End-to-end (E2E) neural networks have emerged as flexible and accurate models for multilingual automatic speech recognition (ASR). However, as the number of supported languages increases, particularly those with large character sets like Chinese, Japanese, and Korean (CJK), the output layer size grows substantially. This expansion negatively impacts compute resources, memory usage, and asset size. The…
Large Language Models (LLMs) have revolutionized software engineering, demonstrating remarkable capabilities in various coding tasks. While recent efforts have produced autonomous software agents based on LLMs for end-to-end development tasks, these systems are typically designed for specific Software Engineering (SE) tasks. Researchers from FPT Software AI Center, Viet Nam, introduce HyperAgent, a novel generalist multi-agent…
Understanding multi-page documents and news videos is a common task in human daily life. To tackle such scenarios, Multimodal Large Language Models (MLLMs) should be equipped with the ability to understand multiple images with rich visually-situated text information. However, comprehending document images is more challenging than natural images, as it requires a more fine-grained perception…
AI has seen significant progress in coding, mathematics, and reasoning tasks. These advancements are driven largely by the increased use of large language models (LLMs), essential for automating complex problem-solving tasks. These models are increasingly used to handle highly specialized and structured problems in competitive programming, mathematical proofs, and real-world coding issues. This rapid evolution…
Recent advancements in medical multimodal large language models (MLLMs) have shown significant progress in medical decision-making. However, many models, such as Med-Flamingo and LLaVA-Med, are designed for specific tasks and require large datasets and high computational resources, limiting their practicality in clinical settings. While the Mixture-of-Expert (MoE) strategy offers a solution using smaller, task-specific modules…
AI models, such as language models, need to maintain a long-term memory of their interactions to generate relevant and contextually appropriate content. One of the primary challenges in maintaining a long-term memory of their interactions is data storage and retrieval efficiency. Current language models, such as Claude, need more effective memory systems, leading to repetitive…
Phind has officially announced the release of its new flagship model, Phind-405B, along with an innovative Phind Instant model aimed at revolutionizing AI-powered search and programming tasks. These advancements represent a milestone in technical capabilities, empowering developers and technical users with more efficient, powerful tools for complex problem-solving. Introduction of Phind-405B Phind-405B is the cornerstone…
Large language models (LLMs) have gained significant attention in the field of artificial intelligence, particularly in the development of model-based agents. These agents, equipped with probabilistic world models, can anticipate future environmental states and plan accordingly. While world models have shown promise in reinforcement learning, researchers are now exploring their potential to enhance agent controllability.…