STARFlow2: Bridging Language Models and Normalizing Flows for Unified Multimodal Generation

STARFlow2 presents a unified multimodal generation framework by interleaving a frozen pretrained VLM stream with a TARFlow stream using residual skip connections. This approach preserves multimodal understanding, enables high-fidelity continuous image generation, and achieves structural unification under a single causal mechanism. It supports cache-friendly interleaved generation where both text and visual outputs enter the KV-cache without re-encoding.