Drug discovery is a costly, lengthy process with high failure rates, as only one viable drug typically emerges from a million screened compounds. Advanced high-throughput (HTS) and ultra-high-throughput screening (uHTS) technologies allow rapid testing of large compound libraries, enabling Pharma and Biotech companies to explore more chemical compounds and novel biological targets. Despite these technologies,…
Machine learning (ML) has revolutionized wireless communication systems, enhancing applications like modulation recognition, resource allocation, and signal detection. However, the growing reliance on ML models has increased the risk of adversarial attacks, which threaten the integrity and reliability of these systems by exploiting model vulnerabilities to manipulate predictions and performance. The increasing complexity of wireless…
In the evolving field of artificial intelligence, a major challenge has been building models that excel in specific tasks while also being capable of understanding and reasoning across multiple data types, such as text, images, and audio. Traditional large language models have been successful in natural language processing (NLP) tasks, but they often struggle to…
In today’s increasingly interconnected world, effective communication across languages is essential. However, many natural language processing (NLP) models still struggle with less common languages. This challenge is particularly evident for low-resource languages such as Thai, Mongolian, and Khmer, which lack the data and processing infrastructure available for languages like English or Chinese. Traditional NLP models…
The development of vision-language models (VLMs) has faced challenges in handling complex visual question-answering tasks. Despite substantial advances in reasoning capabilities by large language models like OpenAI’s GPT-o1, VLMs still struggle with systematic and structured reasoning. Current models often lack the ability to organize information and engage in logical, sequential reasoning, limiting their effectiveness for…
In recent years, the development of large language models has significantly advanced natural language processing (NLP). These models, trained on extensive datasets, can generate, understand, and analyze human language with remarkable proficiency. However, building such models requires substantial amounts of data, and access to high-quality multilingual datasets remains a considerable challenge. The scarcity of openly…
The field of artificial intelligence is advancing rapidly, yet significant challenges remain in developing and applying AI systems, particularly in complex reasoning. Many current AI solutions, including advanced models like GPT-4 and Claude 3.5 Sonnet, still struggle with intricate coding tasks, deep conversations, and mathematical reasoning. The limitations of individual models—no matter how sophisticated—lead to…
Recommender systems have been widely applied for studying user preferences; however, they face significant challenges in accurately capturing user preferences, particularly in the context of neural graph collaborative filtering. While these systems use interaction histories between users and items through Graph Neural Networks (GNNs) to mine latent information and capture high-order interactions, the quality of…