Saved in:
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.05599 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910994230411264 |
|---|---|
| author | Peng, Yi Wang, Peiyu Wang, Xiaokun Wei, Yichen Pei, Jiangbo Qiu, Weijie Jian, Ai Hao, Yunzhuo Pan, Jiachun Xie, Tianyidan Ge, Li Zhuang, Rongxian Song, Xuchen Liu, Yang Zhou, Yahui |
| author_facet | Peng, Yi Wang, Peiyu Wang, Xiaokun Wei, Yichen Pei, Jiangbo Qiu, Weijie Jian, Ai Hao, Yunzhuo Pan, Jiachun Xie, Tianyidan Ge, Li Zhuang, Rongxian Song, Xuchen Liu, Yang Zhou, Yahui |
| contents | We introduce Skywork R1V, a multimodal reasoning model extending the an R1-series Large language models (LLM) to visual modalities via an efficient multimodal transfer method. Leveraging a lightweight visual projector, Skywork R1V facilitates seamless multimodal adaptation without necessitating retraining of either the foundational language model or the vision encoder. To strengthen visual-text alignment, we propose a hybrid optimization strategy that combines Iterative Supervised Fine-Tuning (SFT) with Group Relative Policy Optimization (GRPO), significantly enhancing cross-modal integration efficiency. Additionally, we introduce an adaptive-length Chain-of-Thought distillation approach for reasoning data generation. This approach dynamically optimizes reasoning chain lengths, thereby enhancing inference efficiency and preventing excessive reasoning overthinking. Empirical evaluations demonstrate that Skywork R1V, with only 38B parameters, delivers competitive performance, achieving a score of 69.0 on the MMMU benchmark and 67.5 on MathVista. Meanwhile, it maintains robust textual reasoning performance, evidenced by impressive scores of 72.0 on AIME and 94.0 on MATH500. The Skywork R1V model weights have been publicly released to promote openness and reproducibility. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_05599 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-Thought Peng, Yi Wang, Peiyu Wang, Xiaokun Wei, Yichen Pei, Jiangbo Qiu, Weijie Jian, Ai Hao, Yunzhuo Pan, Jiachun Xie, Tianyidan Ge, Li Zhuang, Rongxian Song, Xuchen Liu, Yang Zhou, Yahui Computer Vision and Pattern Recognition Computation and Language We introduce Skywork R1V, a multimodal reasoning model extending the an R1-series Large language models (LLM) to visual modalities via an efficient multimodal transfer method. Leveraging a lightweight visual projector, Skywork R1V facilitates seamless multimodal adaptation without necessitating retraining of either the foundational language model or the vision encoder. To strengthen visual-text alignment, we propose a hybrid optimization strategy that combines Iterative Supervised Fine-Tuning (SFT) with Group Relative Policy Optimization (GRPO), significantly enhancing cross-modal integration efficiency. Additionally, we introduce an adaptive-length Chain-of-Thought distillation approach for reasoning data generation. This approach dynamically optimizes reasoning chain lengths, thereby enhancing inference efficiency and preventing excessive reasoning overthinking. Empirical evaluations demonstrate that Skywork R1V, with only 38B parameters, delivers competitive performance, achieving a score of 69.0 on the MMMU benchmark and 67.5 on MathVista. Meanwhile, it maintains robust textual reasoning performance, evidenced by impressive scores of 72.0 on AIME and 94.0 on MATH500. The Skywork R1V model weights have been publicly released to promote openness and reproducibility. |
| title | Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-Thought |
| topic | Computer Vision and Pattern Recognition Computation and Language |
| url | https://arxiv.org/abs/2504.05599 |