标签
Inkling is a large open-weights multimodal model (975B total, 41B active parameters) using a sparse MoE architecture, accepting text, image, and audio inputs and generating text outputs, intended for agentic systems, coding assistants, and chatbots.
该论文引入了连续音频思考(CoAT)框架,为大型音频语言模型配备了一个连续的潜在工作空间,用于在生成文本响应之前组织声学信息,从而在音频推理、理解和转录任务中提升性能,且不增加额外的解码成本。