GEAR jointly trains VQ tokenizer and AR generator end-to-end via dual hard/soft read-out and representation alignment, achieving up to 10x faster ImageNet gFID convergence than LlamaGen-REPA while generalizing across quantizers and to text-to-image.
hub Canonical reference
Diffusion Transformers with Representation Autoencoders
Canonical reference. 73% of citing Pith papers cite this work as background.
89
Pith papers citing it
Background
73% of classified citations
abstract
Latent generative modeling, where a pretrained autoencoder maps pixels into a latent space for the diffusion process, has become the standard strategy for Diffusion Transformers (DiT); however, the autoencoder component has barely evolved. Most DiTs continue to rely on the original VAE encoder, which introduces several limitations: outdated backbones that compromise architectural simplicity, low-dimensional latent spaces that restrict information capacity, and weak representations that result from purely reconstruction-based training and ultimately limit generative quality. In this work, we explore replacing the VAE with pretrained representation encoders (e.g., DINO, SigLIP, MAE) paired with trained decoders, forming what we term Representation Autoencoders (RAEs). These models provide both high-quality reconstructions and semantically rich latent spaces, while allowing for a scalable transformer-based architecture. Since these latent spaces are typically high-dimensional, a key challenge is enabling diffusion transformers to operate effectively within them. We analyze the sources of this difficulty, propose theoretically motivated solutions, and validate them empirically. Our approach achieves faster convergence without auxiliary representation alignment losses. Using a DiT variant equipped with a lightweight, wide DDT head, we achieve strong image generation results on ImageNet: 1.51 FID at 256x256 (no guidance) and 1.13 at both 256x256 and 512x512 (with guidance). RAE offers clear advantages and should be the new default for diffusion transformer training.
hub tools
citation-role summary
background 17
baseline 3
method 1
other 1
citation-polarity summary
claims ledger
- abstract Latent generative modeling, where a pretrained autoencoder maps pixels into a latent space for the diffusion process, has become the standard strategy for Diffusion Transformers (DiT); however, the autoencoder component has barely evolved. Most DiTs continue to rely on the original VAE encoder, which introduces several limitations: outdated backbones that compromise architectural simplicity, low-dimensional latent spaces that restrict information capacity, and weak representations that result from purely reconstruction-based training and ultimately limit generative quality. In this work, we ex
co-cited works
representative citing papers
PRA approximates sequential rollout training in parallel for pixel-space AR models via intermediate states and a pixel decoder, achieving FID 2.58 (135M params) and 1.94 (511M params) on ImageNet-1K 256x256, new SOTA among pixel-space AR models.
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.
A diffusion-based contrastive analysis method that decomposes conditioning into common and salient factors with weak supervision and proves identifiability of the additive model.
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.
Mind-Omni unifies seven brain-vision-language tasks in one discrete-diffusion framework with a brain tokenizer and a new BQA dataset, claiming SOTA multi-task performance competitive with larger single-task models.
JET is a conditional flow matching framework that generates EEG as continuous raw sequences with added constraints for spectral and temporal properties, achieving over 40% lower TS-FID than prior discrete denoising methods on three benchmarks.
DRoRAE adaptively fuses multi-layer features from vision encoders via energy-constrained routing to enrich visual tokens, cutting rFID from 0.57 to 0.29 and generation FID from 1.74 to 1.65 on ImageNet-256 while revealing a log-linear scaling law with fusion capacity.
RLA-WM predicts residual latent actions via flow matching to create visual feature world models that outperform prior feature-based and diffusion approaches while enabling offline video-based robot RL.
CoReDi coevolves semantic representations with the diffusion model via a jointly learned linear projection stabilized by stop-gradient, normalization, and regularization, yielding faster convergence and higher sample quality than fixed-representation baselines.
A 3D-grounded autoencoder and diffusion transformer allow direct generation of 3D scenes in an implicit latent space using a fixed 1K-token representation for arbitrary views and resolutions.
SetFlow is a flow-matching generative model for permutation-invariant MIL bags in representation space that produces synthetic data improving classification performance and enabling training on synthetic data alone.
Matched benchmarking reveals FID misleads in few-step regimes under CFG, prompting CLIP-scaled and PickScore-scaled FID and IS variants for better semantic evaluation of one-step image generators.
