Element-Aware Group Learning for E-Commerce Image Generation

• URL: http://arxiv.org/abs/2608.00584v1
• Date: Sat, 01 Aug 2026 10:45:03 GMT
• Title: Element-Aware Group Learning for E-Commerce Image Generation
• Abstract summary: Vision-language models (VLMs) can generate image-editing prompts from product images and metadata.<n>Further improving their prompt-writing capabilities requires post-training with feedback from the generated images.<n>E-commerce images produce higher-quality e-commerce images than competitive VLM prompt-writing baselines.
• Score: 18.989839742726975
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advances in image generation and editing have made prompt quality a key bottleneck for e-commerce creatives. Vision-language models (VLMs) can generate image-editing prompts from product images and metadata, but further improving their prompt-writing capabilities requires post-training with feedback from the generated images. Group Relative Policy Optimization (GRPO) is a natural framework for such outcome-level reward optimization. However, it assigns credit only at the full-prompt level, even though image quality often depends on specific design elements such as composition, background, and the presentation of selling points. Existing fine-grained credit assignment methods typically require step-level supervision or learned critics. To address this, we propose EAGLE-GRPO (Element-Aware Group Learning for E-Commerce Image Generation), which decomposes the group-centered reward over predefined elements. We cast element-level credit assignment as a kernel ridge regression problem and derive a closed-form solution, without additional rollouts or separate credit-assignment models. This yields interpretable per-element advantages and more precise policy updates. Experiments show that EAGLE-GRPO sustains performance gains over more training steps before plateauing and generates prompts that produce higher-quality e-commerce images than competitive VLM prompt-writing baselines.

Related papers

• Sketch Then Paint: Hierarchical Reinforcement Learning for Diffusion Multi-Modal Large Language Models [52.40742159500277]
  We show how to optimize Diffusion Multi-Modal Large Language Models (dMLLMs) through reinforcement learning (RL)<n>Our approach features a Sketch-Then-Paint training scheme that organizes updates into three distinct stages: global, structure, and refinement.<n> Experiments using two popular dMLLM backbones, MMaDA and Lumina-DiMOO, demonstrate substantial gains on the GenEval and DPG benchmarks.
  arXiv  Detail & Related papers  (2026-05-16T06:59:54Z)
• ICG: Improving Cover Image Generation via MLLM-based Prompting and Personalized Preference Alignment [70.19758313256503]
  We propose ICG, a framework that integrates MLLM-based prompting with personalized preference alignment to generate contextually relevant covers.<n>ICG extracts semantic features from item titles and reference images via meta tokens, refines them with user embeddings, and injects the resulting personalized context into the diffusion model.<n>Experiments demonstrate that ICG significantly improves image quality, semantic fidelity, and personalization, leading to stronger user appeal and offline recommendation accuracy.
  arXiv  Detail & Related papers  (2026-04-08T06:36:54Z)
• Image-POSER: Reflective RL for Multi-Expert Image Generation and Editing [16.943575863059607]
  Image-POSER orchestrates a diverse registry of pretrained text-to-image and image-to-image experts.<n>It handles long-form prompts end-to-end through dynamic task decomposition.<n>It is consistently preferred in human evaluations.
  arXiv  Detail & Related papers  (2025-11-15T03:15:34Z)
• Bridging Modality Gaps in e-Commerce Products via Vision-Language Alignment [15.068156309599662]
  We propose optimized preference-based AI for listings (OPAL) to generate high-quality item descriptions from images.<n>OPAL bridges the gap between visual and textual modalities, delivering richer, more accurate, and more consistent item descriptions.<n>This work advances automated listing optimization and supports scalable, high-quality content generation in e-commerce platforms.
  arXiv  Detail & Related papers  (2025-08-13T18:22:53Z)
• CAL-RAG: Retrieval-Augmented Multi-Agent Generation for Content-Aware Layout Design [6.830055289299306]
  CAL-RAG is a retrieval-augmented, agentic framework for content-aware layout generation.<n>We implement our framework using LangGraph and evaluate it on a benchmark rich in semantic variability.<n>Results demonstrate that combining retrieval augmentation with agentic multi-step reasoning yields a scalable, interpretable, and high-fidelity solution.
  arXiv  Detail & Related papers  (2025-06-27T06:09:56Z)
• 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)
• CTR-Driven Advertising Image Generation with Multimodal Large Language Models [53.40005544344148]
  We explore the use of Multimodal Large Language Models (MLLMs) for generating advertising images by optimizing for Click-Through Rate (CTR) as the primary objective.<n>To further improve the CTR of generated images, we propose a novel reward model to fine-tune pre-trained MLLMs through Reinforcement Learning (RL)<n>Our method achieves state-of-the-art performance in both online and offline metrics.
  arXiv  Detail & Related papers  (2025-02-05T09:06:02Z)
• Ranking-aware adapter for text-driven image ordering with CLIP [76.80965830448781]
  We propose an effective yet efficient approach that reframes the CLIP model into a learning-to-rank task.<n>Our approach incorporates learnable prompts to adapt to new instructions for ranking purposes.<n>Our ranking-aware adapter consistently outperforms fine-tuned CLIPs on various tasks.
  arXiv  Detail & Related papers  (2024-12-09T18:51:05Z)
• Automatic Generation of Product-Image Sequence in E-commerce [46.06263129000091]
  Multi-modality Unified Imagesequence (MUIsC) is able to simultaneously detect all categories through learning rule violations. By Dec 2021, our AGPIS framework has generated high-standard images for about 1.5 million products and achieves 13.6% in reject rate.
  arXiv  Detail & Related papers  (2022-06-26T23:38:42Z)

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.