Decentralized Autoregressive Generation

Abstract: We present a theoretical analysis of decentralization of autoregressive generation. We define the Decentralized Discrete Flow Matching objective, by expressing probability generating velocity as a linear combination of expert flows. We also conduct experiments demonstrat- ing the equivalence between decentralized and centralized training settings for multimodal LLMs across diverse set of benchmarks. Specifically, we compare two distinct paradigms: LLaVA and InternVL 2.5-1B, which uses a fixed CLIP vision encoder and per- forms full-parameter fine-tuning (ViT+MLP+LLM) during the instruction tuning stage.