#GFlowNet
2 related articles
·2 min
DOGS Framework: Reshaping AI Logo Generation Through Design Space Sampling
The DOGS framework (arXiv:2610.10760) reframes AI Logo generation as structured design-space sampling using a GFlowNet sampler with recognizability, aesthetics, and originality rewards — outperforming nine baselines while building in trademark infringement avoidance.
Read more →
·2 min
GFlowNet Breaks Mode Collapse: Generating Diverse Expert Dialogue Synthetic Data
A new arXiv paper proposes using GFlowNet to solve mode collapse in synthetic data generation, achieving better fidelity, mode coverage, and authenticity in tutoring and emotional support dialogues for LLM post-training.
Read more →