DC-SAE: Deep Compression Semantic Autoencoder for Faster Diffusion Convergence

arXiv:2609.39222 · cs.CV · Submitted 2026-09-30 · Read on arXiv

cs.CV

Submitted: 2026-09-30

Updated: 2026-09-30

Code: https://github.com/DAGroup-PKU/DCSAE

Project page: https://dagroup-pku.github.io/DCSAE

Terminology

• Diffusion Model — 25× in this paper · explained in 8 episodes
• Latent Space — 19× in this paper · explained in 7 episodes
• Fidelity — 17× in this paper · explained in 2 episodes
• Diffusion Models — 10× in this paper · explained in 6 episodes
• Tokenization — 9× in this paper · explained in 2 episodes
• Transformer — 9× in this paper · explained in 2 episodes
• Alignment — 7× in this paper · explained in 1 episode
• Latent Representation — 7× in this paper · explained in 2 episodes
• Generative Model — 6× in this paper · explained in 2 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Generative Models — 4× in this paper · explained in 2 episodes
• Latent Representations — 4× in this paper · explained in 3 episodes
• Regularization — 4× in this paper · explained in 3 episodes
• Ablation Studies — 3× in this paper · explained in 1 episode
• Abstraction — 3× in this paper · explained in 1 episode
• Latent Diffusion Model — 3× in this paper · explained in 2 episodes
• Distillation — 2× in this paper · explained in 2 episodes
• Generative Modeling — 2× in this paper · explained in 3 episodes
• Latent Diffusion Models — 2× in this paper · explained in 2 episodes
• Representation Learning — 2× in this paper · explained in 2 episodes
• Self-distillation — 2× in this paper · explained in 6 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Feature Extraction — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• KL Regularization — 1× in this paper · explained in 2 episodes
• Objective Mismatch — 1× in this paper · explained in 2 episodes
• Quantization — 1× in this paper · explained in 12 episodes
• Semantic Alignment — 1× in this paper · explained in 3 episodes
• Semantic Understanding — 1× in this paper · explained in 2 episodes
• Variational Bayes — 1× in this paper · explained in 2 episodes

Sources

• FlexTok: Resampling Images into 1D Token Sequences of Flexible Length
• Qwen3-VL Technical Report
• DC-AE 1.5: Accelerating Diffusion Model Convergence with Structured Latent Space
• Emu3.5: Native Multimodal Models are World Learners
• Unified Autoregressive Visual Generation and Understanding with Continuous Tokens
• Seed1.5-VL Technical Report
• ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment
• Ming-UniVision: Joint Image Understanding and Generation with a Unified Continuous Tokenizer
• LatentUM: Unleashing the Potential of Interleaved Cross-Modal Reasoning via a Latent-Space Unified Model
• Auto-Encoding Variational Bayes
• TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders
• Autoregressive Image Generation without Vector Quantization
• DGAE: Diffusion-Guided Autoencoder for Efficient Latent Representation Learning
• Delving into Latent Spectral Biasing of Video VAEs for Superior Diffusability
• UniTok: A Unified Tokenizer for Visual Generation and Understanding
• LongCat-Next: Lexicalizing Modalities as Discrete Tokens
• Cosmos World Foundation Model Platform for Physical AI
• Latent Diffusion Model without Variational Autoencoder
• DINOv3
• UniLiP: Adapting CLIP for Unified Multimodal Understanding, Generation and Editing

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models