Back to home

Tag

text-to-image

3 articles

AlphaGRPO teaches multimodal models to self-correct
Research/May 13

AlphaGRPO teaches multimodal models to self-correct

AlphaGRPO adds verifiable reward signals to multimodal models so they can reason, refine outputs, and improve generation without cold-start training.

Normalizing Trajectory Models for 4-Step Generation
Research/May 11

Normalizing Trajectory Models for 4-Step Generation

NTM turns few-step generation into an exact-likelihood flow model and hits strong text-to-image results in four steps.

Making AI Art Less Boring: Repulsion Tricks for Diverse Diffusion Images
Research/Mar 31

Making AI Art Less Boring: Repulsion Tricks for Diverse Diffusion Images

Researchers introduce an on-the-fly repulsion mechanism in diffusion transformers that prevents mode collapse, generating more creative and diverse text-to-image results.