├── ACKNOWLEDGEMENT.md ├── LICENSE ├── MMR1-Math └── temp ├── README.md ├── assets └── logo.png └── requirements.txt /ACKNOWLEDGEMENT.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LengSicong/MMR1/9ec3a05a79560af1c775fdad96d94f144a17884e/ACKNOWLEDGEMENT.md -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /MMR1-Math/temp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LengSicong/MMR1/9ec3a05a79560af1c775fdad96d94f144a17884e/MMR1-Math/temp -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 |

2 | 3 |

4 | 5 |

6 | MMR1: Advancing the Frontiers of Multimodal Reasoning

7 |
If our project helps you, please give us a star ⭐ on GitHub to support us. 🙏🙏
8 | 9 | 10 |
11 | 12 | [![hf_data](https://img.shields.io/badge/🤗-Dataset-9C276A.svg)](https://huggingface.co/datasets/MMR1/MMR1-Math-RL-Data-v0) 13 | [![hf_checkpoint](https://img.shields.io/badge/🤗-Checkpoints-9C276A.svg)](https://huggingface.co/MMR1/MMR1-Math-v0-7B) 14 | [![License](https://img.shields.io/badge/License-Apache%202.0-yellow)](https://github.com/LengSicong/MMR1/blob/main/LICENSE)
15 | [![Hits](https://hits.seeyoufarm.com/api/count/incr/badge.svg?url=https%3A%2F%2Fgithub.com%2FLengSicong%2FMMR1&count_bg=%2379C83D&title_bg=%23555555&icon=&icon_color=%23E7E7E7&title=Visitor&edge_flat=false)](https://hits.seeyoufarm.com) 16 | [![GitHub issues](https://img.shields.io/github/issues/LengSicong/MMR1?color=critical&label=Issues)](https://github.com/LengSicong/MMR1/issues?q=is%3Aopen+is%3Aissue) 17 | [![GitHub closed issues](https://img.shields.io/github/issues-closed/LengSicong/MMR1?color=success&label=Issues)](https://github.com/LengSicong/MMR1/issues?q=is%3Aissue+is%3Aclosed)
18 | 20 |
21 | 22 | 23 | ## 📰 News 24 | 25 | * **[2025.03.11]** 🔥🔥 Release MMR1-Math-v0-7B, achieving SOTA with only **6k public training data**! 26 | 27 | 28 | 29 |

Introduction

30 | Introducing MMR1-Math-v0, a Large Multimodal Model specialized in mathematical tasks. Remarkably, MMR1-Math-v0 achieves state-of-the-art performance among open-source 7B multimodal models, competing effectively even against proprietary models with significantly larger parameter sizes—all trained using only 6k carefully curated data instances. 31 | 32 | ### 💡 Key Highlights: 33 | 34 | - **SOTA Performance**: Sets a new **state-of-the-art** benchmark on math-related multimodal tasks among open-source 7B models. 35 | 36 | - **Minimal Training Data**: Remarkably achieves top-tier performance with just **6k** high-quality samples from **public training datasets**. 37 | 38 | - **Efficient Training with GRPO**: 6 hours of RL training with 64 H100s for 15 epochs. 39 | 40 | - **Public and High-Quality Data**: Publicly sourced datasets, rigorously filtered and balanced across both difficulty and mathematical problem types. 41 | 42 | - **Balanced Data Strategy**: Uniform sampling of data based on both task difficulty (filtering out overly simple problems) and mathematical reasoning diversity. 43 | 44 | 45 | ## ✅ Evaluation Results 46 | 47 | We evaluated our model using [VLMEvalKit](https://github.com/open-compass/VLMEvalKit/tree/main) on four mathematical reasoning benchmarks: MathVista_MINI, MathVision, LogicVista, and MathVerse_MINI. 48 | 49 | We also include results on the MathVerse_MINI_Vision_Only_cot (MathVerse_V) subset to maintain consistency with the VLMEvalKit leaderboard. The table below compares our model's performance against various open-source and proprietary models. 