Downloads · 30 days
1.5K
95% of all-time downloads
OphVLM-R1
QiZishi/OphVLM-R1
OphVLM-R1 is a reinforcement learning model from QiZishi. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product. The card lists the license as cc-by-nc-sa-4.0.
<p align="center" <img src="figures/模型图标.png" width="120" alt="OphVLM-R1 project icon" </p
All-time downloads
1.6K
Public
Parameters
2.3B
4.7 GB on disk
Likes
1
Trending 1
Repo makeup
Click a slice to open those files.
.safetensors4.7 GB · 100%
At a glance
- Task
- Reinforcement Learning
- License
- cc-by-nc-sa-4.0
- Access
- Public
- Created
- Jul 11, 2026
- Updated
- Jul 13, 2026
- SHA
- 91e2b208
Base models
Datasets
Model card
From the Hugging Face model README
<p align="center">
<img src="figures/模型图标.png" width="120" alt="OphVLM-R1 project icon">
</p>
<h1 align="center">OphVLM-R1</h1>
<p align="center"><strong>Efficient Ophthalmic Reasoning via Curriculum Reinforcement Learning</strong></p>
<p align="center">
<a href="https://huggingface.co/QiZishi/OphVLM-R1/blob/main/README.md">English</a> · <a href="https://huggingface.co/QiZishi/OphVLM-R1/blob/main/README_zh.md">简体中文</a>
</p>
<p align="center">
<a href="https://qizishi.github.io/OphVLM-R1/"><img src="https://img.shields.io/badge/Project-Page-2b6cb0?style=for-the-badge" alt="Project page"></a>
<a href="https://github.com/QiZishi/OphAgent/"><img src="https://img.shields.io/badge/Code-OphAgent-181717?style=for-the-badge&logo=github" alt="OphAgent code"></a>
</p>
<p align="center">
<a href="https://huggingface.co/QiZishi/OphVLM-R1"><img src="https://img.shields.io/badge/🤗%20Model-Hugging%20Face-FFD21E?style=for-the-badge" alt="Model on Hugging Face"></a>
<a href="https://www.modelscope.cn/models/MoonNight/OphVLM-R1"><img src="https://img.shields.io/badge/Model-ModelScope-624AFF?style=for-the-badge" alt="Model on ModelScope"></a>
</p>
<p align="center">
<a href="https://huggingface.co/datasets/QiZishi/OphReason-Vision"><img src="https://img.shields.io/badge/🤗%20Dataset-Hugging%20Face-FFD21E?style=for-the-badge" alt="Dataset on Hugging Face"></a>
<a href="https://www.modelscope.cn/datasets/MoonNight/OphReason-Vision"><img src="https://img.shields.io/badge/Dataset-ModelScope-624AFF?style=for-the-badge" alt="Dataset on ModelScope"></a>
</p>
Overview
OphVLM-R1 is a lightweight 2B-parameter vision-language model for ophthalmic multimodal reasoning. Starting from InternVL3.5-2B, it first acquires ophthalmic knowledge through LoRA supervised fine-tuning (SFT), then develops progressively harder clinical reasoning skills through four-stage curriculum reinforcement learning. Group Sequence-level Policy Optimization (GSPO) and hard-sample dynamic backtracking are used to improve optimization over long reasoning trajectories and difficult long-tail cases.
This README focuses on the model training pipeline, architecture and algorithms, and experimental results. For dataset construction and distribution details, see the OphReason-Vision dataset repositories below.
Project Resources
- Project page: https://qizishi.github.io/OphVLM-R1/
- OphVLM-R1 model: Hugging Face | ModelScope
- OphReason-Vision dataset: Hugging Face | ModelScope
- OphAgent system: GitHub
Model and Training Framework
OphVLM-R1 uses InternVL3.5-2B as its backbone. Its 2B parameter scale targets deployment in resource-constrained settings while retaining multimodal clinical reasoning capacity. Training consists of two stages.
