We investigate the capabilities of transformer models on relational reasoning tasks. In these tasks, models are trained on a set of strings encoding abstract relations, and are then tested out-of-distribution on data that contains symbols that did not appear in the training dataset. We prove that for any relational reasoning task in a large family…
Score-based models have quickly become the de facto choice for generative modeling of images, text and more recently molecules. However, to adapt a score-based generative modeling to these domains the score network needs to be carefully designed, hampering its applicability to arbitrary data domains. In this paper we tackle this problem by taking a textit{functional}…
Large Language Models (LLMs) have succeeded greatly and are widely used in various fields. LLMs are sensitive to input prompts, and this behavior has led to multiple research studies to understand and exploit this characteristic. This helps to create prompts for learning tasks like zero-shot and in-context. For instance, AutoPrompt recognizes task-specific tokens for zero-shot…
PyTorch recently introduced ExecuTorch alpha to address the challenge of deploying powerful machine learning models, including extensive language models (LLMs), on edge devices that are limited in resources, such as smartphones and wearables. In the past, such models required a significant amount of computational resources, which rendered their deployment on edge devices impractical. The researchers…
Artificial intelligence and machine learning are fields focused on creating algorithms to enable machines to understand data, make decisions, and solve problems. Researchers in this domain seek to design models that can process vast amounts of information efficiently and accurately, a crucial aspect in advancing automation and predictive analysis. This focus on the efficiency and…
Neuro-Symbolic Artificial Intelligence (AI) represents an exciting frontier in the field. It merges the robustness of symbolic reasoning with the adaptive learning capabilities of neural networks. This integration aims to harness the strong points of symbolic and neural approaches to create more versatile and reliable AI systems. Below, Let’s explore key insights and developments from…
Free LLM Playgrounds and Their Comparative Analysis As the landscape of AI technology advances, the proliferation of free platforms to test large language models (LLMs) online has greatly increased. These ‘playgrounds’ offer a valuable resource for developers, researchers, and enthusiasts to experiment with different models without requiring extensive setup or investment. Let’s explore a comparative…
Large language models (LLMs) are expanding in usage, posing new cybersecurity risks. These risks emerge from their core traits: heightened capability in code generation, heightened deployment for real-time code generation, automated execution within code interpreters, and integration into applications handling untrusted data. This poses the need for a robust mechanism for cybersecurity evaluations. Prior works…
The advent of generative artificial intelligence (AI) marks a significant technological leap, enabling the creation of new text, images, videos, and other media by learning from vast datasets. However, this innovative capability brings forth substantial copyright concerns, as it may utilize and repurpose the creative works of original authors without consent. This research addresses the…
Charts have become indispensable tools for visualizing data in information dissemination, business decision-making, and academic research. As the volume of multimodal data grows, a critical need arises for automated chart comprehension, which has garnered increasing attention from the research community. Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in comprehending images…