Fetching the paper…
Reading the bibliography…
This work revisits the dominant supervised fine-tuning (SFT) then reinforcement learning (RL) paradigm for training Large Vision-Language Models (LVLMs), and reveals a key finding: SFT can significantly undermine subsequent RL by inducing ``pseudo reasoning paths'' imitated from expert models.
Clevr: A diagnostic dataset for compositional language and elementary visual reasoning
Justin Johnson, Bharath Hariharan, Laurens Van Der Maaten, Li Fei-Fei, C Lawrence Zitnick, and Ross Girshick · 2017
Earlier work this paper cites.
Proximal policy optimization algorithms
John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov · 2017
Earlier work this paper cites.
Vizwiz grand challenge: Answering visual questions from blind people
Danna Gurari, Qing Li, Abigale J Stangl, Anhong Guo, Chi Lin, Kristen Grauman, Jiebo Luo, and Jeffrey P Bigham · 2018
Earlier work this paper cites.
Language models are few-shot learners
Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al · 2020
Earlier work this paper cites.
Docvqa: A dataset for vqa on document images
Minesh Mathew, Dimosthenis Karatzas, and CV Jawahar · 2021
Earlier work this paper cites.
Clevr-math: A dataset for compositional language, visual and mathematical reasoning
Adam Dahlgren Lindström and Savitha Sam Abraham · 2022
Earlier work this paper cites.
Chain-of-thought prompting elicits reasoning in large language models
Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al · 2022
Earlier work this paper cites.
Helping or herding? reward model ensembles mitigate but do not eliminate reward hacking
Jacob Eisenstein, Chirag Nagpal, Alekh Agarwal, Ahmad Beirami, Alex D’Amour, DJ Dvijotham, Adam Fisch, Katherine Heller, Stephen Pfohl, Deepak Ramachandran, et al · 2023
Earlier work this paper cites.
G-llava: Solving geometric problem with multi-modal large language model
Jiahui Gao, Renjie Pi, Jipeng Zhang, Jiacheng Ye, Wanjun Zhong, Yufei Wang, Lanqing Hong, Jianhua Han, Hang Xu, Zhenguo Li, et al · 2023
Earlier work this paper cites.
Understanding the effects of rlhf on llm generalisation and diversity
Robert Kirk, Ishita Mediratta, Christoforos Nalmpantis, Jelena Luketina, Eric Hambro, Edward Grefenstette, and Roberta Raileanu · 2023
Earlier work this paper cites.
Reward design with language models
Minae Kwon, Sang Michael Xie, Kalesha Bullard, and Dorsa Sadigh · 2023
Earlier work this paper cites.
Perplexed by perplexity: Perplexity-based data pruning with small reference models
Zachary Ankner, Cody Blakeney, Kartik Sreenivasan, Max Marion, Matthew L Leavitt, and Mansheej Paul · 2024
Earlier work this paper cites.
Vlmevalkit: An open-source toolkit for evaluating large multi-modality models
Haodong Duan, Junming Yang, Yuxuan Qiao, Xinyu Fang, Lin Chen, Yuan Liu, Xiaoyi Dong, Yuhang Zang, Pan Zhang, Jiaqi Wang, et al · 2024
Earlier work this paper cites.
Mme: A comprehensive evaluation benchmark for multimodal large language models, 2024
Chaoyou Fu, Peixian Chen, Yunhang Shen, Yulei Qin, Mengdan Zhang, Xu Lin, Jinrui Yang, Xiawu Zheng, Ke Li, Xing Sun, Yunsheng Wu, and Rongrong Ji · 2024
Cited alongside, same era.
On designing effective rl reward at training time for llm reasoning
Jiaxuan Gao, Shusheng Xu, Wenjie Ye, Weilin Liu, Chuyi He, Wei Fu, Zhiyu Mei, Guangju Wang, and Yi Wu · 2024
Cited alongside, same era.
Openrlhf: An easy-to-use, scalable and high-performance rlhf framework
Jian Hu, Xibin Wu, Zilin Zhu, Xianyu, Weixun Wang, Dehao Zhang, and Yu Cao · 2024
Cited alongside, same era.
Aaron Jaech, Adam Kalai, Adam Lerer, Adam Richardson, Ahmed El-Kishky, Aiden Low, Alec Helyar, Aleksander Madry, Alex Beutel, Alex Carney, et al · 2024
Cited alongside, same era.
Sft memorizes, rl generalizes: A comparative study of foundation model post-training
Tianzhe Chu, Yuexiang Zhai, Jihan Yang, Shengbang Tong, Saining Xie, Dale Schuurmans, Quoc V Le, Sergey Levine, and Yi Ma · 2025
Closest in time.
