Ant Group mở nguồn mô hình đa phương tiện Ling-3.0-flash-VL với 124 tỷ tham số

The Huoxing Finance report states that on September 9, Ant Group announced the official release and open-sourcing of Ling-3.0-flash-VL, the first native multimodal large model in the Ling series. The model is built upon the MoE architecture of Ling-3.0-flash, with a total of 124B parameters and activates 5.5B parameters per inference. It natively supports inputs of images, text, and video, with a context window of 256K tokens. Focused on “how to complete real-world tasks more reliably and efficiently,” Ling-3.0-flash-VL explores the following directions: A common concern when adding visual capabilities to large models is that it may reduce textual intelligence. However, training practices have yielded the opposite conclusion: native multimodal joint training not only expands the application boundaries but also enhances textual intelligence. Ling-3.0-flash-VL introduces a visual feedback mechanism—observing execution outcomes, comparing against goals, identifying deviations, and continuously correcting—that transforms tasks from one-time “generation” into a closed loop of “observe → act → verify → correct,” resulting in more reliable outcomes. Ling-3.0-flash-VL inherits the core advantage of Ling-3.0-flash as an efficient execution node in Agent workflows, balancing output quality and execution efficiency within the visual feedback loop to advance complete tasks at lower cost and in less time.