Point paper links and citation to the latest PDF viewer

README.md

@@ -16,7 +16,7 @@ tags:
 
 **From imagination to living worlds with agents and fast video generation.**
 
-[Project website](https://murea.ai/) · [GitHub code](https://github.com/Murea-Labs/InWorld) · [Technical report](https://www.researchgate.net/publication/415845088_InWorld_From_Imagination_to_Living_Worlds_with_Agents_and_Fast_Video_Generation) · [中文简介](#中文简介)
+[Project website](https://murea.ai/) · [GitHub code](https://github.com/Murea-Labs/InWorld) · [Technical report](https://murea.ai/page/paper/InWorld-technical-report.pdf) · [中文简介](#中文简介)
 
 Murea-InWorld turns actions and imagination into audiovisual stories. **Murea-Mind** plans each story beat, maintains explicit world memory, and checks generated observations. **Murea-Fast** brings those plans to life as video with synchronized sound, conditioned on text and ordered visual references.
 
@@ -94,7 +94,7 @@ The technical report reports the following results for Murea-Fast:
 | OpenS2V-Eval | Total | 64.98 |
 | OS2V-Pro | Aggregate | 69.9 |
 
-See the [technical report](https://www.researchgate.net/publication/415845088_InWorld_From_Imagination_to_Living_Worlds_with_Agents_and_Fast_Video_Generation) and [project results](https://murea.ai/#results) for the evaluation protocols and comparisons.
+See the [technical report](https://murea.ai/page/paper/InWorld-technical-report.pdf) and [project results](https://murea.ai/#results) for the evaluation protocols and comparisons.
 
 ## Hardware and practical limits
 
@@ -132,7 +132,7 @@ The **Murea-Fast weights and required base components** are governed by the [LTX
   author      = {{Murea Labs}},
   institution = {Murea Labs},
   year        = {2026},
-  url         = {https://murea.ai/}
+  url         = {https://murea.ai/page/paper/InWorld-technical-report.pdf}
 }
 ```