LatentUMM proposes dual latent alignment at modality and capacity levels plus latent dynamics stabilization to reduce semantic drift and improve consistency in unified multimodal models.
Generation enhances understanding in unified multimodal models via multi-representation generation
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
abstract
Unified Multimodal Models (UMMs) integrate both visual understanding and generation within a single framework. Their ultimate aspiration is to create a cycle where understanding and generation mutually reinforce each other. While recent post-training methods have successfully leveraged understanding to enhance generation, the reverse direction of utilizing generation to improve understanding remains largely unexplored. In this work, we propose UniMRG (Unified Multi-Representation Generation), a simple yet effective architecture-agnostic post-training method. UniMRG enhances the understanding capabilities of UMMs by incorporating auxiliary generation tasks. Specifically, we train UMMs to generate multiple intrinsic representations of input images, namely pixel (reconstruction), depth (geometry), and segmentation (structure), alongside standard visual understanding objectives. By synthesizing these diverse representations, UMMs capture complementary information regarding appearance, spatial relations, and structural layout. Consequently, UMMs develop a deeper and more comprehensive understanding of visual inputs. Extensive experiments across diverse UMM architectures demonstrate that our method notably enhances fine-grained perception, reduces hallucinations, and improves spatial understanding, while simultaneously boosting generation capabilities.
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 5years
2026 5verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
Latent Action Control learns unobserved action trajectories via variational alignment and GRPO to inject reasoning into flow-based image generation, yielding gains on compositional benchmarks.
SpatialFusion internalizes 3D geometric awareness into unified image generation models by pairing an MLLM with a spatial transformer that produces depth maps to constrain diffusion generation.
UniCanvas introduces a diffusion-based approach for unified multimodal generation by embedding text as visual patterns within images on a shared canvas.
Semantic Generative Tuning applies segmentation-based generative proxies during post-training to align and improve both understanding and generation in unified multimodal models.
citing papers explorer
-
LatentUMM: Dual Latent Alignment for Unified Multimodal Models
LatentUMM proposes dual latent alignment at modality and capacity levels plus latent dynamics stabilization to reduce semantic drift and improve consistency in unified multimodal models.
-
Latent Action Control for Reasoning-Guided Unified Image Generation
Latent Action Control learns unobserved action trajectories via variational alignment and GRPO to inject reasoning into flow-based image generation, yielding gains on compositional benchmarks.
-
SpatialFusion: Endowing Unified Image Generation with Intrinsic 3D Geometric Awareness
SpatialFusion internalizes 3D geometric awareness into unified image generation models by pairing an MLLM with a spatial transformer that produces depth maps to constrain diffusion generation.
-
UniCanvas: A Diffusion-base Unified Model for Text-in-Image Joint Generation
UniCanvas introduces a diffusion-based approach for unified multimodal generation by embedding text as visual patterns within images on a shared canvas.
-
Semantic Generative Tuning for Unified Multimodal Models
Semantic Generative Tuning applies segmentation-based generative proxies during post-training to align and improve both understanding and generation in unified multimodal models.