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.
By Zijian Kan, Wei Wang, Long Luo, Bing Zhao, Xuan Ren, Weixu Qiao, Wenbo Li, Hu Wei, Lin Qu
The paper introduces a post‑training approach that enables a single inference process to transition from text reasoning to image synthesis, eliminating the need for explicit modality switching. Using the 14B BAGEL model, the authors demonstrate that targeted post‑training data and reward‑weighted training improve multimodal image generation across four independent T2I benchmarks. The study highlights the benefits of joint text‑image generation and strategic data selection for enhancing T2I performance.
By Jiahui Chen, Philippe Hansen-Estruch, Xiaochuang Han, Yushi Hu, Emily Dinan, Amita Kamath, Michal Drozdzal, Reyhane Askari-Hemmat, Luke Zettlemoyer, Marjan Ghazvininejad
arXiv:2412. 10362v2 Announce Type: replace Abstract: Low-rank adapters (LoRA) enable finetuning of large models with only a small number of parameters.
By Piotr Teterwak, Kate Saenko, Bryan A. Plummer, Ser-Nam Lim
arXiv:2607. 02291v1 Announce Type: new Abstract: Conventional reinforcement learning strategies for visual generation typically employ sample-wise reward functions, yet this practice frequently results in reward hacking that degrades image diversity and introduces visual anomalies.
By Ruihang Li, Mengde Xu, Shuyang Gu, Leigang Qu, Fuli Feng, Han Hu, Wenjie Wang
The paper introduces PRISM, a Compositional Reward Model framework that decomposes image quality into multiple verifier‑grounded stages for conditional medical image generation. By assigning distinct rewards for fine‑to‑coarse properties—such as intensity, texture, structural alignment, and semantic fidelity—and combining them via a Hierarchical Constrained Propagation mechanism, PRISM addresses shortcomings of single‑scalar reward approaches. Experiments on PanNuke, CeDeM, and ISIC datasets show that data generated with PRISM improves downstream model performance, achieving higher mDice, lower MRE, and increased F1 scores compared to baseline methods.
By Aayush Kumar Tyagi, Prathosh A. P., Mausam
Learning-State-Aware Dynamic Generative Data Augmentation on Small-Scale Datasets proposes LSADA, a method that constructs a learning state for each sample based on its loss and loss‑decrease rate to determine a sample‑specific augmentation strength. LSADA also introduces a decoupled data augmentation and diffusion fusion strategy that applies strength‑controlled transformations to class‑relevant regions while generating diverse class‑irrelevant regions, progressively fusing them to enhance image diversity while preserving class semantics. Experiments on nine public datasets demonstrate that LSADA outperforms the current state‑of‑the‑art dynamic GDA method by an average of 4.5% on six natural image datasets and 2.5% on three medical image datasets.
By Ting Xiang, Chenxi Deng, Jinhui Zhao, Bingting Jiang, Ke Zhang, Changjian Chen, Zhuo Tang
arXiv:2511.22232v2 Announce Type: replace-cross
Abstract: Multimodal large language models (MLLMs) are increasingly capable in medical imaging, yet most focus on single-image settings. Clinical inter...
By Zhen Chen, Yihang Fu, Rong Zhou, Serina Applebaum, Min Kyu Kim, Aidan Gilson, Morten Lee, Salahudeen Mirza, Gabriel Madera, Mauro Giuffre, Yuanting Pan, Roy Jiang, Hyunjae Kim, Hua Xu, Qingyu Chen
arXiv:2603. 23086v2 Announce Type: replace Abstract: Autoregressive (AR) models are highly effective for image generation, yet their standard maximum-likelihood estimation training lacks direct optimization for sample quality and diversity.
By Orhun Bugra Baran, Melih Kandemir, Ramazan Gokberk Cinbis
arXiv:2607. 02637v1 Announce Type: cross Abstract: Recent generative models can produce high-quality synthetic images, offering scalable training training data for data-hungry models.
By Disheng Liu, Tuo Liang, Chaoda Song, Yu Yin
SynerMedGen is a unified framework that aligns medical multimodal understanding with generation tasks through task alignment. It introduces three generation‑aligned understanding tasks and a two‑stage training strategy that transfers representations learned during understanding to medical image synthesis. The model achieves strong zero‑shot performance on 22 synthesis tasks and outperforms state‑of‑the‑art specialized and unified models when combined with generation training, supported by a new 1M‑sample SynerMed dataset.
By Weiren Zhao, Yi Dong, Cheng Chen
arXiv:2609.37372v1 Announce Type: new
Abstract: Visual reward models are essential for evaluating and improving visual generation models, yet existing approaches typically map task conditions and can...
By Xuehai Bai, Zhenchen Tang, Yang Shi, Dianyi Wang, Tengfei Liu, Wanshun Su, Xuanyu Zhu, Ruohui Wang, Haiwen Diao, Haotian Wang, Xiaoling Gu, Yuanxing Zhang
arXiv:2509. 24900v2 Announce Type: replace-cross Abstract: The performance of unified multimodal models for image generation and editing is fundamentally constrained by the quality and comprehensiveness of their training data.
By Zhihong Chen, Xuehai Bai, Yang Shi, Chaoyou Fu, Huanyu Zhang, Haotian Wang, Xiaoyan Sun, Zhang Zhang, Liang Wang, Yuanxing Zhang, Pengfei Wan, Yi-Fan Zhang