50 | 51 | | Model | size | MathVista | MathVision | LogicVista | MathVerse_V | MathVerse | 52 | |-------|:----:|:--------------:|:----------:|:----------:|:--------------:|:-------------------:| 53 | | **Close-sourced** | | | | | | | 54 | | [GPT-4o 1120](https://openai.com/index/gpt-4o-system-card/) | - | 60.0 | 31.2 | 52.8 | 40.6 | - | 55 | | [Gemini-2.0-flash](https://deepmind.google/technologies/gemini/flash/) | - | 70.4 | 43.6 | 52.3 | 47.8 | - | 56 | | [Claude3.7-Sonnet](https://www.anthropic.com/news/claude-3-7-sonnet) | - | 66.8 | 41.9 | 58.2 | 46.7 | - | 57 | | **R1-related** | | | | | | | 58 | | [LLaVA-CoT](https://github.com/PKU-YuanGroup/LLaVA-CoT) | 11B | 52.5 | 19.9 | 39.6 | 22.6 | - | 59 | | [Open-R1-Multimodal](https://github.com/EvolvingLMMs-Lab/open-r1-multimodal) | 7B | 60.6 | - | - | - | - | 60 | | [Mulberry](https://github.com/HJYao00/Mulberry) | 7B | 63.1 | - | - | - | - | 61 | | [LMM-R1](https://arxiv.org/abs/2503.07536) | 3B | 63.2 | 26.4 | - | - | 41.6 | 62 | | [R1-Onevision](https://github.com/Fancy-MLLM/R1-Onevision?tab=readme-ov-file) | 7B | - | 26.2 | - | - | 44.1 | 63 | | [MM-Eureka](https://github.com/ModalMinds/MM-EUREKA) | 8B | 67.1 | 22.2 | - | - | 40.4 | 64 | | [MM-Eureka](https://github.com/ModalMinds/MM-EUREKA) | 38B | 64.2 | 26.6 | - | - | 48.9 | 65 | | **Open-sourced** | | | | | | | 66 | | [Ovis2-8b](https://github.com/AIDC-AI/Ovis) | 8B | 71.8 | 25.9 | 39.4 | 42.3 | - | 67 | | [MiniCPM-o-2.6](https://github.com/OpenBMB/MiniCPM-o) | 8B | **71.9** | 21.7 | 36.0 | 35.0 | - | 68 | | [VITA-1.5](https://github.com/VITA-MLLM/VITA) | 7B | 66.2 | 19.5 | 38.9 | - | 23.4 | 69 | | [Qwen2.5-VL](https://github.com/QwenLM/Qwen2.5-VL) (official) | 7B | 68.2 | 25.4 | 47.9 | 41.1 | - | 70 | | [Qwen2.5-VL](https://github.com/QwenLM/Qwen2.5-VL) (reproduced) | 7B | 67.5 | 25.6 | 46.8 | 42.5 | 46.9 | 71 | | **Ours** | | | | | | | 72 | | **MMR1-math-v0** | 7B | 71.0 | **30.2** | **50.8** | **45.1** | **49.8** | 73 | 74 | ### Ablation Studies 75 | To further examine the effectiveness of GRPO, we perform ablation experiments by comparing our model with two SFT-based variants. Specifically, we fine-tune Qwen2.5-VL-7B on the 6k dataset using direct answer supervision (Qwen2.5-VL-sft) and chain-of-thought supervision (Qwen2.5-VL-sft-cot). 76 | 77 | | Model | size | MathVista | MathVision | LogicVista | MathVerse | MathVerse_V | 78 | |-------|:----:|:--------------:|:----------:|:----------:|:--------------:|:-------------------:| 79 | | Qwen2.5-VL-sft | 7B | 52.2 | 27.0 | 31.8 | 20.7 | 24.7 | 80 | | Qwen2.5-VL-sft-cot | 7B | 54.7 | 23.4 | 33.8 | 23.7 | 25.7 | 81 | | **MMR1-math-v0** | 7B | 71.0 | **30.2** | **50.8** | **45.1** | **49.8** | 82 | 83 | 84 | ## 🏫 Project Zoo 85 | | Project | Latest Model | Checkpoints | Data | Link | 86 | |-----------|--------------|-------|-----|-----------| 87 | | MMR1-Math | MMR1-Math-v0 | [![hf_space](https://img.shields.io/badge/🤗-7B-9C276A.svg)](https://huggingface.co/MMR1/MMR1-Math-v0-7B) | [![hf_space](https://img.shields.io/badge/🤗-data-9C276A.svg)](https://huggingface.co/datasets/MMR1/MMR1-Math-RL-Data-v0) | [🔗](https://github.com/LengSicong/MMR1/tree/main/MMR1-Math) | 88 | | MMR1-Science (coming soon!)| | | | | 89 | 90 | 91 | ## 💪 TODO 92 | This project is under active development. Stay tuned for our upcoming updates! 93 | - [ ] Release data composition and preprocessing scripts. 94 | - [ ] Release GRPO training scripts. 