congkai commited on
Commit
09ae307
·
verified ·
1 Parent(s): 7771cda

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -0
README.md CHANGED
@@ -13,10 +13,19 @@ Welcome to **InfiX-ai**! We are a research-driven organization dedicated to buil
13
 
14
  ---
15
  ### Models
 
 
 
16
  - [InfiR](https://huggingface.co/papers/2502.11573): **InfiR** aims to advance AI systems by improving reasoning, reducing adoption barriers, and addressing privacy concerns through smaller model sizes.
 
 
17
  - [InfiAlign](http://huggingface.co/collections/InfiX-ai/infialign-688600ca363ab9ef0b78f7a6): **InfiAlign** is a scalable and data-efficient post-training framework that combines supervised fine-tuning (SFT) and reinforcement learning (RL) with a high-quality data selection pipeline to enhance reasoning in large language models.
 
 
18
  - [InfiGUI](https://huggingface.co/papers/2501.04575): **InfiGUIAgent** is a GUI agent powered by a multimodal large language model, designed to perform multi-step task automation through native reasoning. It is trained with a two-stage supervised pipeline that combines GUI understanding with hierarchical and expectation-reflection reasoning.
19
  - [InfiGUI-R1-3B](https://huggingface.co/InfiX-ai/InfiGUI-R1-3B): **InfiGUI-R1** is an MLLM-based GUI agent developed through our Actor2Reasoner framework.
 
 
20
  - [InfiFusion](https://huggingface.co/collections/InfiX-ai/infifusion-683c7d7f00c71614ba8ceb96):
21
 
22
  ---
 
13
 
14
  ---
15
  ### Models
16
+ #### Reaoning-enhanced Continual Pretrain
17
+ We aim to enhance the reasoning capabilities of the base model through continual pretraining.
18
+
19
  - [InfiR](https://huggingface.co/papers/2502.11573): **InfiR** aims to advance AI systems by improving reasoning, reducing adoption barriers, and addressing privacy concerns through smaller model sizes.
20
+
21
+ #### Efficient Post-training for Reasoning
22
  - [InfiAlign](http://huggingface.co/collections/InfiX-ai/infialign-688600ca363ab9ef0b78f7a6): **InfiAlign** is a scalable and data-efficient post-training framework that combines supervised fine-tuning (SFT) and reinforcement learning (RL) with a high-quality data selection pipeline to enhance reasoning in large language models.
23
+
24
+ #### Advanced vision-native GUI Agent Model
25
  - [InfiGUI](https://huggingface.co/papers/2501.04575): **InfiGUIAgent** is a GUI agent powered by a multimodal large language model, designed to perform multi-step task automation through native reasoning. It is trained with a two-stage supervised pipeline that combines GUI understanding with hierarchical and expectation-reflection reasoning.
26
  - [InfiGUI-R1-3B](https://huggingface.co/InfiX-ai/InfiGUI-R1-3B): **InfiGUI-R1** is an MLLM-based GUI agent developed through our Actor2Reasoner framework.
27
+
28
+ #### Model over Models
29
  - [InfiFusion](https://huggingface.co/collections/InfiX-ai/infifusion-683c7d7f00c71614ba8ceb96):
30
 
31
  ---