Add pipeline tag

README.md

@@ -1,10 +1,11 @@
 ---
+library_name: hermes
 license: apache-2.0
 tags:
 - ICCV 25
 - Driving World Model
 - Unified Understanding and Generation
-library_name: hermes
+pipeline_tag: image-to-3d
 ---
 
 <div  align="center">    
@@ -48,7 +49,7 @@ Check our *awesome* for the latest World Models! [![Awesome World Model](https:/
 
 ## Abstract
 
-Driving World Models (DWMs) have become essential for autonomous driving by enabling future scene prediction. However, existing DWMs are limited to scene generation and fail to incorporate scene understanding, which involves interpreting and reasoning about the driving environment. In this paper, we present a unified Driving World Model named **HERMES**. Through a unified framework, we seamlessly integrate scene understanding and future scene evolution (generation) in driving scenarios. Specifically, **HERMES** leverages a Bird‘s-Eye View (BEV) representation to consolidate multi-view spatial information while preserving geometric relationships and interactions. Additionally, we introduce world queries, which incorporate world knowledge into BEV features via causal attention in the Large Language Model (LLM), enabling contextual enrichment for both understanding and generation tasks. We conduct comprehensive studies on nuScenes and OmniDrive-nuScenes datasets to validate the effectiveness of our method. **HERMES** achieves state-of-the-art performance, reducing generation error by 32.4% and improving understanding metrics such as CIDEr by 8.0%.
+Driving World Models (DWMs) have become essential for autonomous driving by enabling future scene prediction. However, existing DWMs are limited to scene generation and fail to incorporate scene understanding, which involves interpreting and reasoning about the driving environment. In this paper, we present a unified Driving World Model named **HERMES**. Through a unified framework, we seamlessly integrate scene understanding and future scene evolution (generation) in driving scenarios. Specifically, **HERMES** leverages a Bird's-Eye View (BEV) representation to consolidate multi-view spatial information while preserving geometric relationships and interactions. Additionally, we introduce world queries, which incorporate world knowledge into BEV features via causal attention in the Large Language Model (LLM), enabling contextual enrichment for both understanding and generation tasks. We conduct comprehensive studies on nuScenes and OmniDrive-nuScenes datasets to validate the effectiveness of our method. **HERMES** achieves state-of-the-art performance, reducing generation error by 32.4% and improving understanding metrics such as CIDEr by 8.0%.
 
 ## Overview