The development of natural language processing has been significantly propelled by the advancements in large language models (LLMs). These models have showcased remarkable performance in tasks like translation, question answering, and text summarization, proving their efficiency in generating high-quality text. However, despite their effectiveness, one major limitation remains their slow inference speed, which hinders their… →
Imagine you’re looking for the perfect gift for your kid – a fun yet safe tricycle that ticks all the boxes. You might search with a query like “Can you help me find a push-along tricycle from Radio Flyer that’s both fun and safe for my kid?” Sounds pretty specific, right? But what if the… →
Fine-tuning large language models (LLMs) efficiently and effectively is a common challenge. Imagine you have a massive LLM that needs adjustments or training for specific tasks, but the process is slow and resource-intensive. This can slow down the progress and make it difficult to deploy AI solutions quickly. Currently, some solutions are available for fine-tuning… →
Many applications have used large language models (LLMs). However, when deployed to GPU servers, their high memory and computing demands result in substantial energy and financial expenditures. Some acceleration solutions can be used with laptop commodity GPUs, but their precision could be better. Although many LLM acceleration methods aim to decrease the number of non-zero… →
Gene editing is a cornerstone of modern biotechnology. It enables the precise manipulation of genetic material, which has implications across various fields, from medicine to agriculture. Recent innovations have pushed the boundaries of this technology, providing tools that enhance precision and expand applicability. The primary challenge in gene editing lies in the complexity of designing… →
Understanding Human and Artificial Intelligence: Human intelligence is complex, encompassing various cognitive abilities such as problem-solving, creativity, emotional intelligence, and social interaction. In contrast, artificial intelligence represents a different paradigm, focusing on specific tasks performed through algorithms, data processing, and machine learning techniques. Fundamental Differences: Human and artificial intelligence differ fundamentally in structure, speed, connectivity,… →
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… →