Large language models (LLMs) have shown promise in solving planning problems, but their success has been limited, particularly in the process of translating natural language planning descriptions into structured planning languages such as the Planning Domain Definition Language (PDDL). Current models, including GPT-4, have achieved only 35% accuracy on simple planning tasks, emphasizing the need…
Robustness plays a significant role in implementing deep learning models in real-world use cases. Vision Transformers (ViTs), launched in the 2020s, have proven themselves to be robust and offer high-performance levels in various visual tasks, surpassing traditional Convolutional Neural Networks (CNNs). It’s been recently seen that large kernel convolutions can potentially match or overtake ViTs…
Natural Language Processing (NLP) is rapidly evolving, with small efficient language models gaining relevance. These models, ideal for efficient inference on consumer hardware and edge devices, allow for offline applications and have shown significant utility when fine-tuned for tasks like sequence classification or question answering. They can often outperform larger models in specialized areas.
One…
Artificial intelligence (AI) continues to shape and influence a multitude of sectors with its profound capabilities. Especially in video game creation, AI has shown significant strides by admirably handling complex procedures that generally need human intervention. One of the latest breakthroughs in this domain is the development of “GAVEL,” an automated system that leverages large…
A team from Harvard University and the Kempner Institute at Harvard University have conducted an extensive comparative study on optimization algorithms used in training large-scale language models. The investigation targeted popular algorithms like Adam - an optimizer lauded for its adaptive learning capacity, Stochastic Gradient Descent (SGD) that trades adaptive capabilities for simplicity, Adafactor with…
Researchers from the Massachusetts Institute of Technology, University of Toronto, and Vector Institute for Artificial Intelligence have developed a new method called IF-COMP for improving the estimation of uncertainty in machine learning, particularly in deep learning neural networks. These fields place importance on not only accurately predicting outcomes but quantifying the uncertainty involved in these…
Methods for evaluating the dependability of a multi-functional AI model prior to its implementation.
Foundation models, or large-scale deep-learning models, are becoming increasingly prevalent, particularly in powering prominent AI services such as DALL-E, or ChatGPT. These models are trained on huge quantities of general-purpose, unlabeled data, which is then repurposed for various uses, such as image generation or customer service tasks. However, the complex nature of these AI tools…
IBM researchers are working on addressing the challenge of digging out beneficial insights from large databases, a problem often encountered in businesses. The volume and variety of data are overwhelming and can pose a significant challenge for employees to find the necessary information. Writing SQL codes, needed to retrieve data across multiple programs and tables,…
IBM researchers have taken a major step toward simplifying the process of extracting valuable insights from large business databases. Currently, these databases are queried using Structured Query Language (SQL), a dominating language for database interactions. However, SQL proficiency typically lies within a small group of data professionals, presenting a barrier to broader data access and…
Human-computer interaction (HCI) greatly enhances the communication between individuals and computers across various dimensions including social dialogue, writing assistance, and multimodal interactions. However, issues surrounding continuity and personalization during long-term interactions remain. Many existing systems require tracking user-specific details and preferences over longer periods, leading to discontinuity and insufficient personalization.
In response to these challenges,…