RealUnify: 统一模型真的能从统一中受益吗？一个全面的基准测试
RealUnify: Do Unified Models Truly Benefit from Unification? A Comprehensive Benchmark
AI总结：
RealUnify基准测试旨在评估统一模型中理解与生成能力的双向协同效应，通过10类32子任务的1000个人工标注实例，揭示现有统一模型在协同能力上的不足，强调需新的训练策略来提升统一建模潜力。
摘要：
将视觉理解和生成整合到统一多模态模型中是迈向通用人工智能的重要一步。然而，现有基准测试未能回答核心问题：这种架构统一是否能促进各能力的协同互动？现有评估方法主要单独评估理解和生成，无法判断统一模型是否能利用理解增强生成，或用生成模拟促进深度理解。为填补这一空白，我们引入RealUnify基准测试，专门评估双向能力协同。RealUnify包含1000个精心人工标注的实例，涵盖10类和32个子任务。其结构围绕两个核心轴线：1）理解增强生成，要求推理（如常识、逻辑）指导图像生成；2）生成增强理解，需心理模拟或重建（如变换或混乱的视觉输入）以解决推理任务。关键贡献是我们的双评估协议，结合直接端到端评估与诊断分步评估，将任务分解为独立的理解和生成阶段。此协议使我们能精确区分性能瓶颈源于核心能力缺陷还是整合失败。通过大规模评估12个领先统一模型和6个专用基线，发现当前统一模型仍难以实现有效协同，表明架构统一本身不足。这些结果强调需要新的训练策略和归纳偏置来完全释放统一建模潜力。
英文摘要：
The integration of visual understanding and generation into unified multimodal models represents a significant stride toward general-purpose AI. However, a fundamental question remains unanswered by existing benchmarks: does this architectural unification actually enable synergetic interaction between the constituent capabilities? Existing evaluation paradigms, which primarily assess understanding and generation in isolation, are insufficient for determining whether a unified model can leverage its understanding to enhance its generation, or use generative simulation to facilitate deeper comprehension. To address this critical gap, we introduce RealUnify, a benchmark specifically designed to evaluate bidirectional capability synergy. RealUnify comprises 1,000 meticulously human-annotated instances spanning 10 categories and 32 subtasks. It is structured around two core axes: 1) Understanding Enhances Generation, which requires reasoning (e.g., commonsense, logic) to guide image generation, and 2) Generation Enhances Understanding, which necessitates mental simulation or reconstruction (e.g., of transformed or disordered visual inputs) to solve reasoning tasks. A key contribution is our dual-evaluation protocol, which combines direct end-to-end assessment with a diagnostic stepwise evaluation that decomposes tasks into distinct understanding and generation phases. This protocol allows us to precisely discern whether performance bottlenecks stem from deficiencies in core abilities or from a failure to integrate them. Through large-scale evaluations of 12 leading unified models and 6 specialized baselines, we find that current unified models still struggle to achieve effective synergy, indicating that architectural unification alone is insufficient. These results highlight the need for new training strategies and inductive biases to fully unlock the potential of unified modeling.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
