Model Releases
RAC: Rectified Flow Auto Coder
arXiv:2603.05925v2 Announce Type: replace Abstract: In this paper, we propose a Rectified Flow Auto Coder (RAC) inspired by Rectified Flow to replace the traditional VAE: 1. It achieves multi-step dec
arXiv:2603.05925v2 Announce Type: replace Abstract: In this paper, we propose a Rectified Flow Auto Coder (RAC) inspired by Rectified Flow to replace the traditional VAE: 1. It achieves multi-step decoding by applying the decoder to flow timesteps. Its decoding path is straight and correctable, enabling step-by-step refinement. 2. The model inherently supports bidirectional inference, where the decoder serves as the encoder through time reversal (hence Coder rather than encoder or decoder), reducing parameter count by nearly 41%. 3. This generative decoding method improves generation quality since the model can correct latent variables along the path, partially addressing the reconstruction--generation gap. Experiments show that RAC achieves a Pareto improvement over SOTA VAEs, where even a 10imes parameter-reduced decoder exceeds full-scale VAE performance in both reconstruction and generation quality, validating the effectiveness of our approach.
Related
- Delta Rectified Flow Sampling for Text-to-Image Editing
- Contrast-X: A Multi-Modal Contrast Image Synthesis Benchmark and Universal Modality Flow Matching
- Setting-Matched and Semantics-Scaled Benchmarking of One-Step Generative Models Against Multistep Diffusion and Flow Models
Source: arXiv cs.CV | 2026-10-06