REVIEW 20 cited by
MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizer
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
MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizer
read the original abstract
Despite its success in image synthesis, we observe that diffusion probabilistic models (DPMs) often lack contextual reasoning ability to learn the relations among object parts in an image, leading to a slow learning process. To solve this issue, we propose a Masked Diffusion Transformer (MDT) that introduces a mask latent modeling scheme to explicitly enhance the DPMs' ability to contextual relation learning among object semantic parts in an image. During training, MDT operates in the latent space to mask certain tokens. Then, an asymmetric diffusion transformer is designed to predict masked tokens from unmasked ones while maintaining the diffusion generation process. Our MDT can reconstruct the full information of an image from its incomplete contextual input, thus enabling it to learn the associated relations among image tokens. We further improve MDT with a more efficient macro network structure and training strategy, named MDTv2. Experimental results show that MDTv2 achieves superior image synthesis performance, e.g., a new SOTA FID score of 1.58 on the ImageNet dataset, and has more than 10x faster learning speed than the previous SOTA DiT. The source code is released at https://github.com/sail-sg/MDT.
Forward citations
Cited by 20 Pith papers
-
Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers
Chat-template tokens in LLM-conditioned DiTs act as implicit semantic registers: they absorb object identity from image latents and maintain it, while direct prompt-reading heads are causally inert.
-
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 ...
-
MaskAlign: Token-Subset Representation Alignment for Efficient Diffusion Training
MaskAlign uses random token-subset alignment and pre-mask mixing to reduce diffusion models' reliance on complete clean-image token sets during representation alignment.
-
Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation
A new shared video-image tokenizer enables large language models to surpass diffusion models on standard visual generation benchmarks.
-
Twins: Learn to Predict Unified Representations with Focal Loss
Channel-wise concatenation of SigLIP2 and Flux VAE features into one token, trained with a focal-style flow-matching loss, yields a unified representation with 1.59 gFID on ImageNet 256 and VAE-level reconstruction.
-
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.
-
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.
-
SRC-Flow: Compact Semantic Representations Enable Normalizing Flows for Image Generation
SRC-Flow compresses RAE features into a low-dimensional semantic space with a Semantic Representation Compressor, enabling normalizing flows to achieve SOTA gFID scores of 1.65 and 2.07 on ImageNet 256x256 and 512x512...
-
SRC-Flow: Compact Semantic Representations Enable Normalizing Flows for Image Generation
A learned 32-channel semantic compression lets a normalizing flow reach gFID 1.65 on ImageNet 256×256, the best FID reported for flow-based image generation.
-
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.
-
Frequency-Aware Flow Matching for High-Quality Image Generation
FreqFlow introduces frequency-aware conditioning and a two-branch architecture to flow matching, reaching FID 1.38 on ImageNet-256 and outperforming DiT and SiT.
-
Self-transcendence: Is External Feature Guidance Indispensable for Accelerating Diffusion Transformer Training?
A self-supervised two-stage training method—VAE-latent feature alignment then feature-level classifier-free guidance—lets DiT models match or beat DINO-guided REPA training without any external feature extractor.
-
MixFlow Training: Alleviating Exposure Bias with Slowed Interpolation Mixture
Training diffusion models on a mixture of higher-noise interpolations (MixFlow) improves generation FID across SiT, REPA, RAE and SD3.5, reaching ImageNet 256 gFID 1.43 after post-training.
-
REGLUE Your Latents with Global and Local Semantics for Entangled Diffusion
Nonlinear multi-layer compression of frozen VFM patch semantics, jointly denoised with VAE latents, improves ImageNet 256x256 FID (12.9 vs 15.2 for REG at SiT-B/2, 400K) and accelerates convergence over REPA/ReDi/REG.
-
Diagnosing and Improving Diffusion Models by Estimating the Optimal Loss Value
Derives closed-form optimal loss for unified diffusion models, provides variance-controlled estimators, and shows improved diagnosis, training schedules, and power-law scaling after subtracting the optimal value.
-
Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think
Aligning noisy hidden states in diffusion transformers to clean features from pretrained visual encoders speeds up training over 17x and reaches FID 1.42.
-
Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders
Training flow matching along sphere geodesics with a curvature-aware loss weight lets standard DiT-B converge on DINOv2 features (FID 3.37 with guidance), contradicting the need for width scaling.
-
Elucidating Representation Degradation Problem in Diffusion Model Training
Diffusion models suffer representation degradation at high noise due to recoverability mismatch; ERD mitigates this by dynamic optimization reallocation, accelerating convergence across backbones.
-
Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models
The paper reviews the background, technology, applications, limitations, and future directions of OpenAI's Sora text-to-video generative model based on public information.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.