Remove Model Details section from model card
Browse files
README.md
CHANGED
|
@@ -39,14 +39,6 @@ base_model:
|
|
| 39 |
|
| 40 |
Trained on a 15B-token corpus with a multi-task balanced RL recipe, it further drives a **Planner-Grounder-Corrector (PGC)** closed-loop framework where one model acts as planner, grounder, and corrector to autonomously complete long-horizon real-world tasks. With only 8B parameters, Embodied-R1.5 is best on **16 of 24** embodied VLM benchmarks (avg. **70.4%**), surpassing Gemini-Robotics-ER-1.5 and GPT-5.4; with light action-data fine-tuning it adapts into **Embodied-R1.5-VLA**, outperforming strong baselines like $\pi_{0.5}$ across 4 manipulation benchmark suites; and it generalizes zero-shot to real robots on instruction following, affordance grounding, articulated manipulation, and long-horizon tasks.
|
| 41 |
|
| 42 |
-
## Model Details
|
| 43 |
-
|
| 44 |
-
- **Architecture:** Qwen3-VL (`Qwen3VLForConditionalGeneration`)
|
| 45 |
-
- **Parameters:** ~8B
|
| 46 |
-
- **Base model:** Qwen/Qwen3-VL-8B-Instruct
|
| 47 |
-
- **Modality:** Image / Video + Text → Text
|
| 48 |
-
- **Output format:** All outputs are plain-text token sequences, with the final decision emitted within an `<answer>...</answer>` tag.
|
| 49 |
-
|
| 50 |
## Output Conventions
|
| 51 |
|
| 52 |
Embodied-R1.5 follows the Qwen3-VL chat format and outputs structured answers inside `<answer>...</answer>` tags. The supported task types and their answer formats are:
|
|
|
|
| 39 |
|
| 40 |
Trained on a 15B-token corpus with a multi-task balanced RL recipe, it further drives a **Planner-Grounder-Corrector (PGC)** closed-loop framework where one model acts as planner, grounder, and corrector to autonomously complete long-horizon real-world tasks. With only 8B parameters, Embodied-R1.5 is best on **16 of 24** embodied VLM benchmarks (avg. **70.4%**), surpassing Gemini-Robotics-ER-1.5 and GPT-5.4; with light action-data fine-tuning it adapts into **Embodied-R1.5-VLA**, outperforming strong baselines like $\pi_{0.5}$ across 4 manipulation benchmark suites; and it generalizes zero-shot to real robots on instruction following, affordance grounding, articulated manipulation, and long-horizon tasks.
|
| 41 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
## Output Conventions
|
| 43 |
|
| 44 |
Embodied-R1.5 follows the Qwen3-VL chat format and outputs structured answers inside `<answer>...</answer>` tags. The supported task types and their answer formats are:
|