DREAM introduces Masking Warmup and Semantically Aligned Decoding to let a single encoder handle both contrastive alignment and masked generation, yielding gains over CLIP and FLUID on understanding and generation benchmarks.
PointDiT is a from-scratch pixel-space Diffusion Transformer for monocular 3D point map estimation that outperforms latent diffusion models in sharpness and ambiguous regions while using a simpler architecture.
FlowWM applies flow matching directly in pretrained feature space with a one-step projection mechanism, improving perception accuracy, mode coverage, and horizon robustness on synthetic and real-world benchmarks.
PixelU is a minimalist U-shaped Diffusion Transformer for pixel-space diffusion that decouples frequencies with zero-cost skip connections and constant-channel downsampling, outperforming baselines like JiT-G at 1/3 the compute cost with FID 1.63 on ImageNet 256x256.
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.
IDEAL improves discrete representation autoencoders by jointly aligning quantized tokens with shallow and deep VFM features, reporting 0.61 rFID on ImageNet and 1.89 gFID for autoregressive image generation.
Echo-DM proposes a mask-free conditional latent diffusion framework with region-aware fusion for removing markers from ultrasound images while preserving anatomical fidelity.
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.
Representation Forcing enables end-to-end pixel-space unified multimodal models by making visual representation prediction a native autoregressive generation target that guides subsequent pixel diffusion in the same backbone.
MergeTok unifies VAE and VQ tokenizers via token merging to impose semantic alignment on continuous latents and stabilize discrete codebook training, achieving lower rFID on ImageNet-256.
Dasheng AudioGen uses multi-view captions and a unified semantic-acoustic representation to enable end-to-end generation of mixed audio scenes from text descriptions.
citing papers explorer
-
GEAR: Guided End-to-End AutoRegression for Image Synthesis
GEAR jointly trains VQ tokenizer and AR generator end-to-end via dual hard/soft read-out and representation alignment, achieving up to 10x faster ImageNet gFID convergence than LlamaGen-REPA while generalizing across quantizers and to text-to-image.
-
Parallel Rollout Approximation for Pixel-Space Autoregressive Image Generation
PRA approximates sequential rollout training in parallel for pixel-space AR models via intermediate states and a pixel decoder, achieving FID 2.58 (135M params) and 1.94 (511M params) on ImageNet-1K 256x256, new SOTA among pixel-space AR models.
-
STREAM: Stochastic Riemannian Flow Matching with Anisotropic Decoder for Digital Histopathology Image Generation
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.
-
Diff-CA: Separating Common and Salient Factors with Diffusion Models
A diffusion-based contrastive analysis method that decomposes conditioning into common and salient factors with weak supervision and proves identifiability of the additive model.
-
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.
-
Mind-Omni: A Unified Multi-Task Framework for Brain-Vision-Language Modeling via Discrete Diffusion
Mind-Omni unifies seven brain-vision-language tasks in one discrete-diffusion framework with a brain tokenizer and a new BQA dataset, claiming SOTA multi-task performance competitive with larger single-task models.
-
Let EEG Models Learn EEG
JET is a conditional flow matching framework that generates EEG as continuous raw sequences with added constraints for spectral and temporal properties, achieving over 40% lower TS-FID than prior discrete denoising methods on three benchmarks.
-
Beyond the Last Layer: Multi-Layer Representation Fusion for Visual Tokenization
DRoRAE adaptively fuses multi-layer features from vision encoders via energy-constrained routing to enrich visual tokens, cutting rFID from 0.57 to 0.29 and generation FID from 1.74 to 1.65 on ImageNet-256 while revealing a log-linear scaling law with fusion capacity.
-
Learning Visual Feature-Based World Models via Residual Latent Action
RLA-WM predicts residual latent actions via flow matching to create visual feature world models that outperform prior feature-based and diffusion approaches while enabling offline video-based robot RL.
-
Coevolving Representations in Joint Image-Feature Diffusion
CoReDi coevolves semantic representations with the diffusion model via a jointly learned linear projection stabilized by stop-gradient, normalization, and regularization, yielding faster convergence and higher sample quality than fixed-representation baselines.
-
Any 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at Scale
A 3D-grounded autoencoder and diffusion transformer allow direct generation of 3D scenes in an implicit latent space using a fixed 1K-token representation for arbitrary views and resolutions.