95 | - [ ] Cold-start before RL training. Both dataset and checkpoint for cold-start will be released soon. 96 | - [ ] More efficient GRPO training recipes. (Coming soon) 97 | - [ ] More model sizes and variants. 98 | 99 | 100 | 101 | 102 | ## 🛠️ Requirements and Installation 103 | 104 | Basic Dependencies: 105 | 106 | * Python >= 3.10 107 | * transformers>=4.49.0 108 | * flash-attn>=2.4.3 109 | * vllm>=0.7.3 110 | 111 | Install required packages: 112 | 113 | ```bash 114 | pip install -r requirements.txt 115 | ``` 116 | 117 | ## 🤖 Inference 118 | Here we show a code snippet to show you how to use MMR1-Math with `transformers` and `qwen_vl_utils`: 119 | 120 | ```python 121 | from transformers import Qwen2_5_VLForConditionalGeneration, AutoTokenizer, AutoProcessor 122 | from qwen_vl_utils import process_vision_info 123 | # default: Load the model on the available device(s) 124 | model = Qwen2_5_VLForConditionalGeneration.from_pretrained( 125 | "MMR1/MMR1-Math-v0-7B", 126 | torch_dtype=torch.bfloat16, 127 | attn_implementation="flash_attention_2", 128 | device_map="auto", 129 | ) 130 | # default processer 131 | processor = AutoProcessor.from_pretrained("MMR1/MMR1-Math-v0-7B") 132 | # Example input 133 | messages = [ 134 | { 135 | "role": "user", 136 | "content": [ 137 | { 138 | "type": "image", 139 | "image": "path/to/image.jpeg", 140 | }, 141 | {"type": "text", "text": "Describe this image."}, 142 | ], 143 | } 144 | ] 145 | # Preparation for inference 146 | text = processor.apply_chat_template( 147 | messages, tokenize=False, add_generation_prompt=True 148 | ) 149 | image_inputs, video_inputs = process_vision_info(messages) 150 | inputs = processor( 151 | text=[text], 152 | images=image_inputs, 153 | videos=video_inputs, 154 | padding=True, 155 | return_tensors="pt", 156 | ) 157 | inputs = inputs.to("cuda") 158 | # Inference: Generation of the output 159 | generated_ids = model.generate(**inputs, max_new_tokens=128) 160 | generated_ids_trimmed = [ 161 | out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids) 162 | ] 163 | output_text = processor.batch_decode( 164 | generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False 165 | ) 166 | print(output_text) 167 | ``` 168 |
169 | Batch inference 170 | 171 | ```python 172 | # Sample messages for batch inference 173 | messages1 = [ 174 | { 175 | "role": "user", 176 | "content": [ 177 | {"type": "image", "image": "file:///path/to/image1.jpg"}, 178 | {"type": "image", "image": "file:///path/to/image2.jpg"}, 179 | {"type": "text", "text": "What are the common elements in these pictures?"}, 180 | ], 181 | } 182 | ] 183 | messages2 = [ 184 | {"role": "system", "content": "You are a helpful assistant."}, 185 | {"role": "user", "content": "Who are you?"}, 186 | ] 187 | # Combine messages for batch processing 188 | messages = [messages1, messages2] 189 | # Preparation for batch inference 190 | texts = [ 191 | processor.apply_chat_template(msg, tokenize=False, add_generation_prompt=True) 192 | for msg in messages 193 | ] 194 | image_inputs, video_inputs = process_vision_info(messages) 195 | inputs = processor( 196 | text=texts, 197 | images=image_inputs, 198 | videos=video_inputs, 199 | padding=True, 200 | return_tensors="pt", 201 | ) 202 | inputs = inputs.to("cuda") 203 | # Batch Inference 204 | generated_ids = model.generate(**inputs, max_new_tokens=128) 205 | generated_ids_trimmed = [ 206 | out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids) 207 | ] 208 | output_texts = processor.batch_decode( 209 | generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False 210 | ) 211 | print(output_texts) 212 | ``` 213 |
