Despite large successes of recent language models on diverse tasks, they suffer from severe performance degeneration in low-resource settings with limited training data available. Many existing works tackle this problem by generating synthetic data from the training data and then training models on them, recently using Large Language Models (LLMs). However, in low-resource settings, the amount of seed data samples to use for data augmentation is very small, which makes generated samples suboptimal and less diverse. To tackle this challenge, we propose a novel method that augments training data by incorporating a wealth of examples from other datasets, along with the given training data. Specifically, we first retrieve the relevant instances from other datasets, such as their input-output pairs or contexts, based on their similarities with the given seed data, and then prompt LLMs to generate new samples with the contextual information within and across the original and retrieved samples. This approach can ensure that the generated data is not only relevant but also more diverse than what could be achieved using the limited seed data alone. We validate our proposed Retrieval-Augmented Data Augmentation (RADA) framework on multiple datasets under low-resource settings of training and test-time data augmentation scenarios, on which it outperforms existing LLM-powered data augmentation baselines.

For a long time, Humanoid Robots have been gaining popularity in India. Even though India is still catching up to other countries in terms of artificial intelligence and robotics, Indian companies and the government are working hard to incorporate new-age technology. Humanoid Robots are often built for a specific purpose like healthcare, education, and Humanoid Robots based on applications. According to IFR data, robot sales in India grew by 27% to a record high of 2,627 units, nearly identical to Thailand. According to another poll, India is ranked third in the world for robotic automation implementation.

Adversarial training is a useful approach to promote the learning of transferable representations across the source and target domains, which has been widely applied for domain adaptation (DA) tasks based on deep neural networks. Until very recently, existing adversarial domain adaptation (ADA) methods ignore the useful information from the label space, which is an important factor accountable for the complicated data distributions associated with different semantic classes. Especially, the inter-class semantic relationships have been rarely considered and discussed in the current work of transfer learning. In this paper, we propose a novel relationship-aware adversarial domain adaptation (RADA) algorithm, which first utilizes a single multi-class domain discriminator to enforce the learning of inter-class dependency structure during domain-adversarial training and then aligns this structure with the inter-class dependencies that are characterized from training the label predictor on the source domain. Specifically, we impose a regularization term to penalize the structure discrepancy between the inter-class dependencies respectively estimated from domain discriminator and label predictor. Through this alignment, our proposed method makes the ADA aware of class relationships. Empirical studies show that the incorporation of class relationships significantly improves the performance on benchmark datasets.

But they did not imagine one thing: that the first places where humans and humanoids interacted would be airports. Robots now do things like scan boarding passes and provide duty free shopping advice. For many people, this will be the very first chance to interact in an everyday context with robots designed to mimic human behavior. Many of us have cleaning robots at home, of course. They are able to roam around, avoiding furniture and any other obstacle -- and that's kind of like one of the robots you'll find at Seoul Incheon airport, one of the busiest in the world.

You have heard it right. Recently this July, Vistara has introduced India's first airport robot named RADA. The robot is designed for the customer assistance and Indra Gandhi international airport is the first one in India to have its airport robot, at its signature lounge in terminal 3 by Vistara. RADA is all set to assist passengers for their flight-related queries. Also, it offers games, videos and music options through its user-friendly interface. RADA is the innovation of Mr. Ravinder Pal Singh who is Vistara's chief information and innovation officer.