-
SetFlow: Generating Structured Sets of Representations for Multiple Instance Learning
SetFlow is a flow-matching generative model for permutation-invariant MIL bags in representation space that produces synthetic data improving classification performance and enabling training on synthetic data alone.
-
Setting-Matched and Semantics-Scaled Benchmarking of One-Step Generative Models Against Multistep Diffusion and Flow Models
Matched benchmarking reveals FID misleads in few-step regimes under CFG, prompting CLIP-scaled and PickScore-scaled FID and IS variants for better semantic evaluation of one-step image generators.
-
Unifying Contrastive and Generative Objectives for Visual Understanding and Text-to-Image Generation
DREAM introduces Masking Warmup and Semantically Aligned Decoding to let a single encoder handle both contrastive alignment and masked generation, yielding gains over CLIP and FLUID on understanding and generation benchmarks.
-
PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation
PointDiT is a from-scratch pixel-space Diffusion Transformer for monocular 3D point map estimation that outperforms latent diffusion models in sharpness and ambiguous regions while using a simpler architecture.
-
Flow Matching in Feature Space for Stochastic World Modeling
FlowWM applies flow matching directly in pretrained feature space with a one-step projection mechanism, improving perception accuracy, mode coverage, and horizon robustness on synthetic and real-world benchmarks.
-
PixelU: A U-Shaped Transformer for Efficient End-to-End Pixel Diffusion
PixelU is a minimalist U-shaped Diffusion Transformer for pixel-space diffusion that decouples frequencies with zero-cost skip connections and constant-channel downsampling, outperforming baselines like JiT-G at 1/3 the compute cost with FID 1.63 on ImageNet 256x256.
-
HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers
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.
-
IDEAL: In-DEpth ALignment Makes A Discrete Representation AutoEncoder
IDEAL improves discrete representation autoencoders by jointly aligning quantized tokens with shallow and deep VFM features, reporting 0.61 rFID on ImageNet and 1.89 gFID for autoregressive image generation.
-
Echo-DM: Ultrasound Marker Removal via Conditional Latent Diffusion and Region-Aware Fusion
Echo-DM proposes a mask-free conditional latent diffusion framework with region-aware fusion for removing markers from ultrasound images while preserving anatomical fidelity.
-
Generate in Reconstruction Space, Match in Semantic Space: Transport Geometry for One-Step Generation
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.
-
Representation Forcing for Bottleneck-Free Unified Multimodal Models
Representation Forcing enables end-to-end pixel-space unified multimodal models by making visual representation prediction a native autoregressive generation target that guides subsequent pixel diffusion in the same backbone.
-
MergeTok: Unified Continuous and Discrete Visual Tokenization via Token Merging
MergeTok unifies VAE and VQ tokenizers via token merging to impose semantic alignment on continuous latents and stabilize discrete codebook training, achieving lower rFID on ImageNet-256.
-
Dasheng AudioGen: A Unified Model for Generating Coherent Audio Scenes from Text
Dasheng AudioGen uses multi-view captions and a unified semantic-acoustic representation to enable end-to-end generation of mixed audio scenes from text descriptions.
-
PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion
PiD is a pixel diffusion decoder that performs latent-to-pixel conversion and 4-8x upsampling in one generative step, enabling early stopping of latent diffusion and achieving sub-second 2048x2048 decoding with claimed better fidelity than cascaded baselines.
-
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.
-
Spatial Gram Alignment for Ultra-High-Resolution Image Synthesis
Spatial Gram Alignment aligns internal self-similarities of LDM features with foundation priors to reconcile global structure and fine details in ultra-high-resolution text-to-image synthesis.
-
Rethinking Cross-Layer Information Routing in Diffusion Transformers
DAR replaces residual addition in DiTs with learnable, timestep-adaptive aggregation of sublayer outputs, yielding 2.11 FID improvement on SiT-XL/2 and 8.75x faster convergence on ImageNet 256x256.
-
UniRefiner: Teaching Pre-trained ViTs to Self-Dispose Dross via Contrastive Register
UniRefiner uses contrastive registers and a dual alignment objective to remove three categories of spurious tokens from pre-trained ViTs, yielding up to 9.4% mIoU gains on ADE20K and 22% zero-shot segmentation improvements.
-
Lance: Unified Multimodal Modeling by Multi-Task Synergy
Lance presents a dual-stream mixture-of-experts model with modality-aware positional encoding and staged multi-task training that outperforms prior open-source unified models on image and video generation while keeping strong understanding performance.
