ViGoR-Bench: How Far Are Visual Generative Models From Zero-Shot Visual Reasoners?
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908916106919936 |
|---|---|
| author | Han, Haonan Huang, Jiancheng Sun, Xiaopeng He, Junyan Yang, Rui Hu, Jie Peng, Xiaojiang Ma, Lin Wei, Xiaoming Li, Xiu |
| author_facet | Han, Haonan Huang, Jiancheng Sun, Xiaopeng He, Junyan Yang, Rui Hu, Jie Peng, Xiaojiang Ma, Lin Wei, Xiaoming Li, Xiu |
| contents | 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/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_25823 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ViGoR-Bench: How Far Are Visual Generative Models From Zero-Shot Visual Reasoners? Han, Haonan Huang, Jiancheng Sun, Xiaopeng He, Junyan Yang, Rui Hu, Jie Peng, Xiaojiang Ma, Lin Wei, Xiaoming Li, Xiu Computer Vision and Pattern Recognition Artificial Intelligence 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/ |
| title | ViGoR-Bench: How Far Are Visual Generative Models From Zero-Shot Visual Reasoners? |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2603.25823 |