Announcement_1
We presented our paper Understanding Reward Hacking in Text-to-Image Reinforcement Learning at CVPR 2026, which uncovers how different rewards lead to exploitations in T2I RL and mitigation methods; code is available on Github.
We presented our paper Understanding Reward Hacking in Text-to-Image Reinforcement Learning at CVPR 2026, which uncovers how different rewards lead to exploitations in T2I RL and mitigation methods; code is available on Github.