HiCoGen: Hierarchical Compositional Text-to-Image Generation in Diffusion Models via Reinforcement Learning

• URL: http://arxiv.org/abs/2511.19965v1
• Date: Tue, 25 Nov 2025 06:24:25 GMT
• Title: HiCoGen: Hierarchical Compositional Text-to-Image Generation in Diffusion Models via Reinforcement Learning
• Abstract summary: HiCoGen is built upon a novel Chain of Synthesis paradigm.<n>It decomposes complex prompts into minimal semantic units.<n>It then synthesizes these units iteratively, where the image generated in each step provides crucial visual context for the next.<n>Experiments show our approach significantly outperforms existing methods in both concept coverage and compositional accuracy.
• Score: 66.99487505369254
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in diffusion models have demonstrated impressive capability in generating high-quality images for simple prompts. However, when confronted with complex prompts involving multiple objects and hierarchical structures, existing models struggle to accurately follow instructions, leading to issues such as concept omission, confusion, and poor compositionality. To address these limitations, we propose a Hierarchical Compositional Generative framework (HiCoGen) built upon a novel Chain of Synthesis (CoS) paradigm. Instead of monolithic generation, HiCoGen first leverages a Large Language Model (LLM) to decompose complex prompts into minimal semantic units. It then synthesizes these units iteratively, where the image generated in each step provides crucial visual context for the next, ensuring all textual concepts are faithfully constructed into the final scene. To further optimize this process, we introduce a reinforcement learning (RL) framework. Crucially, we identify that the limited exploration of standard diffusion samplers hinders effective RL. We theoretically prove that sample diversity is maximized by concentrating stochasticity in the early generation stages and, based on this insight, propose a novel Decaying Stochasticity Schedule to enhance exploration. Our RL algorithm is then guided by a hierarchical reward mechanism that jointly evaluates the image at the global, subject, and relationship levels. We also construct HiCoPrompt, a new text-to-image benchmark with hierarchical prompts for rigorous evaluation. Experiments show our approach significantly outperforms existing methods in both concept coverage and compositional accuracy.

Related papers

• HiTokSR: A Coarse-to-Fine Tokenizer with Hierarchical Codebooks for High-Fidelity Real-World Image Super-Resolution [2.4519602914420475]
  We present HiTokSR, a hierarchical token prediction framework.<n>We show that HiTokSR achieves state-of-the-art performance in both quality and reconstruction fidelity.
  arXiv  Detail & Related papers  (2026-05-31T11:02:58Z)
• TILT: Improving Compositional Generation in Diffusion Models with a Model-Intrinsic Reward [7.47572316039482]
  We present TILT, a training-free framework for compositional text-to-image generation via test-time reward alignment.<n>We interpret compositional failures as overlap modes between joint and single-concept distributions, and define a reward that favors samples where all concepts are jointly present.<n>Experiments on prompts from T2ICompBench show that our method improves compositional alignment while preserving image quality compared to previous baselines.
  arXiv  Detail & Related papers  (2026-05-16T16:56:52Z)
• The Thinking Pixel: Recursive Sparse Reasoning in Multimodal Diffusion Latents [13.516336193977144]
  We propose a sparse mixture-of-experts framework integrated into conventional diffusion models to solve text-to-image generation tasks.<n>Our approach iteratively refines visual tokens over multiple latent steps while efficiently sharing parameters via sparse selection of neural modules.<n> Comprehensive evaluation on class-conditioned ImageNet image generation tasks and additional studies on the GenEval and DPG benchmark demonstrate the superiority of the proposed method in enhancing model image generation performance.
  arXiv  Detail & Related papers  (2026-04-28T07:09:18Z)
• StepVAR: Structure-Texture Guided Pruning for Visual Autoregressive Models [98.72926158261937]
  We propose a training-free token pruning framework for Visual AutoRegressive models.<n>We employ a lightweight high-pass filter to capture local texture details, while leveraging Principal Component Analysis (PCA) to preserve global structural information.<n>To maintain valid next-scale prediction under sparse tokens, we introduce a nearest neighbor feature propagation strategy.
  arXiv  Detail & Related papers  (2026-03-02T11:35:05Z)
• Chain-of-Image Generation: Toward Monitorable and Controllable Image Generation [7.987662261007762]
  Chain-of-Image Generation (CoIG) framework reframes image generation as a sequential, semantic process analogous to how humans create art.<n>Our experimental results indicate that CoIG substantially enhances quantitative monitorability while achieving competitive robustness compared to established baseline models.
  arXiv  Detail & Related papers  (2025-12-09T14:35:12Z)
• GloTok: Global Perspective Tokenizer for Image Reconstruction and Generation [51.95701097588426]
  We introduce a Global Perspective Tokenizer (GloTok) to model a more uniform semantic distribution of tokenized features.<n>A residual learning module is proposed to recover the fine-grained details to minimize the reconstruction error caused by quantization.<n>Experiments on the standard ImageNet-1k benchmark clearly show that our proposed method achieves state-of-the-art reconstruction performance and generation quality.
  arXiv  Detail & Related papers  (2025-11-18T06:40:26Z)
• IAR2: Improving Autoregressive Visual Generation with Semantic-Detail Associated Token Prediction [77.06211178777939]
  IAR2 is an advanced autoregressive framework that enables a hierarchical semantic-detail synthesis process.<n>We show that IAR2 sets a new state-of-the-art for autoregressive image generation, achieving a FID of 1.50 on ImageNet.
  arXiv  Detail & Related papers  (2025-10-08T12:08:21Z)
• Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generation [54.588082888166504]
  We present Mogao, a unified framework that enables interleaved multi-modal generation through a causal approach.<n>Mogoo integrates a set of key technical improvements in architecture design, including a deep-fusion design, dual vision encoders, interleaved rotary position embeddings, and multi-modal classifier-free guidance.<n>Experiments show that Mogao achieves state-of-the-art performance in multi-modal understanding and text-to-image generation, but also excels in producing high-quality, coherent interleaved outputs.
  arXiv  Detail & Related papers  (2025-05-08T17:58:57Z)
• Boosting Generative Image Modeling via Joint Image-Feature Synthesis [15.133906625258797]
  We introduce a novel generative image modeling framework that seamlessly bridges the gap by leveraging a diffusion model to jointly model low-level image latents.<n>Our latent-semantic diffusion approach learns to generate coherent image-feature pairs from pure noise.<n>By eliminating the need for complex distillation objectives, our unified design simplifies training and unlocks a powerful new inference strategy: Representation Guidance.
  arXiv  Detail & Related papers  (2025-04-22T17:41:42Z)
• 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)
• Nested Diffusion Models Using Hierarchical Latent Priors [23.605302440082994]
  We introduce nested diffusion models, an efficient and powerful hierarchical generative framework.<n>Our approach employs a series of diffusion models to progressively generate latent variables at different semantic levels.<n>To construct these latent variables, we leverage a pre-trained visual encoder, which learns strong semantic visual representations.
  arXiv  Detail & Related papers  (2024-12-08T16:13:39Z)

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.