Recent breakthroughs in instruction-based image editing have captured significant attention, as models are now capable of handling real-world editing demands with the practicality required by everyday users. However, editing models trained primarily for single-turn edits often break down in multi-turn editing--the natural interactive setting where a user iteratively refines an image based on the model's own previous outputs.
arXiv:2607. 03748v1 Announce Type: new Abstract: Unified multi-modal models (UMMs) have shown promising interleaved text-image reasoning capabilities, yet effectively optimizing such multi-turn generation via reinforcement learning (RL) remains an open challenge.
By Zican Hu, Xuyang Hu, Yiming Liu, Zuwei Long, Wei Liu, Yunzhuo Hao, Jiawei Gu, Linjie Li, Yu Cheng, Zhenhong Sun, Weibo Gu, Xing Sun, Zhi Wang
arXiv:2606. 11209v1 Announce Type: cross Abstract: Visual question answering increasingly requires multi-step reasoning.
By Jingpei Wu, Xiao Han, Weixiang Shen, Boer Zhang, Zifeng Ding, Volker Tresp
arXiv:2606. 27608v1 Announce Type: cross Abstract: We present Qwen-Image-2.
By Yixian Xu, Kaiyuan Gao, Yuxiang Chen, Yilei Chen, Zecheng Tang, Zihao Liu, Zikai Zhou, Deqing Li, Hao Meng, Kuan Cao, Jiahao Li, Jie Zhang, Liang Peng, Lihan Jiang, Ningyuan Tang, Shengming Yin, Tianhe Wu, Xiaoyue Chen, Yan Shu, Yanran Zhang, Yi Wang, Yu Wu, Yujia Wu, Zekai Zhang, Zhendong Wang, Xiao Xu, Kun Yan, Chenfei Wu
arXiv:2510. 05592v2 Announce Type: replace Abstract: Outcome-driven reinforcement learning has advanced reasoning in large language models (LLMs), but prevailing tool-augmented approaches train a single, monolithic policy that interleaves thoughts and tool calls under full context; this scales poorly with long horizons and diverse tools and generalizes weakly to new scenarios.
By Zhuofeng Li, Haoxiang Zhang, Seungju Han, Sheng Liu, Jianwen Xie, Yu Zhang, Yejin Choi, James Zou, Pan Lu
arXiv:2610.16593v1 Announce Type: new
Abstract: Reinforcement learning with verifiable rewards (RLVR) implemented with Group Relative Policy Optimization (GRPO) has driven substantial progress in tra...
By Haifeng Qian, David Mosallanezhad, Christian Munley, Adithya Renduchintala, Oleksii Kuchaiev
PrismGPT is a Vision‑Language Model that generates structured, region‑aware photo‑editing plans from a single image, without relying on commercial black‑box tools. It learns to diagnose aesthetic issues globally and locally while predicting precise editing parameters, using proxy‑guided learning with operation decomposition and region‑aware aesthetic ranking to bootstrap the model. A competence‑based dynamic scheduler shifts training focus from proxy tasks to the main editing task as skills improve, and all reasoning traces for fine‑tuning are self‑synthesized by the model itself. Experiments on MIT‑Adobe FiveK and a new professionally retouched benchmark, SPIRE, show PrismGPT achieves state‑of‑the‑art results using only about 6% of the training data required by previous methods.
By Ke Zhao, Hue Nguyen, Abhijith Punnappurath, Zhongling Wang, Iqbal Mohomed, Michael S. Brown
arXiv:2606. 14792v1 Announce Type: cross Abstract: RL-based post-training has been widely adopted to enable interleaved visual and textual reasoning in unified multimodal models capable of both text and image generation.
By Yoonjeon Kim, Yuhta Takida, Chieh-Hsin Lai, Eunho Yang, Yuki Mitsufuji
arXiv:2601. 03555v3 Announce Type: replace Abstract: Training reliable tool-augmented agents remains a significant challenge, largely due to the difficulty of credit assignment in multi-step reasoning.
By Yuxuan Jiang, Francis Ferraro
arXiv:2604.13491v4 Announce Type: replace
Abstract: With the rapid progress of Multimodal Large Language Models (MLLMs), unified MLLMs that jointly perform image understanding and generation have adv...
By Yongjin Kim, Yoonjin Oh, Yerin Kim, Hyomin Kim, Jeeyoung Yun, Yujung Heo, Minjun Kim, Sungwoong Kim
The paper introduces Stepwise Marginal Information Gain (MIG), an intrinsic process reward that evaluates how each reasoning step of a large language model (LLM) or vision-language model (VLM) improves the likelihood of the reference answer. MIG rewards only new likelihood maxima, preventing duplicate credit, and is combined with outcome, format, and self‑distillation objectives to guide training. Experiments on eight benchmarks show that this method outperforms outcome‑only reinforcement learning and improves accuracy by up to 4.8 points over binary‑reward training, including a 12.6‑point gain on MathVerse and a 12.9‑point advantage on vision‑language transfer at 7B parameters.
By Xiangwei Wang, Wei Wang, Ken Chen, Nanduni Nimalsiri, Sachith Seneviratne, Saman Halgamuge
arXiv:2605. 06094v5 Announce Type: replace-cross Abstract: Training VideoLLMs for complex reasoning remains challenging due to sparse sequence level rewards and the lack of fine grained credit assignment over long, temporally grounded reasoning trajectories.
By Hao Lin, Kunyang Lv, Xu Jiang, Jingqi Tian, Zhongjing Du, Jiayu Ding, Qiaoman Zhang, Hongbo Jin