CADMA: Capacity-Aware Coverage Decomposition for Generative Model Assessment
cs.CV, cs.LG
Submitted: 2026-11-09
Updated: 2026-11-09
Code: https://github.com/Open-Debin/CADMA_NeurIPS2026
Terminology
Sources
- Consistency-diversity-realism Pareto fronts of conditional image generative models
- A Note on the Inception Score
- Demystifying MMD GANs
- Auto-Encoding Variational Bayes
- DINOv2: Learning Robust Visual Features without Supervision
- Position: All Current Generative Fidelity and Diversity Metrics are Flawed
- Denoising Diffusion Implicit Models
- An empirical study on evaluation metrics of generative adversarial networks
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs