arXiv:2602. 07533v2 Announce Type: replace Abstract: Reward models are critical for reinforcement learning from human feedback, as they determine the alignment quality and reliability of generative models.
By Yankai Yang, Yancheng Long, Hongyang Wei, Wei Chen, Tianke Zhang, Kaiyu Jiang, Haonan Fan, Changyi Liu, Jiankang Chen, Kaiyu Tang, Bin Wen, Fan Yang, Tingting Gao, Han Li, Shuo Yang
The paper presents a post‑training approach for text‑to‑image models that combines a preference reward, trained on large human preference data, with rubric‑based rewards that assess prompt faithfulness and other desirable traits. The authors show that a simple reward composition strategy outperforms a naive weighted average, leading to significant Elo gains on the Arena leaderboard for models like Flux2dev and Ideogram‑4. They also release Arena‑T2I‑Training, a 1K subset of data to aid reproducible research in post‑training.
By Yuanhao Ban, I-Hung Hsu, Anastasios Angelopoulos, Wei-Lin Chiang, Ion Stoica, Cho-Jui Hsieh
arXiv:2605.07872v2 Announce Type: replace-cross
Abstract: Multimodal reward models have advanced substantially in text and image domains, yet progress in video understanding reward modeling remains s...
By Yuancheng Wei, Linli Yao, Lei Li, Haojie Zhang, Hao Zhou, Fandong Meng, Xu Sun
arXiv:2609.35942v1 Announce Type: new
Abstract: Recent work in visual question answering has shown that vision-language models can exhibit strong reasoning capabilities by translating visual inputs i...
By Ting-Chih Chen, Emile van Krieken, Shujian Yu, Filip Ilievski
Recent advances in multimodal generative models have enabled instruction-based image generation to move beyond semantic manipulation to knowledge-driven visual reasoning. However, these methods focus on explicit commonsense reasoning, shallow causal understanding, and direct knowledge recall, failing at knowledge-intensive generation.
The paper introduces RECAP, a training method that enhances vision‑language models by incorporating temporally localized reactivation of image evidence—called visual revisit—into the reinforcement learning process. Visual revisit peaks are shown to predict correctness and causally improve performance; masking them hurts accuracy more than masking non‑peaks, while adding revisit peaks to failed reasoning partially restores correct answers. RECAP applies revisit‑conditioned advantage estimation, dynamic discounting, and gated value prediction to propagate final rewards through visually important reasoning steps, achieving significant gains on HallusionBench and other benchmarks without extra rewards or inference‑time changes.
By Zhaolu Kang, Tailong Luo, Chenxin Li, Yingjie He, Zhenyu Yu, Fengyu Zhou, Jiachen Qian, Lei Wei, Shuang Chen, Jiachen Li, Eric Hanchen Jiang, Rongchao Zhang, Zhengtao Yao, Hoi Leong Lee, Guansu Wang, Kaiyue Zhou