Paraphrase generation is a longstanding NLP task and achieves great success with the aid of large corpora. However, transferring a paraphrasing model to another domain encounters the problem of domain shifting especially when the data is sparse. At the same time, widely using large pre-trained language models (PLMs) faces the overfitting problem when training on scarce labeled data. To mitigate these two issues, we propose, LAPA, an effective adapter for PLMs optimized by meta-learning. LAPA has three-stage training on three types of related resources to solve this problem: 1. pre-training PLMs on unsupervised corpora, 2. inserting an adapter layer and meta-training on source domain labeled data, and 3. fine-tuning adapters on a small amount of target domain labeled data. This method enables paraphrase generation models to learn basic language knowledge first, then learn the paraphrasing task itself later, and finally adapt to the target task. Our experimental results demonstrate that LAPA achieves state-of-the-art in supervised, unsupervised, and low-resource settings on three benchmark datasets. With only 2\% of trainable parameters and 1\% labeled data of the target task, our approach can achieve a competitive performance with previous work.

We introduce Latent Action Pretraining for general Action models (LAPA), an unsupervised method for pretraining Vision-Language-Action (VLA) models without ground-truth robot action labels. Existing Vision-Language-Action models require action labels typically collected by human teleoperators during pretraining, which significantly limits possible data sources and scale. In this work, we propose a method to learn from internet-scale videos that do not have robot action labels. We first train an action quantization model leveraging VQ-VAE-based objective to learn discrete latent actions between image frames, then pretrain a latent VLA model to predict these latent actions from observations and task descriptions, and finally finetune the VLA on small-scale robot manipulation data to map from latent to robot actions. Experimental results demonstrate that our method significantly outperforms existing techniques that train robot manipulation policies from large-scale videos. Furthermore, it outperforms the state-of-the-art VLA model trained with robotic action labels on real-world manipulation tasks that require language conditioning, generalization to unseen objects, and semantic generalization to unseen instructions. Training only on human manipulation videos also shows positive transfer, opening up the potential for leveraging web-scale data for robotics foundation model.

This whole technology of putting artificial brain into machine is really fascinating, we humans because of our ingenious intellect has this natural instincts to go beyond what seems impossible to create tools and technology which becomes an extension to our day to day life, which can make decisions on our part and make our living super efficient. It is with this urge to make humans super productive we started putting artificial intelligence to the computer machines and now we have come a long way to build machines which can nearly think like human brains. Today we will see how Deep learning a branch of ML is really doing justice to all those valuable data floating around in this universe and processing it efficiently to help us reach to some rational conclusions in the filed of Speech recognition, Image Recognition, NLP, Healthcare, Financial Sector etc.. As we know that various Machine Learning techniques has been used to process our raw data to help us is content filtering on social network, to write recommendation engine for e-commerce based portals, In Image and Pattern recognitions, to transcribe speech to text etc. In 1986 Rina Dechter coined the expression Deep Learning for the first time, but Ivakhnenko & Lapa in 1965 wrote the first working learning algorithm for supervised, deep, feedforward, multilayer perceptrons was published by Ivakhnenko and Lapa in 1965.These ideas were implemented in a computer identification system by the World School Council London called "Alpha", which demonstrated the learning process.