The remarkable success of OpenAI’s o1 series and DeepSeek-R1 has unequivocally demonstrated the power of large-scale reinforcement learning (RL) in eliciting sophisticated reasoning behaviors and significantly enhancing the capabilities of large language models (LLMs). However, the core training methodologies behind these groundbreaking reasoning models often remain veiled in their technical reports. Recent community efforts have…
Share My Research is Synced’s column that welcomes scholars to share their own research breakthroughs with over 2M global AI enthusiasts. Beyond technological advances, Share My Research also calls for interesting stories behind the research and exciting research ideas. Meet the authorInstitutions: Penn State University, Duke University, Google DeepMind, University of Washington, Meta, Nanyang Technological University, and…
A pair of groundbreaking research initiatives from Meta AI in late 2024 is challenging the fundamental “next-token prediction” paradigm that underpins most of today’s large language models (LLMs). The introduction of the BLT (Byte-Level Transformer) architecture, which eliminates the need for tokenizers and demonstrates significant potential in multimodal alignment and fusion, coincided with the unveiling…