REVIEW 20 cited by
EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Latent generative models have emerged as a leading approach for high-quality image synthesis. These models rely on an autoencoder to compress images into a latent space, followed by a generative model to learn the latent distribution. We identify that existing autoencoders lack equivariance to semantic-preserving transformations like scaling and rotation, resulting in complex latent spaces that hinder generative performance. To address this, we propose EQ-VAE, a simple regularization approach that enforces equivariance in the latent space, reducing its complexity without degrading reconstruction quality. By finetuning pre-trained autoencoders with EQ-VAE, we enhance the performance of several state-of-the-art generative models, including DiT, SiT, REPA and MaskGIT, achieving a 7 speedup on DiT-XL/2 with only five epochs of SD-VAE fine-tuning. EQ-VAE is compatible with both continuous and discrete autoencoders, thus offering a versatile enhancement for a wide range of latent generative models. Project page and code: https://eq-vae.github.io/.
Forward citations
Cited by 20 Pith papers
-
SPAE: Spectrally Guided Autoencoder for Pretrained Visual Latents
SPAE compresses pretrained vision latents into a 64-channel bottleneck with channel-wise masking, improving image generation while keeping reconstruction and semantic understanding strong.
-
Diffusing in the Right Space: A Systematic Study of Latent Diffusability
A large-scale empirical study across tokenizers and diffusion backbones identifies Velocity Irreducible Variance (VIV) as one of the most stable predictors of latent diffusion generation quality.
-
How Neural Losses Shape VAE Latents
Neural reconstruction losses in VAEs reduce latent information content and produce more isotropic latent geometries with even uncertainty distribution.
-
AnchorMark: Robust Diffusion Watermarking via Latent-Space Rotation Synchrony
Image rotation is shown to rotate the recovered latent by the same angle, and a central phase anchor exploits this to estimate and undo rotation before decoding the watermark.
-
ROMS-IMLE: A Minimalist Approach to Competitive Single-Step Generative Modelling
A single-step IMLE generator with per-stage supervision and a robust loss reports FID 2.56 on ImageNet-256 by filtering ~5% of samples at test time.
-
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.
-
RiT: Vanilla Diffusion Transformers Suffice in Representation Space
A vanilla Diffusion Transformer trained via x-prediction on frozen DINOv2 features reaches FID 1.14 on ImageNet 256x256 with fewer parameters and faster sampling than prior DiT variants.
-
Vision Foundation Models as Generalist Tokenizers for Image Generation
VFMTok builds a generalist image tokenizer on frozen VFMs using adaptive quantization and semantic alignment, delivering gFID 1.36 for autoregressive and 1.25 for continuous generation on ImageNet with 3x faster convergence.
-
Aligning Latent Geometry for Spherical Flow Matching in Image Generation
Projecting VAE latents to a fixed spherical radius and replacing linear interpolation with spherical linear interpolation improves class-conditional ImageNet-256 FID while leaving the diffusion architecture unchanged.
-
What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion
Prior-Aligned AutoEncoders shape latent manifolds with spatial coherence, local continuity, and global semantics to improve latent diffusion, achieving SOTA gFID 1.03 on ImageNet 256x256 with up to 13x faster convergence.
-
Representations Before Pixels: Semantics-Guided Hierarchical Video Prediction
Re2Pix decomposes video prediction into semantic feature forecasting followed by representation-conditioned diffusion synthesis, with nested dropout and mixed supervision to handle prediction errors.
-
MPDiT: Multi-Patch Global-to-Local Transformer Architecture For Efficient Flow Matching and Diffusion Model
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.
-
VFM-VAE: Vision Foundation Models Can Be Good Tokenizers for Latent Diffusion Models
VFM-VAE uses a frozen VFM directly as LDM tokenizer via a custom decoder, reaching gFID 2.22 in 80 epochs and 1.62 after 640 epochs.
-
Missing Fine Details in Images: Last Seen in High Frequencies
A wavelet-based VAE that trains low- and high-frequency branches separately improves image reconstruction and diffusion generation.
-
Latent Wavelet Diffusion For Ultra-High-Resolution Image Synthesis
Latent Wavelet Diffusion uses wavelet energy map masking and a scale-consistent VAE to improve detail fidelity in 2K-4K image generation without extra inference overhead.
-
gen2seg: Generative Models Enable Generalizable Instance Segmentation
Finetuning generative models on limited instance segmentation data produces zero-shot generalization to unseen object categories and styles, matching or exceeding supervised baselines like SAM on ambiguous boundaries.
-
VOID: Defeating Unauthorized Mimicry in Latent Diffusion Models
VOID defeats mimicry in LDMs via stochasticity manipulation in the diffusion pipeline, raising average FID from 113 to 365 across evaluations.
-
Transforming the Use of Earth Observation Data: Exascale Training of a Generative Compression Model with Historical Priors for up to 10,000x Data Reduction
A generative compression model using historical priors for Earth observation data achieves up to 10,000x reduction after exascale training on an Armv9 supercomputer.
-
Cloning Deterministic Worlds: The Critical Role of Latent Geometry in Long-Horizon World Models
GRWM uses temporal contrastive learning to geometrically regularize latent spaces in world models for high-fidelity cloning of deterministic 3D worlds.
-
Home-made Diffusion Model from Scratch to Hatch
A consumer-grade diffusion model trains on four RTX5090 GPUs for $535-620 and produces 1024x1024 anime-style images, claiming competitive quality and emergent camera control.
Discussion (0). Sign in to comment.