Add library_name to metadata and improve model card links

README.md

@@ -1,16 +1,17 @@
 ---
-license: apache-2.0
+base_model:
+- Qwen/Qwen3-VL-4B-Instruct
 language:
 - en
+license: apache-2.0
+pipeline_tag: image-text-to-text
+library_name: transformers
 tags:
 - autonomous-driving
 - vision-language-action
 - chain-of-thought
 - trajectory-prediction
 - VLA
-base_model:
-- Qwen/Qwen3-VL-4B-Instruct
-pipeline_tag: image-text-to-text
 ---
 
 # OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation
@@ -90,15 +91,6 @@ Staged training is essential — ablation shows that skipping it collapses PDM-s
 | AR CoT+Answer | 2.99 | 8.54 | 3.51 |
 | **OneVL** | **2.62** | 7.53 | **3.26** |
 
-### CoT Text Quality (NAVSIM)
-
-| Method | Meta Action Acc. ↑ | STS Score ↑ | LLM Judge ↑ | Latency (s) ↓ |
-|---|:---:|:---:|:---:|:---:|
-| AR CoT+Answer | 73.20 | 79.75 | 81.86 | 6.58 |
-| **OneVL** | 71.00 | 78.26 | 79.13 | **4.46** |
-
-OneVL's language auxiliary decoder recovers 97% of explicit CoT quality at answer-only inference speed.
-
 ---
 
 ## Usage
@@ -144,25 +136,7 @@ python infer_onevl.py \
     --c_thought_visual 4 --max_visual_tokens 2560
 ```
 
-### Multi-GPU Inference
-
-```bash
-export MODEL_PATH=/path/to/OneVL-checkpoint
-export TEST_SET_PATH=test_data/navsim_test.json
-export OUTPUT_PATH=output/navsim/navsim_results.json
-bash run_infer.sh
-```
-
-Per-benchmark scripts are available in `scripts/`:
-
-```bash
-bash scripts/infer_navsim.sh
-bash scripts/infer_ar1.sh
-bash scripts/infer_roadwork.sh
-bash scripts/infer_impromptu.sh
-```
-
-For full documentation, evaluation scripts, and data format details, see the [GitHub repository](https://github.com/xiaomi-research/onevl).
+For full documentation, evaluation scripts, and data format details, see the [official GitHub repository](https://github.com/xiaomi-research/onevl).
 
 ---
 
@@ -195,4 +169,4 @@ For full documentation, evaluation scripts, and data format details, see the [Gi
 
 Released under the [Apache 2.0 License](https://www.apache.org/licenses/LICENSE-2.0).
 
-Model weights are built on [Qwen3-VL-4B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-4B-Instruct) and the visual tokenizer is from [Emu3.5-VisionTokenizer](https://huggingface.co/BAAI/Emu3.5-VisionTokenizer); please refer to their respective licenses as well.
+Model weights are built on [Qwen3-VL-4B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-4B-Instruct) and the visual tokenizer is from [Emu3.5-VisionTokenizer](https://huggingface.co/BAAI/Emu3.5-VisionTokenizer); please refer to their respective licenses as well.