EchoGen: Cycle-Consistent Learning for Unified Layout-Image Generation and Understanding

• URL: http://arxiv.org/abs/2603.18001v1
• Date: Wed, 18 Mar 2026 17:59:03 GMT
• Title: EchoGen: Cycle-Consistent Learning for Unified Layout-Image Generation and Understanding
• Abstract summary: EchoGen is a unified framework for layout-to-image generation and image grounding.<n>Image grounding possesses strong text and layout understanding abilities, which can compensate for the limitations in layout-to-image generation.<n>Images generated from layouts exhibit high diversity in content, thereby enhancing the robustness of image grounding.
• Score: 21.73510227758125
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this work, we present EchoGen, a unified framework for layout-to-image generation and image grounding, capable of generating images with accurate layouts and high fidelity to text descriptions (e.g., spatial relationships), while grounding the image robustly at the same time. We believe that image grounding possesses strong text and layout understanding abilities, which can compensate for the corresponding limitations in layout-to-image generation. At the same time, images generated from layouts exhibit high diversity in content, thereby enhancing the robustness of image grounding. Jointly training both tasks within a unified model can promote performance improvements for each. However, we identify that this joint training paradigm encounters several optimization challenges and results in restricted performance. To address these issues, we propose progressive training strategies. First, the Parallel Multi-Task Pre-training (PMTP) stage equips the model with basic abilities for both tasks, leveraging shared tokens to accelerate training. Next, the Dual Joint Optimization (DJO) stage exploits task duality to sequentially integrate the two tasks, enabling unified optimization. Finally, the Cycle RL stage eliminates reliance on visual supervision by using consistency constraints as rewards, significantly enhancing the model's unified capabilities via the GRPO strategy. Extensive experiments demonstrate state-of-the-art results on both layout-to-image generation and image grounding benchmarks, and reveal clear synergistic gains from optimizing the two tasks together.

Related papers

• GMAIL: Generative Modality Alignment for generated Image Learning [51.071351994330605]
  We propose a novel framework for discriminative use of generated images, coined GMAIL, that explicitly treats generated images as a separate modality from real images.<n>Our framework can be easily incorporated with various vision-language models, and we demonstrate its efficacy throughout extensive experiments.
  arXiv  Detail & Related papers  (2026-02-17T05:40:25Z)
• Interleaving Reasoning for Better Text-to-Image Generation [83.69082794730664]
  We introduce Interleaving Reasoning Generation (IRG), a framework that alternates between text-based thinking and image synthesis.<n>To train IRG effectively, we propose Interleaving Reasoning Generation Learning (IRGL), which targets two sub-goals.<n>Experiments show SoTA performance, yielding absolute gains of 5-10 points on GenEval, WISE, TIIF, GenAI-Bench, and OneIG-EN.
  arXiv  Detail & Related papers  (2025-09-08T17:56:23Z)
• MENTOR: Efficient Multimodal-Conditioned Tuning for Autoregressive Vision Generation Models [30.494968865008513]
  Recent text-to-image models struggle with precise visual control, balancing multimodal inputs, and requiring extensive training for complex image generation.<n>We propose MENTOR, a novel framework for efficient Multimodal-conditioned Tuning for Autoregressive multimodal image generation.<n>Our method delivers superior image reconstruction fidelity, broad task adaptability, and improved training efficiency compared to diffusion-based methods.
  arXiv  Detail & Related papers  (2025-07-13T10:52:59Z)
• Policy Optimized Text-to-Image Pipeline Design [73.9633527029941]
  We introduce a novel reinforcement learning-based framework for text-to-image generation.<n>Our approach first trains an ensemble of reward models capable of predicting image quality scores directly from prompt-workflow combinations.<n>We then implement a two-phase training strategy: initial vocabulary training followed by GRPO-based optimization.
  arXiv  Detail & Related papers  (2025-05-27T17:50:47Z)
• Unified Autoregressive Visual Generation and Understanding with Continuous Tokens [52.21981295470491]
  We present UniFluid, a unified autoregressive framework for joint visual generation and understanding.<n>Our unified autoregressive architecture processes multimodal image and text inputs, generating discrete tokens for text and continuous tokens for image.<n>We find though there is an inherent trade-off between the image generation and understanding task, a carefully tuned training recipe enables them to improve each other.
  arXiv  Detail & Related papers  (2025-03-17T17:58:30Z)
• Towards Enhanced Image Generation Via Multi-modal Chain of Thought in Unified Generative Models [52.84391764467939]
  Unified generative models have shown remarkable performance in text and image generation.<n>We introduce Chain of Thought (CoT) into unified generative models to address the challenges of complex image generation.<n>Experiments show that FoX consistently outperforms existing unified models on various T2I benchmarks.
  arXiv  Detail & Related papers  (2025-03-03T08:36:16Z)
• Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step [86.69947123512836]
  Chain-of-Thought (CoT) reasoning has been extensively explored in large models to tackle complex understanding tasks.<n>We provide the first comprehensive investigation of the potential of CoT reasoning to enhance autoregressive image generation.<n>We propose the Potential Assessment Reward Model (PARM) and PARM++, specialized for autoregressive image generation.
  arXiv  Detail & Related papers  (2025-01-23T18:59:43Z)
• SpotActor: Training-Free Layout-Controlled Consistent Image Generation [43.2870588035256]
  We present a new formalization of dual energy guidance with optimization in a dual semantic-latent space. We propose a training-free pipeline, SpotActor, which features a layout-conditioned backward update stage and a consistent forward sampling stage. The results prove that SpotActor fulfills the expectations of this task and showcases the potential for practical applications.
  arXiv  Detail & Related papers  (2024-09-07T11:52:48Z)
• A Generative Adversarial Framework for Optimizing Image Matting and Harmonization Simultaneously [7.541357996797061]
  We propose a new Generative Adversarial (GAN) framework which optimizing the matting network and the harmonization network based on a self-attention discriminator. Our dataset and dataset generating pipeline can be found in urlhttps://git.io/HaMaGAN
  arXiv  Detail & Related papers  (2021-08-13T06:48:14Z)
• LT-GAN: Self-Supervised GAN with Latent Transformation Detection [10.405721171353195]
  We propose a self-supervised approach (LT-GAN) to improve the generation quality and diversity of images. We experimentally demonstrate that our proposed LT-GAN can be effectively combined with other state-of-the-art training techniques for added benefits.
  arXiv  Detail & Related papers  (2020-10-19T22:09:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.