Stage 1: LoRA Supervised Fine-Tuning
The cold-start stage injects ophthalmic domain knowledge with Low-Rank Adaptation:
$$ W_0 + \Delta W = W_0 + BA, \qquad h = W_0x + \frac{\alpha}{r}BAx $$
where \(B \in \mathbb{R}^{d \times r}\), \(A \in \mathbb{R}^{r \times k}\), and \(r \ll \min(d,k)\). The SFT objective is
$$ \mathcal{L}{\mathrm{SFT}}=-\mathbb{E}\left[\sum{t=1}^{\lvert y\rvert}\log\pi_\phi(y_t\mid x,y_{\lt t})\right]. $$
| Setting | Value |
|---|---|
| Training subset | 3,418 cold-start samples |
| LoRA rank / scaling | \(r=64\), \(\alpha=128\) |
| Target projections | \(W_q\), \(W_k\), \(W_v\), \(W_o\) |
| Learning rate | \(1\times10^{-4}\) with cosine annealing |
| Batch size / epochs | 32 / 3 |
| Trainable parameters | Approximately 0.5% |
Stage 2: Curriculum Reinforcement Learning
GSPO computes the policy ratio at sequence level rather than independently clipping token-level ratios:
$$ s_i(\phi)=\left(\frac{\pi_\phi(y_i\mid x)}{\pi_{\phi_{\mathrm{old}}}(y_i\mid x)}\right)^{\frac{1}{\lvert y_i\rvert}}=\exp\left(\frac{1}{\lvert y_i\rvert}\sum_{t=1}^{\lvert y_i\rvert}\log\frac{\pi_\phi(y_{i,t}\mid x,y_{i,\lt t})}{\pi_{\phi_{\mathrm{old}}}(y_{i,t}\mid x,y_{i,\lt t})}\right). $$
The PPO-style objective uses group-normalized advantages:
$$ \mathcal{J}{\mathrm{GSPO}}(\phi)=\mathbb{E}\left[\frac{1}{G}\sum{i=1}^{G}\min\left(s_i\hat A_i,\operatorname{clip}(s_i,1-\varepsilon,1+\varepsilon)\hat A_i\right)\right]. $$
Each stage uses a mixed reward
$$ r(x,y)=\lambda_1r_{\mathrm{rule}}(x,y)+\lambda_2r_{\mathrm{judge}}(x,y), $$
where the judge reward is produced by Intern-S1-mini. The curriculum follows increasing clinical complexity:
- Lesion Localization — single-image visual perception.
- Multi-image Selection — cross-image comparison.
- Report Generation — structured, long-form synthesis.
- Knowledge Q&A — integration of visual findings and clinical knowledge.
| Setting | Value |
|---|---|
| Group size / clipping | \(G=8\), \(\varepsilon=0.2\) |
| Learning rate | \(5\times10^{-6}\) |
| KL coefficient | \(\beta_{\mathrm{KL}}=0.04\) |
| Reward weights | \(\lambda_1=0.6\), \(\lambda_2=0.4\) |
| Training length | 2 epochs per curriculum stage |
Hard-Sample Dynamic Backtracking
Prompts that repeatedly receive low rewards during the most recent \(k=5\) rounds are resampled on-policy:
$$ P_{\mathrm{sample}}(x,y)\propto f(x,y)^\beta, $$
where \(f(x,y)\) is the consecutive failure count and \(\beta=2.0\). Resampled prompts always receive fresh rollouts, and the resampling share is capped at 30% of each batch.
Training Stack
- Hardware: 8 NVIDIA GeForce RTX 4090 GPUs (24 GB each).
- SFT: 4 GPUs.
- Reinforcement learning: 6 GPUs for training and 2 GPUs for vLLM rollout generation.
- Software: ms-swift, DeepSpeed ZeRO-3, AdamW, vLLM, and EvalScope.