214 | 215 | 216 | ## 🗝️ Training 217 | Coming soon! 218 | 219 | 220 | ## 🤝 Contribution and Contact 221 | This project is still under active development. Community feedback and contributions are highly appreciated. If you want to contribute, please feel free to make a pull request or create an issue. 222 | 223 | If you have any questions or would like to engage with our community, feel free to scan the QR code below to join our WeChat group. 224 | 225 | 226 | ## 👍 Acknowledgement 227 | Our MMR1 is build on top of [Qwen2.5VL](https://github.com/QwenLM/Qwen2.5-VL), [LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory) and [EasyR1](https://github.com/hiyouga/EasyR1/tree/main). 228 | Besides, our MMR1 benefits from tons of open-source efforts. We sincerely appreciate these efforts and compile a list in [ACKNOWLEDGEMENT.md](https://github.com/LengSicong/MMR1/blob/main/ACKNOWLEDGEMENT.md) to express our gratitude. If your work is used in MMR1 but not mentioned in either this repo or the technical report, feel free to let us know :heart:. 229 | 230 |
💡 Some other multimodal-LLM projects from our team may interest you ✨.

231 | 232 | > [**VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding**](https://github.com/DAMO-NLP-SG/VideoLLaMA3)
233 | > Boqiang Zhang* , Kehan Li* , Zesen Cheng* , Zhiqiang Hu* , Yuqian Yuan* , Guanzheng Chen* , Sicong Leng* , Yuming Jiang* , Hang Zhang* , Xin Li* , Peng Jin, Wenqi Zhang, Fan Wang, Lidong Bing, Deli Zhao
234 | [![github](https://img.shields.io/badge/-Github-black?logo=github)](https://github.com/DAMO-NLP-SG/VideoLLaMA3) [![github](https://img.shields.io/github/stars/DAMO-NLP-SG/VideoLLaMA3.svg?style=social)](https://github.com/DAMO-NLP-SG/VideoLLaMA3) [![arXiv](https://img.shields.io/badge/Arxiv-2501.13106-b31b1b.svg?logo=arXiv)](https://arxiv.org/abs/2501.13106)
235 | 236 | > [**VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs**](https://github.com/DAMO-NLP-SG/VideoLLaMA2)
237 | > Zesen Cheng*, Sicong Leng*, Hang Zhang*, Yifei Xin*, Xin Li*, Guanzheng Chen, Yongxin Zhu, Wenqi Zhang, Ziyang Luo, Deli Zhao, Lidong Bing
238 | [![github](https://img.shields.io/badge/-Github-black?logo=github)](https://github.com/DAMO-NLP-SG/VideoLLaMA2) [![github](https://img.shields.io/github/stars/DAMO-NLP-SG/VideoLLaMA2.svg?style=social)](https://github.com/DAMO-NLP-SG/VideoLLaMA2) [![arXiv](https://img.shields.io/badge/Arxiv-2406.07476-b31b1b.svg?logo=arXiv)](https://arxiv.org/abs/2406.07476) 239 | 240 | > [**VCD: Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding**](https://arxiv.org/abs/2311.16922)
241 | > Sicong Leng*, Hang Zhang*, Guanzheng Chen, Xin Li, Shijian Lu, Chunyan Miao, Lidong Bing
242 | [![github](https://img.shields.io/badge/-Github-black?logo=github)](https://github.com/DAMO-NLP-SG/VCD) [![github](https://img.shields.io/github/stars/DAMO-NLP-SG/VCD.svg?style=social)](https://github.com/DAMO-NLP-SG/VCD) [![arXiv](https://img.shields.io/badge/Arxiv-2311.16922-b31b1b.svg?logo=arXiv)](https://arxiv.org/abs/2311.16922)
243 | 244 | > [**The Curse of Multi-Modalities: Evaluating Hallucinations of Large Multimodal Models across Language, Visual, and Audio**](https://arxiv.org/abs/2410.12787)
