There is currently a significant gap between the performance of fine-tuned models and prompting approaches using Large Language Models (LLMs) on the challenging task of text-to-SQL, as evaluated on datasets such as Spider. To improve the performance of LLMs in the reasoning process, we study how decomposing the task into smaller sub-tasks can be effective. In particular, we show that breaking down the generation problem into sub-problems and feeding the solutions of those sub-problems into LLMs can be an effective approach for significantly improving their performance. Our experiments with three LLMs show that this approach consistently improves their simple few-shot performance by roughly 10%, pushing the accuracy of LLMs towards SOTA or surpassing it. On the holdout test set of Spider, the SOTA, in terms of execution accuracy, was 79.9 and the new SOTA at the time of this writing using our approach is 85.3. Our approach with in-context learning beats many heavily fine-tuned models by at least 5%. Additionally, when evaluated on the BIRD benchmark, our approach achieved an execution accuracy of 55.9%, setting a new SOTA on its holdout test set.

There is currently a significant gap between the performance of fine-tuned models and prompting approaches using Large Language Models (LLMs) on the challenging task of text-to-SQL, as evaluated on datasets such as Spider. To improve the performance of LLMs in the reasoning process, we study how decomposing the task into smaller sub-tasks can be effective. In particular, we show that breaking down the generation problem into sub-problems and feeding the solutions of those sub-problems into LLMs can be an effective approach for significantly improving their performance. Our experiments with three LLMs show that this approach consistently improves their simple few-shot performance by roughly 10%, pushing the accuracy of LLMs towards SOTA or surpassing it. On the holdout test set of Spider, the SOTA, in terms of execution accuracy, was 79.9 and the new SOTA at the time of this writing using our approach is 85.3.

Generative models create latent representations, which distil information from big data in order to generate realistic and novel data points. In the long term, these models could be vital in developing accurate world models, as well as learning categorical and continuous features of a dataset in an unsupervised way. Currently, generative models are demonstrating their value in a variety of downstream tasks such as inpainting, super-resolution, and generating continuous exploration spaces for reinforcement learning. Generative Adversarial Networks (GANs) have represented the state of the art (SotA) for some time, however recently OpenAI has published results that make a strong case for a new era of Denoising Diffusion Probabilistic models dominating generative SotA applications. In this article, I shall introduce the theory behind this method and describe the contributions which have enabled this relatively unstudied technique to topple GANs.

Building versatile vision-language models that not only work on a single language but can generalize across all the world's approximately 7,000 languages is difficult -- and the task becomes even more challenging if the model is transferred without any additional annotated training data. To tackle this issue, a research team from Carnegie Mellon, Oxford and Facebook AI has proposed a transformer-based model, Multilingual Multimodal Pretraining (MMP), that can learn contextualized multilingual multimodal embeddings under a zero-shot setting. Recent research in cross-lingual transfer learning has demonstrated that models using only English annotation can nonetheless generalize to a non-English language. This success is attributed to the shared underlying vocabulary or structure amongst many languages. For example, many English and German words stem from the same origin, and many languages have the same recursive structures.

New SOTA in video object segmentation is insane VOS aims at segment target instances in a video sequence. A high-performing #AI should be able to delineate an object from the background or other distractors (e.g., similar instances) under occlusion, appearance changes, and deformation. Frame aggregation process as a (fast) voting problem New SOTA and faster: 20 FPS for multiple objects Link to paper, project, and source code in the first comment Want to know more about #AI? Follow ARGO Vision or ping me #artificialintelligence #machinelearning #deeplearningai #deepneuralnetworks #neuralnetworks #ml #deeplearning #computervision #nvidiavgpu #nvidia #neurips2021

Following on the February release of its contrastive learning framework SimCLR, the same team of Google Brain researchers guided by Turing Award honouree Dr. Geoffrey Hinton has presented SimCLRv2, an upgraded approach that boosts the SOTA results by 21.6 percent. The updated framework takes the "unsupervised pretrain, supervised fine-tune" paradigm popular in natural language processing and applies it to image recognition. Unlabelled data is learned in a task-agnostic way in the pretraining phase, which means the model has no prior classification knowledge. The researchers find that using a deep and wide neural network can be more label-efficient and greatly improve accuracy. Unlike SimCLR, whose largest model is ResNet-50, SimCLRv2's largest model is a 152-layer ResNet, which is three times wider in channels and selective kernels.

The results from all the categories are mindblowing. For example, for traditional language modeling tasks, GPT-3 sets a new SOTA on the Penn Tree Bank dataset by a margin of 15 points based on zero-shot perplexity. GPT-3 showed amazing results in question answering tests. In general, these tests are separated into open-book and closed-book tests. Due to the number of possible queries, open-book tests use an information retrieval system to find relevant text and then the model learns to generate the answer from the question and retrieved text. Closed-book tests don't have this retrieval system.