xiachongfeng commited on
Commit
d536f11
·
verified ·
1 Parent(s): 5f25179

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -18
README.md CHANGED
@@ -9,23 +9,8 @@ pinned: false
9
 
10
  # DiffuSpace
11
 
12
- **Building the next foundation model paradigm beyond autoregression.**
13
 
14
- We build diffusion language models to explore new possibilities for machine intelligence. Through parallel generation, bidirectional modeling, and iterative refinement, we aim to make language generation more flexible, efficient, and controllable.
15
 
16
- We believe intelligence should consider the whole context, navigate uncertainty, and refine possibilities into answers.
17
-
18
- ## Research Directions
19
-
20
- - **Diffusion Language Models** — Advancing diffusion as a foundation for language modeling beyond token-by-token generation.
21
- - **Reasoning & Planning** — Exploring how iterative refinement supports complex reasoning, search, and planning.
22
- - **Code Generation** — Developing diffusion models for code generation and infilling.
23
- - **Multimodal Intelligence** — Extending diffusion language model backbones to vision-language and vision-language-action modeling.
24
-
25
- ## Explore DiffuSpace
26
-
27
- 🌐 [Website](https://diffuspace.ai/) · 📚 [Research](https://diffuspace.ai/research)
28
-
29
- ---
30
-
31
- *Shaping structure from possibilities.*
 
9
 
10
  # DiffuSpace
11
 
12
+ **Beyond autoregression.**
13
 
14
+ We build diffusion language models for more flexible, efficient, and controllable intelligence through parallel generation, bidirectional modeling, and iterative refinement.
15
 
16
+ [Website](https://diffuspace.ai/) · [Research](https://diffuspace.ai/research)