GRACE: Generation-aware latent compression for efficient video generation
cs.CV
Submitted: 2026-10-07
Updated: 2026-10-07
Project page: https://cvlab-kaist.github.io/GRACE/8
Sources
- DA-VAE: Plug-in Latent Compression for Diffusion via Detail Alignment
- Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models
- DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder
- DC-AE 1.5: Accelerating Diffusion Model Convergence with Structured Latent Space
- Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers
- LeanVAE: An Ultra-Efficient Reconstruction VAE for Video Diffusion Models
- Scaling Rectified Flow Transformers for High-Resolution Image Synthesis
- LTX-Video: Realtime Video Latent Diffusion
- LoRA: Low-Rank Adaptation of Large Language Models
- VBench: Comprehensive Benchmark Suite for Video Generative Models
- VBench++: Comprehensive and Versatile Benchmark Suite for Video Generative Models
- Auto-Encoding Variational Bayes
- T2V-Turbo: Breaking the Quality Bottleneck of Video Consistency Model with Mixed Reward Feedback
- WF-VAE: Enhancing Video VAE by Wavelet-Driven Energy Flow for Latent Video Diffusion Model
- DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps
- Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model
- Progressive Growing of Video Tokenizers for Temporally Compact Latent Spaces
- V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning
- Cosmos World Foundation Model Platform for Physical AI
- GPT-4 Technical Report
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