MIRA: Towards Mitigating Reward Hacking in Inference-Time Alignment of T2I Diffusion Models

MIRA: Towards Mitigating Reward Hacking in Inference-Time Alignment of T2I Diffusion Models

2 October 2025

Anirudh Thatipelli

Souradip Chakraborty

Anit Kumar Sahu

Amrit Singh Bedi

ArXiv (abs)PDF HTML

Papers citing "MIRA: Towards Mitigating Reward Hacking in Inference-Time Alignment of T2I Diffusion Models"

Title
No papers found