Experiments
Evaluation Benchmarks
| Benchmark | Samples | Tasks / sources | Role |
|---|---|---|---|
| In-Domain | 2,000 | 4 tasks | Held-out clinical reasoning |
| Fundus-MMBench | 620 | 31 tasks | Fine-grained fundus analysis |
| OmniMedVQA-Eye | 10,044 | 11 sources | Out-of-domain VQA |
Main Results
Accuracy is reported in percent. The cross-benchmark average is reference-only because the benchmarks differ in task format, difficulty, and random baseline; per-benchmark comparisons are primary.
| Model | In-Domain | Fundus | Omni-Eye | Avg.* |
|---|---|---|---|---|
| InternVL3.5-2B | 34.50 | 36.61 | 55.47 | 42.19 |
| InternVL3.5-4B | 36.23 | 42.10 | 77.51 | 51.95 |
| MedVLM-R1-2B | 27.80 | 20.81 | 68.06 | 38.89 |
| Lingshu-7B | 44.20 | 41.29 | 87.42 | 57.64 |
| HuatuoGPT-Vision-7B | 38.30 | 28.06 | 71.78 | 46.05 |
| FundusExpert-8B | 31.20 | 54.84 | 64.71 | 50.25 |
| OphthaReason-Intern-2B | 31.00 | 35.48 | 79.61 | 48.70 |
| OphthaReason-Qwen-3B | 36.60 | 38.87 | 86.86 | 54.11 |
| OphVLM-R1-2B (ours) | 38.40 | 42.58 | 88.24 | 56.41 |
OphVLM-R1 reaches 88.24% on OmniMedVQA-Eye and 42.58% on Fundus-MMBench. Its 56.41% reference average is 4.46 percentage points above InternVL3.5-4B and 2.30 points above OphthaReason-Qwen-3B. Comparisons with off-the-shelf 7B/8B models should be interpreted cautiously because data exposure and parameter scale are not controlled.
Ablation Results
| Configuration | In-Domain | Fundus | Omni-Eye | \(\Delta\) Omni |
|---|---|---|---|---|
| OphVLM-R1 (full) | 38.40 | 42.58 | 88.24 | — |
| SFT only | 37.52 | 34.47 | 62.03 | -26.21 |
| SFT + RL one-shot | 37.96 | 38.62 | 78.14 | -10.10 |
| SFT + RL shuffled | 37.73 | 37.85 | 76.48 | -11.76 |
| Without Stage 1 | 38.14 | 40.43 | 85.62 | -2.62 |
| Without Stage 2 | 38.02 | 40.17 | 85.13 | -3.11 |
| Without Stage 3 | 37.88 | 39.72 | 84.38 | -3.86 |
| Without Stage 4 | 38.07 | 40.31 | 85.47 | -2.77 |
| Token-level GRPO | 37.84 | 39.76 | 84.52 | -3.72 |
| Without hard-sample backtracking | 38.11 | 40.83 | 86.12 | -2.12 |
The ablations show that ordered curriculum RL, sequence-level optimization, and hard-sample backtracking make independent contributions. All reported results are single runs without confidence intervals or significance tests. In addition, the theoretical variance-reduction argument for GSPO is exact only under i.i.d. per-token log-ratio assumptions and is approximate for correlated natural-language tokens.
Citation
@inproceedings{qi2026ophvlm,
title={OphVLM-R1: Efficient Ophthalmic Reasoning via Curriculum Reinforcement Learning},
author={Qi, Zishi and Hu, Xiaoya and Pan, Huilin and Gao, Ang and Hou, Jiaxin and Li, Jiankun and Qian, Yongao},
booktitle={Proceedings of the World Artificial Intelligence Conference Academic (WAICA)},
year={2026}
}
Acknowledgements
We thank OpenGVLab for the InternVL foundation model and the ophthalmologists who contributed to data review and quality assurance.
- Task
- Reinforcement Learning
- License
- cc-by-nc-sa-4.0
- Languages
- en
- Created
- Jul 11, 2026
- Updated
- Jul 13, 2026