图像生成

ScalingAR: Scaling Confidence for Autoregressive Image Generation

ScalingAR: 自回归图像生成的置信度缩放

Harold Haodong Chen, Xianfeng Wu, Wen-Jie Shu, Rongjin Guo, Disen Lan, Harry Yang, Ying-Cong Chen

专题命中 图像生成评测 ：image generation(title,abstract)；分类 cs.CV

AI总结 提出ScalingAR框架，通过令牌熵作为置信度信号，在轮廓级和策略级进行自适应轨迹剪枝和动态引导调度，无需早期解码或外部奖励，显著提升自回归图像生成性能。

Comments ICML 2026; Code: https://github.com/EnVision-Research/ScalingAR

AMVICC: A Novel Benchmark for Cross-Modal Failure Mode Profiling for VLMs and IGMs

AMVICC: 一种用于VLM和IGM跨模态故障模式分析的新型基准

Aahana Basappa, Pranay Goel, Anusri Karra, Anish Karra, Asa Gilmore, Kevin Zhu

机构 * Centennial High School, Frisco, Texas, USA（Centennial High School, Texas, USA） ； Lebanon Trail High School, Frisco, Texas, USA（Lebanon Trail High School, Texas, USA） ； West Windsor-Plainsboro High School, Princeton Junction, New Jersey, USA（West Windsor-Plainsboro High School, New Jersey, USA） ； Algoverse AI Research, Palo Alto, California, USA（Algoververse AI Research, California, USA） 纠错

专题命中 图像生成评测 ：image generation(abstract)；text-to-image(abstract)；分类 cs.CV

AI总结 提出AMVICC基准，通过图像到文本和文本到图像任务系统比较多模态大模型和图像生成模型的视觉推理失败模式，发现故障模式在模型和模态间共享，但存在特定于模型和模态的失败。

Comments 14 pages, 4 figures, 8 tables. Presented at the 39th Conference on Neural Information Processing Systems Workshop: VLM4RWD. Presented at the 43th International Conference on Machine Learning Workshops: ICML 2026 CTB, ICML 2026 FAGEN, ICML 2026 EMM-QA. Authors Aahana Basappa and Pranay Goel contributed equally. Code: https://github.com/AahanaB24/AMVICC, Data: https://doi.org/10.5281/zenodo.17646068

C3-Bench: A Context-Aware Change Captioning Benchmark

C3-Bench：一种上下文感知的变化描述基准

Jae-Woo Kim, Hyeongbeom Kim, Ue-Hwan Kim

机构 * Gwangju Institute of Science and Technology（光州科学技术院） 纠错

专题命中 图像生成评测 ：image editing(abstract)；分类 cs.CV

AI总结 提出C3-Bench基准，包含51种真实变化场景的4996对图像，并首次引入LLM-as-Judge评估框架，揭示现有模型在非训练分布场景下的系统性盲点。

Comments ECCV 2026 Camera-ready version