WISE
Emerging5papers using it
2026first seen
The WISE dataset/benchmark is used to evaluate the reasoning capabilities of text-to-image diffusion models by providing diverse textual prompts and their corresponding visual representations.
Papers using WISE (5)
- Mural: Transferring LLM knowledge to image generation via Mixture-of-TransformersUniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated SupervisionThink-Then-Generate: Reasoning-Aware Text-to-Image Diffusion with LLM EncodersShow, Don't Tell: Morphing Latent Reasoning into Image GenerationAlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable Reward