Continuous language diffusion works by entering high-margin decoder basins where frozen T5 embeddings recover 93-96% of native decisions and linear readouts reach 97.9% agreement, implying models should be evaluated as representation-decoder systems.
Diffuse and disperse: Image generation with representation regularization
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
citation-role summary
background 1
baseline 1
citation-polarity summary
years
2026 13representative citing papers
STREAM applies stochastic Riemannian flow matching on VFM-derived unit hypersphere latents with a novel anisotropic decoder to achieve SOTA reconstruction and generation on breast and colorectal cancer histopathology datasets.
Feature self-guidance disperses internal features of flow models during batch generation and applies manifold regularization to increase output diversity while preserving condition alignment.
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.
HYDRA-X presents the first unified multimodal model using a single ViT for holistic image-video tokenization, with ablations on attention and compression plus a latent-level editing improvement.
Matching in semantic SSL feature space via Sinkhorn divergence enables effective one-step generation on ImageNet by inducing compact geometry for distribution matching, with training and evaluation features best kept distinct.
RAE v2 reaches gFID 1.06 on ImageNet-256 in 80 epochs by combining multi-layer encoder sums, complementary REPA targets, and free guidance via output reparameterization.
A semantic progress signal from SSL discrepancy slope enables three stage-aware mechanisms that improve training efficiency and performance in audio diffusion models over static baselines.
Continuous adversarial flow models replace MSE in flow matching with adversarial training via a discriminator, improving guidance-free FID on ImageNet from 8.26 to 3.63 for SiT and similar gains for JiT and text-to-image benchmarks.
MPDiT uses a hierarchical multi-patch design in transformers to lower computation in diffusion models by handling coarse global features first then fine local details, plus faster-converging embeddings.
Premier learns user-specific embeddings to modulate text-to-image generation, outperforming prior methods on preference alignment, text consistency, and expert ratings even with limited history.
Native3D introduces a direct 3D scene generation method using unified mesh-texture representation and 3D REPA Loss for semantic alignment, claimed to outperform prior 2D-dependent approaches.
Med-DisSeg uses a dispersive loss on batch representations plus adaptive multi-scale decoding to achieve state-of-the-art fine-grained segmentation on five medical imaging datasets.
citing papers explorer
-
Continuous Adversarial Flow Models
Continuous adversarial flow models replace MSE in flow matching with adversarial training via a discriminator, improving guidance-free FID on ImageNet from 8.26 to 3.63 for SiT and similar gains for JiT and text-to-image benchmarks.