Problem
Research questions and friction points this paper is trying to address.
news image generation
image synthesis
text-to-image
media generation
headline-based image creation
A Test-time Actor-Critic Approach to News Images Generation
🤖 AI Summary
This work addresses the task of generating semantically consistent images from news headlines by proposing ACIG, a test-time, model-agnostic Actor-Critic image generation method. ACIG introduces the Actor-Critic paradigm from reinforcement learning into text-to-image synthesis for the first time, iteratively refining textual prompts through a self-feedback loop: the Actor proposes prompt modifications, while the Critic evaluates the semantic alignment and quality of the resulting images and provides feedback to guide subsequent refinements. Notably, this optimization occurs entirely at inference time without requiring additional training. ACIG is flexibly compatible with existing text-to-image models and achieved top performance on the official leaderboard of the MediaEval NewsImages 2026 challenge, significantly enhancing the semantic consistency between generated images and their corresponding news content.
📝 Abstract
This paper introduces the CERTH-ITI solution for the MediaEval NewsImages 2026 challenge, which focuses on generating images related to news headlines. Inspired by the Actor-Critic paradigm in reinforcement learning, we present a test-time, model-agnostic Actor-Critic Image Generation approach (ACIG). ACIG generates prompts for image creation, produces the images, evaluates the generated results, and if needed refines the image generation prompts accordingly in a feedback loop. ACIG achieved the best results in the NewsImages 2026 challenge, according to the challenge's leaderboard.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Actor-Critic
test-time adaptation
prompt refinement
image generation
model-agnostic
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
