Reconstruction Alignment Improves Unified Multimodal Models
For practitioners of unified multimodal models, RECA offers an efficient and general post-training strategy to improve generation and editing fidelity without requiring additional captioned data.
Reconstruction Alignment (RECA) is a post-training method that improves unified multimodal models by using visual understanding embeddings as dense text prompts to reconstruct input images, achieving significant gains in generation (GenEval 0.73→0.90, DPGBench 80.93→88.15) and editing (ImgEdit 3.38→3.75, GEdit 6.94→7.27) with only 27 GPU hours.
Unified multimodal models (UMMs) unify visual understanding and generation within a single architecture. However, conventional training relies on image-text pairs (or sequences) whose captions are typically sparse and miss fine-grained visual details, even when they use hundreds of words to describe a simple image. We introduce Reconstruction Alignment (RECA), a resource-efficient post-training method that leverages visual understanding encoder embeddings as dense "text prompts", providing rich supervision without captions. Concretely, RECA conditions a UMM on its own visual understanding embeddings and optimizes it to reconstruct the input image with a self-supervised reconstruction loss, thereby realigning understanding and generation. Despite its simplicity, RECA is broadly applicable: across autoregressive, masked-autoregressive, and diffusion-based UMMs, it consistently improves generation and editing fidelity. With only 27 GPU hours, post-training with RECA substantially improves image generation performance on GenEval (0.73 $\rightarrow$ 0.90) and DPGBench (80.93 $\rightarrow$ 88.15), while also boosting editing benchmarks (ImgEdit 3.38 $\rightarrow$ 3.75, GEdit 6.94 $\rightarrow$ 7.27). Notably, RECA surpasses much larger open-source models and applies broadly across diverse UMM architectures, establishing it as an efficient and general post-training alignment strategy for UMMs.