Update README.md
Browse files
README.md
CHANGED
|
@@ -16,8 +16,15 @@ Official Repository of the paper: *[IterComp](https://arxiv.org/abs/2410.07171)*
|
|
| 16 |
|
| 17 |
## News🔥🔥🔥
|
| 18 |
|
| 19 |
-
|
| 20 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
|
| 22 |
## Introduction
|
| 23 |
|
|
|
|
| 16 |
|
| 17 |
## News🔥🔥🔥
|
| 18 |
|
| 19 |
+
**[2025.02]** We open-source three composition-aware reward models in [HuggingFace Repo](https://huggingface.co/comin/IterComp/tree/main/reward_models), which can be used for preference learning and as **new image generation evaluators**.
|
| 20 |
+
|
| 21 |
+
**[2025.02]** We enhance IterComp-RPG with LLMs that possess the strongest reasoning capabilities, including [**DeepSeek-R1**](https://github.com/deepseek-ai/DeepSeek-R1), [**OpenAI o3-mini**](https://openai.com/index/openai-o3-mini/), and [**OpenAI o1**](https://openai.com/index/learning-to-reason-with-llms/) to achieve outstanding compositional image generation under complex prompts.
|
| 22 |
+
|
| 23 |
+
**[2025.01]** IterComp is accepted by ICLR 2025!!!
|
| 24 |
+
|
| 25 |
+
**[2024.10]** Checkpoints of base diffusion model are publicly available on [HuggingFace Repo](https://huggingface.co/comin/IterComp).
|
| 26 |
+
|
| 27 |
+
**[2024.10]** Our main code of IterComp is released.
|
| 28 |
|
| 29 |
## Introduction
|
| 30 |
|