# CADMA: Capacity-Aware Coverage Decomposition for Generative Model Assessment

**Authors:** Debin Meng, Zheng Gao, Ziquan Liu, Yanran Li, Ioannis Patras, Georgios Tzimiropoulos  
**Published:** 9 Nov 2026  
**Links:** [arXiv](https://arxiv.org/abs/2611.12243) · [PDF](https://arxiv.org/pdf/2611.12243) · [Code](https://github.com/Open-Debin/CADMA_NeurIPS2026) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2611.12243.html)

## Abstract

Evaluating generative models requires measuring not only sample fidelity but also how well a generated set covers the real data distribution. Recent work has therefore introduced recall-oriented metrics for distribution-level evaluation. However, existing recall metrics often reduce distributional coverage to geometry-based coverage. This simplifying assumption weakens their diagnostic value and interpretability in two ways: these metrics provide only a single aggregate score that cannot distinguish essential diversity failures such as mode dropping and mode collapse, and geometry-based coverage can provide unreliable estimates by assigning high scores to poorly covered generative distributions. We therefore introduce CADMA, a capacity-aware framework for recall-oriented evaluation and diagnosis. CADMA evaluates distributional coverage through local capacity matching between real and generated samples, separating geometry-based coverage from effective coverage. This yields multi-dimensional coverage diagnostics that quantify mode dropping and mode collapse while reducing the overly optimistic estimates produced by geometry-based metrics. Through extensive experiments on toy data, real-world datasets, and generative models, we show that CADMA provides more reliable coverage estimates and more fine-grained, interpretable diagnostic signals of diversity failures than existing metrics. Our code is available at https://github.com/Open-Debin/CADMA_NeurIPS2026.

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.