NanoGen unifies DiT training on ImageNet and T2I, reveals negative Pearson correlations (-0.377 to -0.580) in method rankings across metrics from 21 models, and motivates DiffusionBench for holistic evaluation.
arXiv:2407.00783 (2024) 4
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
Sparse internal snapshots at canonical low-noise levels from frozen diffusion backbones suffice for competitive out-of-distribution detection without full trajectories or large heads.
Aligning noisy hidden states in diffusion transformers to clean features from pretrained visual encoders speeds up training over 17x and reaches FID 1.42.
Semantic Generative Tuning applies segmentation-based generative proxies during post-training to align and improve both understanding and generation in unified multimodal models.
A simplified one-step diffusion distillation uses pretrained teacher features directly for drifting loss plus a mode coverage term, achieving FID 1.58 on ImageNet-64 and 18.4 on SDXL.
citing papers explorer
-
DiffusionBench: On Holistic Evaluation of Diffusion Transformers
NanoGen unifies DiT training on ImageNet and T2I, reveals negative Pearson correlations (-0.377 to -0.580) in method rankings across metrics from 21 models, and motivates DiffusionBench for holistic evaluation.