Staff

Artificial intelligence research often examines whether next-token prediction—the convention for AI language models—can replicate some aspects of human intelligence such as planning and reasoning. However, despite its extensive use, this method may have native limitations when it comes to tasks necessitating foresight and decision-making. This is important because overcoming this could allow the development of…

FlashAttention-3, the newest addition to the FlashAttention series, was created to address the fundamental issues related to Transformer architectures' attention layer. This is particularly important to the performance of large language models (LLMs) and applications that need long-context processing. Historically, the FlashAttention series, which includes FlashAttention and FlashAttention-2, has reshaped how attention mechanisms function on GPUs…

Recent research into Predictive Large Models (PLM) aims to align the models with human values, avoiding harmful behaviors while maximising efficiency and applicability. Two significant methods used for alignment are supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF). RLHF, notably, commoditizes the reward model to new prompt-response pairs. However, this approach often faces…

The field of large language models (LLMs), such as GPT, Claude, and Gemini, has seen rapid advancement, enabling the creation of autonomous agents capable of natural language interactions and executing diverse tasks. These AI agents are increasingly benefiting from the integration of external tools and knowledge sources, which expand their capacity to access and use…