arXiv Computer Vision
Understanding Reward Hacking in Text-to-Image Reinforcement Learning
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv AI
Jul 20
Debiasing Text-to-Image Evaluation via Implicit Cultural Alignment Reward Modeling
arXiv:2607. 15740v1 Announce Type: cross Abstract: As Text-to-Image (T2I) systems rapidly advance, evaluating the cultural authenticity of synthesized content has become increasingly important for fair and trustworthy generative AI.
arXiv Computer Vision
Aug 25
Can We Perform Online RL for Image Editing without Editing Rewards?
arXiv:2608.22780v1 Announce Type: new Abstract: Reinforcement learning (RL) enables direct preference optimization for image editing through editing-specific rewards, which remain less developed due...
arXiv AI
Jul 13
Multimodal Reward Hacking in Reinforcement Learning
arXiv:2607. 09492v1 Announce Type: new Abstract: Reinforcement learning (RL) is increasingly used to align multimodal large language models (MLLMs), but higher rewards do not always imply better task performance.
arXiv AI
Jul 2
Right in the Right Way: LM Training with Verifiable Rewards and Human Demonstrations
arXiv:2607. 01181v1 Announce Type: cross Abstract: RL with verifiable rewards (RLVR) has emerged as a powerful paradigm for training LMs on tasks with well-defined success metrics, such as code generation and mathematical reasoning.
arXiv Machine Learning
Jun 3
HARVE: Hacking-Aware Reward-Head Vector Editing for Robust Reward Models
arXiv:2606. 03131v1 Announce Type: new Abstract: Reward models are central to large language model (LLM) alignment, but they remain vulnerable to reward hacking.
arXiv Computer Vision
Aug 28
RubricRM: Generative Reward Modeling via Dynamic Rubrics for Image Generation and Editing
RubricRM introduces a pairwise generative reward modeling framework that generates an input‑specific rubric—comprising evaluation dimensions, weights, and scoring criteria—to score candidate images. The method is trained in two stages: supervised fine‑tuning to learn the rubric‑based scoring paradigm and GRPO to refine dimension‑level rewards. Experiments on text‑to‑image generation and instruction‑based image editing benchmarks demonstrate that RubricRM outperforms existing specialized reward models and competes with strong proprietary MLLM judges while using smaller backbones.