VDOT++: Unified Few-Step Video Generation via Unbalanced Optimal Transport Distillation
cs.CV
Submitted: 2026-10-02
Updated: 2026-10-10
Terminology
Sources
- UNIC: Unified In-Context Video Editing
- HunyuanVideo: A Systematic Framework For Large Video Generative Models
- Wan: Open and Advanced Large-Scale Video Generative Models
- Neodragon: Mobile Video Generation using Diffusion Transformer
- PARE: Pruning and Adaptive Routing for Efficient Video Generation
- PulseQuant: Propagation-Guided Subspace Correction for 4-Bit Video Diffusion Transformers
- Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity
- LoSA: Near-Lossless Sparse Attention for Training-Free Video Diffusion Acceleration
- Salt++: Context-Aligned Post-Training for Few-Step Streaming Multimodal Generation
- Progressive Distillation for Fast Sampling of Diffusion Models
- Consistency Models
- Salt: Self-Consistent Distribution Matching with Cache-Aware Training for Fast Video Generation
- Diffusion Adversarial Post-Training for One-Step Video Generation
- AccVideo: Accelerating Video Diffusion Model with Synthetic Dataset
- Wasserstein Auto-Encoders
- YOLOX: Exceeding YOLO Series in 2021
- ChordEdit: One-Step Low-Energy Transport for Image Editing
- The relativistic discriminator: a key element missing from standard GAN
- LTX-Video: Realtime Video Latent Diffusion
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