Paper Notes
Search
搜索
暗色模式
亮色模式
探索
标签: reward-hacking
此标签下有6条笔记。
2026年5月
Do Less, Achieve More: Do We Need Every-Step Optimization for RL Fine-tuning of Diffusion Models?
2026年5月
E²PO: Embedding-perturbed Exploration Preference Optimization for Flow Models
2026年5月
Imperfect World Models are Exploitable
2026年5月
Reward Hacking in Rubric-Based Reinforcement Learning
2025年11月
The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generation
2025年8月
Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning