Best of Both Worlds: Multimodal Reasoning and Generation via Unified Discrete Flow Matching 事件

Best of Both Worlds: Multimodal Reasoning and Generation via Unified Discrete Flow Matching arXiv:2602.12221v2 Announce Type: replace Abstract: We propose UniDFlow, a unified discrete flow-matching framework for multimodal understanding, generation, and editing. It decouples understanding and generation via task-specific low-rank adapters, avoiding objective interference and representation entanglement, while a novel reference-based multimodal preference alignment optimizes relative outcomes un