VinciCoder is a unified framework for multimodal code generation that addresses the limitations of single-task models by training on a large-scale curated corpus of 1.3 M direct generation pairs and 300 k visual‑refinement tasks. It introduces a coarse‑to‑fine Visual Reinforcement Learning (ViRL) approach that uses visual similarity across multi‑scale patches to provide an implementation‑agnostic reward, improving alignment between rendered outputs and input visuals. Experiments on diverse benchmarks show VinciCoder outperforms existing methods, and ablation studies confirm the effectiveness of ViRL.
By Xuanle Zhao, Deyang Jiang, Zhixiong Zeng, Lei Chen, Haoyue Yang, Haibo Qiu, Jing Huang, Yufeng Zhong, Liming Zheng, Yilin Cao, Lin Ma
The paper introduces Reflection-Aware GRPO (RA‑GRPO), a reinforcement‑learning framework that aligns diffusion generative models with human preferences. It uses Diffusion Reflection to correct intermediate sampling paths by reversing the diffusion process, and Counterfactual Path Synthesis to embed these corrected trajectories into the policy, avoiding extra inference cost. Experiments on text‑to‑image and text‑to‑video models show RA‑GRPO outperforms existing methods, reducing reward hacking and improving generalization while remaining architecture‑agnostic.
By Junlong Wu, Jiuzhou Lin, Jia Sun, Boheng Zhang, Huaiqing Wang, Dewen Fan, Houde Liu, Qianqian Gan, Fan Yang, Tingting Gao
The paper introduces V‑Rubrics, a reinforcement‑learning framework that evaluates vision‑language model responses by breaking them into atomic propositions and scoring them on Visual Faithfulness, Reasoning Consistency, and Instruction Following. Using a fine‑tuned Qwen3‑VL‑8B‑Instruct model and a newly created 50K‑example V‑Rubrics dataset, the authors demonstrate that rubric‑based GRPO outperforms both a shared SFT baseline and an answer‑only GRPO, especially on knowledge‑oriented and visually grounded reasoning tasks.
By Shulin Tian, Minglun Li, Yuhao Dong, Hao Ding, Jiarui Yao, Haiwen Diao, Jingkang Yang, Hongyuan Zhu, Ziwei Liu
arXiv:2511. 19436v2 Announce Type: replace-cross Abstract: Existing Video Detailed Captioning (VDC) methods predominantly rely on costly human annotations or distillation from powerful proprietary models, creating a dependency on external supervision.
By Qiang Wang, Xinyuan Gao, Yuhang He, Jizhou Han, Jiangyang Li, SongLin Dong, Zhiheng Ma, Yihong Gong
arXiv:2607. 00796v1 Announce Type: new Abstract: Visual Reinforcement Learning (VRL) has achieved considerable success in solving control tasks.
By Jinwen Wang, Youfang Lin, Xiaobo Hu, Qian Xu, Shuo Wang, Zhuo Chen, Kai Lv
arXiv:2606. 10334v1 Announce Type: new Abstract: Code-generating large language models (LLMs) increasingly produce visual artifacts such as charts, web pages, and slides by writing programs that are executed by non-differentiable renderers, committing to code before observing the render.
By Haoyu Dong
The paper introduces SCoRE, an agentic framework for Visual Retrieval-Augmented Generation that explicitly selects and consolidates visual evidence before generating answers. It addresses two key challenges: sparse, scattered evidence and noisy exploration trajectories that obscure reasoning. By maintaining a textual ledger of relevant observations and reloading original images for a logical evidence sequence, SCoRE decouples reasoning from exploration and enforces strict visual grounding, with training that rewards evidence coverage, compactness, and answer correctness.
By Yucheng Shen, Lingyong Yan, Jiulong Wu, Shuaiqiang Wang, Jianmin WU, Dawei Yin, Min Cao
arXiv:2604. 02794v2 Announce Type: replace Abstract: Charts are ubiquitous in scientific and financial literature for presenting structured data.
By Situo Zhang, Yifan Zhang, Zichen Zhu, Da Ma, Lei Pan, Danyang Zhang, Zihan Zhao, Lu Chen, Kai Yu
The paper introduces Objective-aware Trajectory Credit Assignment (OTCA), a framework that refines reinforcement learning for diffusion-based visual generation. OTCA decomposes credit across denoising steps and allocates multiple reward signals adaptively, addressing the coarse, uniform reward assignment of existing GRPO pipelines. Experiments demonstrate that OTCA consistently enhances image and video generation quality across various metrics.
By Rui Li, Ke Hao, Yuanzhi Liang, Haibin Huang, Chi Zhang, Yun Gu, Xuelong Li
arXiv:2606. 17678v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) integrate strong text reasoning with visual inputs, yet their responses can be inconsistent with the underlying images, indicating ineffective utilization of visual evidence during inference.
By Yilian Liu, Sicong Leng, Guoshun Nan, Junyi Zhu, Jiayu Huang, Minghao Sun, Xuancheng Zhu, Yisong Chen, Zexian Wei, Xiaofeng Tao
arXiv:2606. 27922v1 Announce Type: cross Abstract: Current multimodal reflection mechanisms for long video understanding predominantly rely on closed-loop self-reflection within internal parameters.
By Shuimu Chen, Yuteng Chen, Yuanshen Guan, Zebang Cheng, Zeyu Zhang, Shengqian Qin, Bin Xia, Jiaran Li, Wenming Yang, Fei Ma
arXiv:2608.22429v1 Announce Type: new
Abstract: Multimodal Large Language Models (MLLMs) capable of thinking with images often rely on external tools for fine-grained perception. However, this relian...
By Changjiang Jiang, Qiannian Zhao, Lei Xin, Jinxiang Xie, Preslav Nakov, Zhuohan Xie