245 | > Sicong Leng*, Yun Xing*, Zesen Cheng*, Yang Zhou, Hang Zhang, Xin Li, Deli Zhao, Shijian Lu, Chunyan Miao, Lidong Bing
246 | [![github](https://img.shields.io/badge/-Github-black?logo=github)](https://github.com/DAMO-NLP-SG/CMM) [![github](https://img.shields.io/github/stars/DAMO-NLP-SG/CMM.svg?style=social)](https://github.com/DAMO-NLP-SG/CMM) [![arXiv](https://img.shields.io/badge/Arxiv-2410.12787-b31b1b.svg?logo=arXiv)](https://arxiv.org/abs/2410.12787)
247 | 248 | > [**Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss**](https://arxiv.org/abs/2410.17243)
249 | > Zesen Cheng*, Hang Zhang*, Kehan Li*, Sicong Leng, Zhiqiang Hu, Fei Wu, Deli Zhao, Xin Li, Lidong Bing
250 | [![github](https://img.shields.io/badge/-Github-black?logo=github)](https://github.com/DAMO-NLP-SG/Inf-CLIP) [![github](https://img.shields.io/github/stars/DAMO-NLP-SG/Inf-CLIP.svg?style=social)](https://github.com/DAMO-NLP-SG/Inf-CLIP) [![arXiv](https://img.shields.io/badge/Arxiv-2410.17243-b31b1b.svg?logo=arXiv)](https://arxiv.org/abs/2410.17243)
251 | 252 | > [**VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM**](https://arxiv.org/abs/2501.00599)
253 | > Yuqian Yuan, Hang Zhang, Wentong Li, Zesen Cheng, Boqiang Zhang, Long Li, Xin Li, Deli Zhao, Wenqiao Zhang, Yueting Zhuang, Jianke Zhu, Lidong Bing
254 | [![github](https://img.shields.io/badge/-Github-black?logo=github)](https://github.com/DAMO-NLP-SG/VideoRefer) [![github](https://img.shields.io/github/stars/DAMO-NLP-SG/VideoRefer.svg?style=social)](https://github.com/DAMO-NLP-SG/VideoRefer) [![arXiv](https://img.shields.io/badge/Arxiv-2501.00599-b31b1b.svg?logo=arXiv)](https://arxiv.org/abs/2501.00599)
255 | 256 |

257 | 258 | ## 📑 Citation 259 | 260 | If you find MMR1 useful for your research and applications, please cite using this BibTeX: 261 | 262 | ```bibtex 263 | @misc{MMR1-Math2025, 264 | title={MMR1: Advancing the Frontiers of Multimodal Reasoning}, 265 | author={Sicong Leng*, Jing Wang*, Jiaxi Li*, Hao Zhang*, Zhiqiang Hu, Boqiang Zhang, Hang Zhang, Yuming Jiang, Xin Li, Deli Zhao, Fan Wang, Yu Rong, Aixin Sun†, Shijian Lu†}, 266 | year={2025}, 267 | howpublished={\url{https://github.com/LengSicong/MMR1}}, 268 | } 269 | ``` 270 | 271 | ## 🔒 License 272 | 273 | This project is released under the Apache 2.0 license as found in the LICENSE file. 274 | The service is a research preview intended for **non-commercial use ONLY**, subject to the model Licenses of Qwen, Terms of Use of the data generated by OpenAI and Gemini, and Privacy Practices of ShareGPT. Please get in touch with us if you find any potential violations. 275 | 276 | ## Star History 277 | 278 | [![Star History Chart](https://api.star-history.com/svg?repos=LengSicong/MMR1&type=Date)](https://star-history.com/#LengSicong/MMR1&Date) 279 | -------------------------------------------------------------------------------- /assets/logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LengSicong/MMR1/9ec3a05a79560af1c775fdad96d94f144a17884e/assets/logo.png -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | accelerate 2 | codetiming 3 | datasets 4 | flash-attn>=2.4.3 5 | liger-kernel 6 | mathruler 7 | numpy 8 | omegaconf 9 | pandas 10 | peft 11 | pillow 12 | pyarrow>=15.0.0 13 | pylatexenc 14 | qwen-vl-utils 15 | ray 16 | tensordict 17 | torchdata 18 | transformers>=4.49.0 19 | vllm>=0.7.3 20 | wandb 21 | --------------------------------------------------------------------------------