically cover only a limited selection of the thousands of signs used globally. Moreover, creating diverse sign language datasets is an expensive and challenging task due to the costs associated with gathering a varied group of signers. Motivated by these challenges, we aimed to develop a solution that addresses these limitations. In this context, we focused on textually describing body movements from skeleton keypoint sequences, leading to the creation of a new dataset. We structured this dataset around AUTSL, a comprehensive isolated Turkish sign language dataset. We also developed a baseline model, SkelCap, which can generate textual descriptions of body movements. This model processes the skeleton keypoints data as a vector, applies a fully connected layer for embedding, and utilizes a transformer neural network for sequence-to-sequence modeling. We conducted extensive evaluations of our model, including signer-agnostic and sign-agnostic assessments. The model achieved promising results, with a ROUGE-L score of 0.98 and a BLEU-4 score of 0.94 in the signer-agnostic evaluation. The dataset we have prepared, namely the AUTSL-SkelCap, will be made publicly available soon.

Knowledge graphs (KGs), which store an extensive number of relational Knowledge Graphs (KGs), e.g., the widely used YAGO [23], Freebase facts (h,,), serve various applications. While [3], DBpedia [2], WordNet [19], have been serving multiple many downstream tasks highly rely on the expressive modeling and downstream applications such as information retrieval [30], recommender predictive embedding of KGs, most of the current KG representation systems [36, 38], natural language processing [32, 34], learning methods, where each entity is embedded as a vector in the multimedia network analysis [31, 35], question answering [14, 16], Euclidean space and each relation is embedded as a transformation, fact checking [15, 17]. To utilize the extensive amount of knowledge follow an entity ranking protocol. On one hand, such an embedding in the KG, many works have studied Knowledge Graph Embedding design cannot capture many-to-many relations. On the other hand, (KGE), which learns low-dimensional representations of entities in many retrieval cases, the users wish to get an exact set of answers and relations of them [10, 21, 26, 27, 29]. Starting from TransE [4], without any ranking, especially when the results are expected to be a group of translation-based methods TransH [28], TransR [13], precise, e.g., which genes cause an illness. Such scenarios are commonly TransD [9], TorusE [6] model the relation as translations between referred to as "set retrieval". This work presents a pioneering entities in the embedding space. However, the translation-based study on the KG set retrieval problem.

Recent studies have highlighted the effectiveness of tensor decomposition methods in the Temporal Knowledge Graphs Embedding (TKGE) task. However, we found that inherent heterogeneity among factor tensors in tensor decomposition significantly hinders the tensor fusion process and further limits the performance of link prediction. To overcome this limitation, we introduce a novel method that maps factor tensors onto a unified smooth Lie group manifold to make the distribution of factor tensors approximating homogeneous in tensor decomposition. We provide the theoretical proof of our motivation that homogeneous tensors are more effective than heterogeneous tensors in tensor fusion and approximating the target for tensor decomposition based TKGE methods. The proposed method can be directly integrated into existing tensor decomposition based TKGE methods without introducing extra parameters. Extensive experiments demonstrate the effectiveness of our method in mitigating the heterogeneity and in enhancing the tensor decomposition based TKGE models.

AI chip startup Cerebras Systems has deployed one of its CS-2 systems at a well-funded startup that uses natural language processing to analyze massive amounts of biomedical data. As announced on Monday, nference plans to use this CS-2 to train large transformer models that are designed to process information from piles of unstructured medical data to provide fresh insights to doctors and improve patient recovery and treatment. The CS-2 is powered by Cerebras' second-generation, Wafer-Scale Engine processor, so-called because the chip is wafer-size. Cerebras said this deployment marks another significant customer win in the health care and life sciences space after installing similar systems at pharmaceutical giants GlaxoSmithKline and AstraZeneca as well as the US Department of Energy's Argonne National Laboratory for COVID-19-related research. Andrew Feldman, CEO of Cerebras, told The Register this installation at Massachusetts-based nference is another testament to Cerebras' belief that its wafer-sized AI chips are better suited than traditional chips like Nvidia's GPUs for analyzing large amounts of data as fast as possible, which is increasingly important in areas like health care and the life sciences.

It still remains to be seen whether the sci-fi genre is correct and artificial intelligence will one day rise up against the human race, but in the meantime, AI just might save your life. An algorithm developed by the Mayo Clinic can significantly increase the number of cases of low ejection fraction caught in its earliest stages, when it's still most treatable, according to a study published this month in Nature Medicine. The condition, in which the heart is unable to pump enough blood from its chamber with each contraction, is associated with cardiomyopathy and heart failure and is often symptomless in its early stages. Traditionally, the only way to diagnose low ejection fraction is with the use of an echocardiogram, a time-consuming and expensive cardiac ultrasound. The Mayo Clinic's AI algorithm, however, can screen for low ejection fraction in a standard 12-lead electrocardiogram (EKG) reading, which is a much faster and more readily available tool. In the study, more than 22,600 patients received an EKG as part of their usual primary care checkups, then were randomly assigned to have their results analyzed by the AI or by a physician as usual.

Looking to broaden its use of artificial intelligence to help lock down its R&D work, Johnson & Johnson's biotech unit Janssen has penned a new deal with AI specialist nference. The multiyear deal, financial details of which were not disclosed, will see the Big Pharma "leverage the nference artificial intelligence (AI) platform to create a unified data science-powered connective fabric across the Janssen R&D organization." In practical terms, this will see nference uncovering and prioritizing new targets and disease subsets as well as boosting effectiveness by matching the right patients to the right drugs. Further, nference will encourage efficiencies by identifying the optimal sites and investigators for pushing on with clinical trials across hospitals. To do this, nference said it has developed a "holistic data science kernel" that will synthesize some of the Janssen R&D databases with "real-time insights gleaned by the core nference AI platform from the world's public biomedical knowledge bases."

Central to the new company will be a mix of established medical expertise (from Mayo Clinic's team) and artificial intelligence (using nference's computer experts). The new company will be called Qrativ. The new organization will set-out to discover and develop treatments for diseases which have an unmet medical need. This includes a range of rare diseases affecting specific patient populations. The reason why artificial intelligence and machine learning are needed is due the complexity of biological data, especially data in relation to uncommon diseases and the different drug combinations that the disease needs to be examined against.

Leading US hospital Mayo Clinic has unveiled a new startup company that uses artificial intelligence to discover novel treatments. Launched in partnership with American tech company nference, Qrativ (pronounced'curative') combines Mayo Clinic's medical expertise and clinical data with nference's AI platform nferX. The deep learning-driven AI sifts through masses of medical literature and clinical data to uncover insights into disease and will form the basis of Qrativ's Darwin.ai These insights can then be used to guide the development of new drugs. Initially, Qrativ will focus on drug repurposing for rare diseases and highly targeted patient populations.