-
Resolving Representation Ambiguity in Feedforward Novel View Synthesis Transformer via Semantic-Spatial Decoupling
Decouples semantic and spatial tokens in NVS transformers to resolve representation ambiguity, yielding consistent gains with near-zero added latency.
-
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.
-
Improved Baselines with Representation Autoencoders
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.
-
SRC-Flow: Compact Semantic Representations Enable Normalizing Flows for Image Generation
SRC-Flow compresses RAE features via a Semantic Representation Compressor into a low-dimensional space, enabling normalizing flows to reach gFID 1.65 on ImageNet 256x256 and 2.07 on 512x512 while retaining exact likelihoods.
-
The Learnability Gap in Medical Latent Diffusion
Pretrained autoencoders in medical latent diffusion encode discriminative features well for reconstruction but structure their latent spaces in ways that hinder classifier learning, a gap that persists across architectures and is not closed by domain fine-tuning.
-
Beyond Point-Wise Matching: Structural Representation Alignment for Accelerating Diffusion Transformers
sREPA enforces structural consistency in relational geometry of pre-trained vision features to accelerate DiT training and improve generation quality.
-
DiLA: Disentangled Latent Action World Models
DiLA uses content-structure disentanglement driven by predictive bottlenecks to create semantically structured latent actions for high-fidelity video world models.
-
Efficient Image Synthesis with Sphere Latent Encoder
Decouples Sphere Encoder into fixed pretrained encoder and spherical latent denoiser, yielding higher quality and faster inference than the joint original on Animal-Faces, Oxford-Flowers and ImageNet-1K.
-
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.
-
One-Step Generative Modeling via Wasserstein Gradient Flows
W-Flow compresses a Wasserstein gradient flow defined via Sinkhorn divergence into a single-step neural generator, reporting 1.29 FID on ImageNet 256x256 with improved mode coverage.
-
PoDAR: Power-Disentangled Audio Representation for Generative Modeling
PoDAR disentangles audio signal power from semantic content in latents using power augmentation and consistency objectives, yielding 2x faster convergence and gains of 0.055 speaker similarity and 0.22 UTMOS when applied to Stable Audio VAE with F5-TTS.
-
How to Train Your Latent Diffusion Language Model Jointly With the Latent Space
Joint training of the latent space with the diffusion process produces a competitive latent diffusion language model that is faster than existing discrete and continuous diffusion baselines.
-
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.
-
Continuous Latent Diffusion Language Model
Cola DLM proposes a hierarchical latent diffusion model that learns a text-to-latent mapping, fits a global semantic prior in continuous space with a block-causal DiT, and performs conditional decoding, establishing latent prior modeling as an alternative to token-level autoregressive language model
-
ViTok-v2: Scaling Native Resolution Auto-Encoders to 5 Billion Parameters
ViTok-v2 is a 5B-parameter native-resolution image autoencoder using NaFlex and DINOv3 loss that matches or exceeds prior tokenizers at 256p and outperforms them at 512p and above while advancing the Pareto frontier in joint scaling with generators.
-
Taming Outlier Tokens in Diffusion Transformers
Outlier tokens in DiTs are addressed with Dual-Stage Registers, which reduce artifacts and improve image generation on ImageNet and text-to-image tasks.
-
End-to-End Autoregressive Image Generation with 1D Semantic Tokenizer
An end-to-end autoregressive model with a jointly trained 1D semantic tokenizer achieves state-of-the-art FID 1.48 on ImageNet 256x256 generation without guidance.
-
Beyond Gaussian Bottlenecks: Topologically Aligned Encoding of Vision-Transformer Feature Spaces
S²VAE replaces Gaussian bottlenecks with hyperspherical Power Spherical latents in a VAE on VGGT features, yielding better results on depth estimation, camera pose recovery, and point cloud reconstruction especially at high compression.
-
CoreFlow: Low-Rank Matrix Generative Models
CoreFlow is a low-rank matrix generative model that trains normalizing flows on shared subspaces to improve efficiency and quality for high-dimensional limited-sample data, including incomplete matrices.
-
Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation
Tuna-2 shows that direct pixel embeddings can replace vision encoders in unified multimodal models, achieving competitive generation and stronger understanding at scale.