GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
IffYuan
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
IffYuan
Model Tree
Qwen/Qwen3-VL-8B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Embodied-R1.5 is a unified Embodied Foundation Model (EFM), built on Qwen3-VL-8B-Instruct, that integrates comprehensive embodied reasoning within a single architecture. Building on our prior work Embodied-R1, it leaps from a pointing specialist to a comprehensive EFM unifying three core capabilities:
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 π0.5 across 4 manipulation benchmark suites; and it generalizes zero-shot to real robots on instruction following, affordance grounding, articulated manipulation, and long-horizon tasks.
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:
| Task Type | Answer Format (inside <answer>) |
|---|---|
multiple choice | A |
numerical | 3.14 |
open-ended | free text |
math | $$-\dfrac{3}{2}$$ |
Coordinate & unit conventions. All points (
point_2d) and boxes are normalized to the[0, 1000]range, regardless of the original image resolution. Fortrace_3d, thedepthvalue is in meters.
python
from transformers import AutoModelForImageTextToText, AutoProcessorfrom PIL import Imagemodel_id = "IffYuan/Embodied-R1.5-8B-SFT"model = AutoModelForImageTextToText.from_pretrained(model_id, torch_dtype="auto", device_map="auto")processor = AutoProcessor.from_pretrained(model_id)image = Image.open("scene.jpg")messages = [{"role": "user","content": [{"type": "image"},{"type": "text", "text": "You are a robot performing manipulation tasks. ""The task instruction is: move the blue cube on top of the yellow cube. ""Use 2D points to mark the target location."},],}]text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = processor(text=[text], images=[image], return_tensors="pt").to(model.device)out = model.generate(**inputs, max_new_tokens=512)print(processor.batch_decode(out, skip_special_tokens=True)[0])
The model reasons over the visual observation and emits its final decision within an <answer> tag, e.g. <answer>[{"point_2d": [750, 748]}]</answer>.
For higher throughput, serve the model with vLLM:
bash
vllm serve IffYuan/Embodied-R1.5-8B-SFT \--served-model-name "Embodied-R1.5-8B-SFT" \--tensor-parallel-size 1 \--mm-encoder-tp-mode data \--gpu-memory-utilization 0.7 \--async-scheduling \--media-io-kwargs '{"video": {"num_frames": 32}, "image": {"max_num": 32}}' \--max_model_len 20000 \--limit-mm-per-prompt '{"image": 8, "video": 1}' \--host 0.0.0.0 --port 22002
More runnable examples (vLLM online / offline, HuggingFace, point decoding & visualization) are provided in the GitHub repository under inference/.
For benchmark evaluation, see EmbodiedEvalKit, our evaluation framework covering 25+ embodied benchmarks.
Embodied-R1.5 is trained in two stages: SFT (LLaMA-Factory) followed by RFT (EasyR1). This checkpoint is the Stage 1 SFT model. Full training scripts are available in the GitHub repository. Datasets are released in the Embodied-R1.5 HuggingFace collection.
If you find Embodied-R1.5 useful in your research, please cite our work:
bibtex
@article{yuan2026embodiedr15,title={Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models},author={Yuan, Yifu and Huang, Yaoting and Yao, Xianze and Zhang, Shuoheng and Han, Linqi and Li, Yutong and Li, Pengyi and Sun, Jiangeng and Jia, Wenting and Hu, Yucheng and Liu, Yuhao and Liao, Ruihao and Wu, Qiyu and Li, Yuxiao and Zhang, Zhao and Dong, Zibin and Ni, Fei and Zheng, Yan and Gu, Shuyang and Ma, Yi and Tang, Hongyao and Hu, Han and Hao, Jianye},journal={arXiv preprint},year={2026}}@article{yuan2025embodied,title={Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation},author={Yuan, Yifu and Cui, Haiqin and Huang, Yaoting and Chen, Yibin and Ni, Fei and Dong, Zibin and Li, Pengyi and Zheng, Yan and Hao, Jianye},journal={ICLR 2026},year={2025}}@article{yuan2025seeing,title={From Seeing to Doing: Bridging Reasoning and Decision for Robotic Manipulation},author={Yuan, Yifu and Cui, Haiqin and Chen, Yibin and Dong, Zibin and Ni, Fei and Kou, Longxin and Liu, Jinyi and Li, Pengyi and Zheng, Yan and Hao, Jianye},journal={ICLR 2026},year={2025}}
Released under the Apache 2.0 license.
spatial grounding{"boxes": [35, 227, 437, 932]} |
point | ```json\n[{"point_2d": [230, 138]}]\n``` |
trace | ```json\n[{"point_2d": [624, 469]}, ...]\n``` |
trace_3d | ```json\n[{"point_2d": [463, 599], "depth": 1.08}, ...]\n``` |