Research map / Image generation / Text-to-image diffusion
SPRO: Improving Image Generation via Self-Play
Ritika Jha, Aanisha Bhattacharyya, Yaman Kumar Singla, Rajiv Ratn Shah, Changyou Chen, Balaji Krishnamurthy
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
The paper proposes SPRO, a self-play approach that leverages vision-language model reasoning to align diffusion image generators with human preferences without large-scale human annotations.
Problem
Aligning diffusion image generation models with nuanced human preferences (aesthetics, engagement, subjective appeal) is hard because large-scale human preference annotations are scarce, expensive, and limited in diversity.
Approach
Leverages the reasoning capabilities of vision-language models to supply preference signals for diffusion model alignment via self-play, instead of collecting human annotations. Abstract is truncated, so details beyond this are not stated.
Closest papers by meaning
- Multimodal Large Language Models Make Text-to-Image Generative Models Align Better (NeurIPS 2024 · similarity 0.89)
- Calibrated Self-Rewarding Vision Language Models (NeurIPS 2024 · similarity 0.88)
- DreamAlign: Dynamic Text-to-3D Optimization with Human Preference Alignment (AAAI 2025 · similarity 0.87)
- Self-Play Fine-tuning of Diffusion Models for Text-to-image Generation (NeurIPS 2024 · similarity 0.87)
- Devil is in the Detail: Towards Injecting Fine Details of Image Prompt in Image Generation via Conflict-free Guidance and Stratified Attention (CVPR 2025 · similarity 0.87)
- Focus-N-Fix: Region-Aware Fine-Tuning for Text-to-Image Generation (CVPR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
