LaViDa-R1用统一框架让多模态扩散语言模型更强推理能力。
LaViDa-R1: Advancing Reasoning for Unified Multimodal Diffusion Language Models
- 用统一后训练框架融合监督微调与多任务强化学习。
- 在视觉数学、图像定位等任务上表现优异，支持图像编辑。
- 适合研究多模态生成与复杂推理的开发者或学者。
扩散语言模型（dLLMs）成为自回归大模型的有力替代。最新研究将其拓展至多模态理解与生成任务。本文提出LaViDa-R1，一种通用多模态推理扩散语言模型。不同于以往通过任务特定强化学习构建推理dLLMs的方法，LaViDa-R1以统一方式整合多种多模态理解与生成任务。其采用新型统一后训练框架，无缝融合监督微调（SFT）与多任务强化学习（RL），并引入答案强制、树搜索和互补似然估计等新训练技术，提升效果与可扩展性。大量实验表明，LaViDa-R1在视觉数学推理、强推理型定位及图像编辑等广泛多模态任务中表现突出。
原文摘要 · Abstract (English)
Diffusion language models (dLLMs) recently emerged as a promising alternative to auto-regressive LLMs. The latest works further extended it to multimodal understanding and generation tasks. In this work, we propose LaViDa-R1, a multimodal, general-purpose reasoning dLLM. Unlike existing works that build reasoning dLLMs through task-specific reinforcement learning, LaViDa-R1 incorporates diverse multimodal understanding and generation tasks in a unified manner. In particular, LaViDa-R1 is built with a novel unified post-training framework that seamlessly integrates supervised finetuning (SFT) and multi-task reinforcement learning (RL). It employs several novel training techniques, including answer-forcing, tree search, and complementary likelihood estimation, to enhance effectiveness and scalability. Extensive experiments demonstrate LaViDa-R1's strong performance on a wide range of multimodal tasks, including visual math reasoning, reason-intensive grounding, and image editing.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。