Paper Trail

Home

❯

generation evaluation

Folder: generation-evaluation

6 items under this folder.

  • Mar 18, 2026

    T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generation

    • paper
    • reward-model
    • hku
    • tsinghua
    • huawei
    • modality/image
    • modality/text
  • Mar 18, 2026

    EvalCrafter: Benchmarking and Evaluating Large Video Generation Models

    • paper
    • reward-model
    • tencent
    • modality/video
    • modality/text
  • Mar 18, 2026

    GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment

    • paper
    • reward-model
    • meta
    • cmu
    • modality/image
    • modality/text
  • Mar 18, 2026

    VBench: Comprehensive Benchmark Suite for Video Generative Models

    • paper
    • reward-model
    • ntu
    • shanghai-ai-lab
    • cuhk
    • nju
    • modality/video
  • Mar 18, 2026

    GenAI-Bench: Evaluating and Improving Compositional Text-to-Visual Generation

    • paper
    • reward-model
    • cmu
    • meta
    • modality/image
    • modality/video
    • modality/text
  • Mar 18, 2026

    VideoPhy: Evaluating Physical Commonsense for Video Generation

    • paper
    • reward-model
    • ucla
    • modality/video
    • modality/text

Created with Quartz v4.5.2 © 2026

  • GitHub