测试视觉生成模型的零样本推理能力，发现顶尖模型仍有严重逻辑短板。
ViGoR-Bench: How Far Are Visual Generative Models From Zero-Shot Visual Reasoners?
- 构建跨模态统一评测框架，覆盖图像到视频任务
- 同时评估生成过程与最终结果，揭示深层缺陷
- 用证据驱动的自动评分，更贴近人类判断
现代AIGC模型虽视觉效果惊艳，但在物理、因果或复杂空间推理任务上表现不佳，形成‘逻辑荒漠’。现有评估多依赖表面指标或碎片化基准，导致‘性能幻觉’。为此，我们提出ViGoR（Vision-Generative Reasoning-centric Benchmark）——一个统一评测框架，通过四大创新：1）贯通图像到图像、视频的跨模态覆盖；2）双轨机制评估中间过程与最终输出；3）基于证据的自动化评判，确保高人类对齐；4）细粒度诊断分析，拆解认知维度表现。在20多个领先模型上的实验表明，即使顶尖系统仍存在显著推理缺陷，验证了ViGoR作为下一代智能视觉模型关键‘压力测试’的价值。演示已开放：https://vincenthancoder.github.io/ViGoR-Bench/
原文摘要 · Abstract (English)
Beneath the stunning visual fidelity of modern AIGC models lies a "logical desert", where systems fail tasks that require physical, causal, or complex spatial reasoning. Current evaluations largely rely on superficial metrics or fragmented benchmarks, creating a ``performance mirage'' that overlooks the generative process. To address this, we introduce ViGoR Vision-G}nerative Reasoning-centric Benchmark), a unified framework designed to dismantle this mirage. ViGoR distinguishes itself through four key innovations: 1) holistic cross-modal coverage bridging Image-to-Image and Video tasks; 2) a dual-track mechanism evaluating both intermediate processes and final results; 3) an evidence-grounded automated judge ensuring high human alignment; and 4) granular diagnostic analysis that decomposes performance into fine-grained cognitive dimensions. Experiments on over 20 leading models reveal that even state-of-the-art systems harbor significant reasoning deficits, establishing ViGoR as a critical ``stress test'' for the next generation of intelligent vision models. The demo have been available at https://vincenthancoder.github.io/ViGoR-Bench/
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。