Reward shaping to mitigate reward hacking in rlhf
Jiayi Fu, Xuandong Zhao, Chengyuan Yao, Heng Wang, Qi Han, and Yanghua Xiao · 2025
Closest in time.
Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning
Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, et al · 2025
Closest in time.
Vision-r1: Incentivizing reasoning capability in multimodal large language models
Wenxuan Huang, Bohan Jia, Zijie Zhai, Shaosheng Cao, Zheyu Ye, Fei Zhao, Yao Hu, and Shaohui Lin · 2025
Closest in time.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts
Pan Lu, Hritik Bansal, Tony Xia, Jiacheng Liu, Chunyuan Li, Hannaneh Hajishirzi, Hao Cheng, Kai-Wei Chang, Michel Galley, and Jianfeng Gao · 2024
Cited alongside, same era.
We-math: Does your large multimodal model achieve human-like mathematical reasoning?
Runqi Qiao, Qiuna Tan, Guanting Dong, Minhui Wu, Chong Sun, Xiaoshuai Song, Zhuoma GongQue, Shanglin Lei, Zhe Wei, Miaoxuan Zhang, et al · 2024
Cited alongside, same era.
Deepseekmath: Pushing the limits of mathematical reasoning in open language models
Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, YK Li, Y Wu, et al · 2024
Cited alongside, same era.
Logicvista: Multimodal llm logical reasoning benchmark in visual contexts
Yijia Xiao, Edward Sun, Tianyu Liu, and Wei Wang · 2024
Cited alongside, same era.
Llava-cot: Let vision language models reason step-by-step, 2024
Guowei Xu, Peng Jin, Hao Li, Yibing Song, Lichao Sun, and Li Yuan · 2024
Cited alongside, same era.
Mathverse: Does your multi-modal llm truly see the diagrams in visual math problems?
Renrui Zhang, Dongzhi Jiang, Yichi Zhang, Haokun Lin, Ziyu Guo, Pengshuo Qiu, Aojun Zhou, Pan Lu, Kai-Wei Chang, Yu Qiao, et al · 2024
Cited alongside, same era.
Math-puma: Progressive upward multimodal alignment to enhance mathematical reasoning
Wenwen Zhuang, Xin Huang, Xiantao Zhang, and Jin Zeng · 2024
Cited alongside, same era.
Chengke Zou, Xingang Guo, Rui Yang, Junyu Zhang, Bin Hu, and Huan Zhang · 2024
Cited alongside, same era.
Afrar Jahin, Arif Hassan Zidan, Yu Bao, Shizhe Liang, Tianming Liu, and Wei Zhang · 2025
Closest in time.
Visual-rft: Visual reinforcement fine-tuning
Ziyu Liu, Zeyi Sun, Yuhang Zang, Xiaoyi Dong, Yuhang Cao, Haodong Duan, Dahua Lin, and Jiaqi Wang · 2025
Closest in time.
Quality-driven curation of remote sensing vision-language data via learned scoring models
Dilxat Muhtar, Enzhuo Zhang, Zhenshi Li, Feng Gu, Yanglangxing He, Pengfeng Xiao, and Xueliang Zhang · 2025
Closest in time.
Lmm-r1: Empowering 3b lmms with strong reasoning abilities through two-stage rule-based rl
Yingzhe Peng, Gongrui Zhang, Miaosen Zhang, Zhiyuan You, Jie Liu, Qipeng Zhu, Kai Yang, Xingzhong Xu, Xin Geng, and Xu Yang · 2025
Closest in time.
Vlm-r1: A stable and generalizable r1-style large vision-language model
Haozhan Shen, Zilun Zhang, Kangjia Zhao, Qianqian Zhang, Ruochen Xu, and Tiancheng Zhao · 2025
Closest in time.
Vilbench: A suite for vision-language process reward modeling
Haoqin Tu, Weitao Feng, Hardy Chen, Hui Liu, Xianfeng Tang, and Cihang Xie · 2025
Closest in time.
Internlm-xcomposer2. 5-reward: A simple yet effective multi-modal reward model
Yuhang Zang, Xiaoyi Dong, Pan Zhang, Yuhang Cao, Ziyu Liu, Shengyuan Ding, Shenxi Wu, Yubo Ma, Haodong Duan, Wenwei Zhang, et al · 2025
Closest in time.
Simplerl-zoo: Investigating and taming zero reinforcement learning for open base models in the wild
Weihao Zeng, Yuzhen Huang, Qian Liu, Wei Liu, Keqing He, Zejun Ma, and Junxian He · 2025
Closest in time.
R1-zero’s” aha moment” in visual reasoning on a 2b non-sft model
Hengguang Zhou, Xirui Li, Ruochen Wang, Minhao Cheng, Tianyi Zhou, and Cho-Jui Hsieh · 2025
Closest in time.