Instructions to use Kunyang-YU/LookStep with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Kunyang-YU/LookStep with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="Kunyang-YU/LookStep")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Kunyang-YU/LookStep")
model = AutoModelForMultimodalLM.from_pretrained("Kunyang-YU/LookStep", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Kunyang-YU/LookStep with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Kunyang-YU/LookStep"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kunyang-YU/LookStep",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/Kunyang-YU/LookStep

SGLang

How to use Kunyang-YU/LookStep with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Kunyang-YU/LookStep" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kunyang-YU/LookStep",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Kunyang-YU/LookStep" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kunyang-YU/LookStep",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use Kunyang-YU/LookStep with Docker Model Runner:
```
docker model run hf.co/Kunyang-YU/LookStep
```

LookStep

简体中文

This is the official checkpoint for the paper LookStep: Efficient Vision-Language Navigation with Linguistic Foresight and Event Driven Memory. The code is available at https://github.com/kunyang-YU/LookStep.

Model details

Field	Value
Base model	`Qwen/Qwen3-VL-8B-Instruct`
Architecture	`Qwen3VLForConditionalGeneration`
Model type	`qwen3_vl`
Parameters	8,767,123,696
Checkpoint format	safetensors, 4 shards, 750 tensors
Indexed tensor bytes	17,534,247,392 bytes
Fine-tuning method	Full-parameter SFT (`tuner_type=full`)
Final optimizer step	18,888
Training epoch	1.0
Training precision	BF16
Training max length	8,192 tokens
Input modality	Navigation instruction plus front-facing RGB observations
Output	Structured LookStep state, candidate outcomes, memory decision, and action

The online policy receives the instruction, up to six long-term event-memory frames, up to two recent frames, and the current RGB frame. It generates:

<progress>...</progress>
<event>...</event>
<memory_write>keep|drop</memory_write>
<memory_role>...</memory_role>
<outcomes>
  <move_forward>...</move_forward>
  <turn_left>...</turn_left>
  <turn_right>...</turn_right>
  <stop>...</stop>
</outcomes>
<action>MOVE_FORWARD|TURN_LEFT|TURN_RIGHT|STOP</action>

Use this checkpoint with the LookStep simulation code to reproduce the paper's R2R-CE and RxR-CE Val-Unseen main results. It is intended for research in embodied vision-language navigation under the published Habitat configuration.

It is not a general-purpose chatbot, a standalone image captioner, a safety
controller, or a validated controller for physical robots.

Training procedure

Hyperparameter	Value
GPUs	8 × NVIDIA A100 80 GB
Epochs	1
Per-device train batch size	2
Gradient accumulation	8
Global batch size	128
Optimizer steps	18,888
Optimizer	`adamw_torch_fused`
Learning rate	`2e-5`
Scheduler	cosine
Warmup ratio	0.03
Weight decay	0.01
Adam betas / epsilon	0.9, 0.95 / `1e-8`
Max gradient norm	1.0
Distributed training	DeepSpeed ZeRO-2
Vision encoder	frozen
Visual aligner	frozen
LLM	trainable
Model/data seeds	42 / 42

Reproduce with LookStep

Create the pinned environment and validate the downloaded model first:

conda env create -f LookStep/simulation/environment.yml
conda activate lookstep-simulation

MODEL_PATH=/path/to/downloaded/checkpoint-18888 \
PROCESSOR_PATH=/path/to/Qwen3-VL-8B-Instruct \
DATA_ROOT=/path/to/data \
bash LookStep/reproduce_paper.sh check-sim

Run a two-episode smoke test, followed by both complete main benchmarks:

MODEL_PATH=/path/to/downloaded/checkpoint-18888 \
PROCESSOR_PATH=/path/to/Qwen3-VL-8B-Instruct \
DATA_ROOT=/path/to/data \
bash LookStep/reproduce_paper.sh smoke-r2r

MODEL_PATH=/path/to/downloaded/checkpoint-18888 \
PROCESSOR_PATH=/path/to/Qwen3-VL-8B-Instruct \
DATA_ROOT=/path/to/data \
CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 \
bash LookStep/reproduce_paper.sh eval-all

bash LookStep/reproduce_paper.sh verify

Citation

@inproceedings{
lookstep,
title={LookStep: Efficient Vision-Language Navigation with Linguistic Foresight and Event Driven Memory},
author={Kun-Yang Yu, Yingzhe Li, Hongyu Xu, Shi-Yu Tian, Zhi Zhou, Yang Chen, Ming Yang, Sheng Wang, Qing Yu, Lan-Zhe Guo, Yu-Feng Li},
booktitle={The 2026 Conference on Empirical Methods in Natural Language Processing},
year={2026}
}

If you have any question, please email to yuky@lamda.nju.edu.cn (Kun-Yang Yu)

Downloads last month: 28

Safetensors

Model size

9B params

Tensor type

BF16

Model tree for Kunyang-YU/LookStep

Base model

Qwen/Qwen3-VL-8B-Instruct

Finetuned

(579)

this model

Paper for Kunyang-YU/LookStep

LookStep: Efficient Vision-Language Navigation with Linguistic Foresight and Event Driven Memory

Paper • 2609.02350 • Published 5 days ago