Reinforcement Learning from Human Feedback (RLHF) has emerged as a vital technique in aligning large language models (LLMs) with human values and expectations. It plays a critical role in ensuring that AI systems behave in understandable and trustworthy ways. RLHF enhances the capabilities of LLMs by training them based on feedback that allows models to…
The adversarial attacks and defenses for LLMs encompass a wide range of techniques and strategies. Manually crafted and automated red teaming methods expose vulnerabilities, while white box access reveals potential for prefilling attacks. Defense approaches include RLHF, DPO, prompt optimization, and adversarial training. Inference-time defenses and representation engineering show promise but face limitations. The control…
The advancement of large language models (LLMs) in natural language processing has significantly improved various domains. As more complex models are developed, evaluating their outputs accurately becomes essential. Traditionally, human evaluations have been the standard approach for assessing quality, but this process is time consuming and needs to be more scalable for the rapid pace…
Text-to-image (T2I) models have seen rapid progress in recent years, allowing the generation of complex images based on natural language inputs. However, even state-of-the-art T2I models need help accurately capture and reflect all the semantics in given prompts, leading to images that may miss crucial details, such as multiple subjects or specific spatial relationships. For…
Multi-View and Multi-Scale Alignment for Mammography Contrastive Learning:Contrastive Language-Image Pre-training (CLIP) has shown potential in medical imaging, but its application to mammography faces challenges due to limited labeled data, high-resolution images, and imbalanced datasets. This study introduces the first full adaptation of CLIP to mammography through a new framework called Multi-view and Multi-scale Alignment (MaMA).…
AMD has recently introduced its new language model, AMD-135M or AMD-Llama-135M, which is a significant addition to the landscape of AI models. Based on the LLaMA2 model architecture, this language model boasts a robust structure with 135 million parameters and is optimized for performance on AMD’s latest GPUs, specifically the MI250. This release marks a…
The research evaluates the reliability of large language models (LLMs) such as GPT, LLaMA, and BLOOM, extensively used across various domains, including education, medicine, science, and administration. As the usage of these models becomes more prevalent, understanding their limitations and potential pitfalls is crucial. The research highlights that as these models increase in size and…
Integrating AI-powered code-generating technologies, such as ChatGPT and GitHub Copilot, is revolutionizing programming education. These tools, by providing real-time assistance to developers, accelerate the development process, enhance problem-solving, and make coding more accessible. Their increasing prevalence has sparked a growing interest in their influence on how students learn programming. While these tools can speed up…
Machine Learning ML offers significant potential for accelerating the solution of partial differential equations (PDEs), a critical area in computational physics. The aim is to generate accurate PDE solutions faster than traditional numerical methods. While ML shows promise, concerns about reproducibility in ML-based science are growing. Issues like data leakage, weak baselines, and insufficient validation…
In the age of data-driven artificial intelligence, LLMs like GPT-3 and BERT require vast amounts of well-structured data from diverse sources to improve performance across various applications. However, manually curating these datasets from the web is labor-intensive, inefficient, and often unscalable, creating a significant hurdle for developers aiming to acquire huge data. Traditional web crawlers…