hzxllll

DEFT-RLVR-model-HF

README

License: apache-2.0

Overview

Autonomous-driving reasoning supervision often reveals the logged ground-truth future trajectory before asking a vision-language model to explain its decision. Our paper identifies this as trajectory anchoring bias: the model can rationalize a known outcome instead of inferring a causally faithful decision from scene evidence.

We introduce two components:

AD-MCQ formulates planning as an exactly verifiable selection among explicit candidate trajectories.
DEFT-RLVR requires the policy to reason about the scene and commit to a high-level driving decision before candidate trajectories are revealed for grounding and verification.

This checkpoint is intended for research on autonomous-driving visual reasoning, candidate-grounded decision making, and reinforcement learning with verifiable rewards.

Resources

Code: github.com/hzx122/DEFT-RLVR
Dataset: hzxllll/AD-MCQ
Base model: Qwen/Qwen3-VL-8B-Instruct

Model Details

Table with columns: Item, Description
Item	Description
Architecture	Qwen3VLForConditionalGeneration
Base model	Qwen3-VL-8B-Instruct
Training method	DEFT-RLVR
Training task	Candidate-trajectory multiple-choice reasoning
Input	Multi-view driving visual context and text instructions
Output	Scene-grounded reasoning and candidate selection
License	Apache 2.0

Usage

Install a Transformers version that supports Qwen3-VL, then load the checkpoint with the standard Hugging Face API:

python
import torch
from transformers import AutoProcessor, Qwen3VLForConditionalGeneration

model_id = "hzxllll/DEFT-RLVR-model-HF"

processor = AutoProcessor.from_pretrained(model_id)
model = Qwen3VLForConditionalGeneration.from_pretrained(
    model_id,
    dtype=torch.bfloat16,
    device_map="auto",
)

messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "image": "path/to/driving_frame.jpg"},
            {"type": "text", "text": "Describe the driving scene and determine the appropriate high-level driving decision."},
        ],
    }
]

inputs = processor.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    return_dict=True,
    return_tensors="pt",
).to(model.device)

with torch.no_grad():
    generated_ids = model.generate(**inputs, max_new_tokens=512)

generated_ids = generated_ids[:, inputs.input_ids.shape[1]:]
print(processor.batch_decode(generated_ids, skip_special_tokens=True)[0])

For the paper's two-turn DEFT protocol and AD-MCQ candidate format, use the prompts and evaluation code provided in the project repository.

Intended Use

The checkpoint is released for research in:

autonomous-driving scene understanding and causal reasoning;
candidate-trajectory selection;
multimodal reasoning evaluation;
RLVR and process-supervised policy adaptation.

Citation

bibtex
@misc{huang2026deftrlvr,
  title        = {Deferred Exposure of Future Trajectories for Verifiable Reasoning in Autonomous Driving VLMs},
  author       = {Huang, Zixuan and Zhou, Yang and Wang, Kaixuan and Zhang, Guli and Xie, Hongyan and Zhu, Yakun and Geng, Hao and Ban, Yikun and Wang, Deqing},
  year         = {2026},
  howpublished = {Preprint}
}

Acknowledgements

This model is built on Qwen3-VL-8B-Instruct. We thank the Qwen team and the open-source community for their contributions.

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Container

Run this model inference with full control and performance in your environment.

Learn more

Model Details

Model Provider

hzxllll

Model Tree

Base

Qwen/Qwen3-VL-8B-Instruct

Fine-tuned

this model

Input Modalities

TextImage

Output Modalities

Text

Supported Functionality

Dedicated EndpointsContainer

Explore FriendliAI today

Get started Talk to an engineer

README

License: apache-2.0

Overview

We introduce two components:

AD-MCQ formulates planning as an exactly verifiable selection among explicit candidate trajectories.
DEFT-RLVR requires the policy to reason about the scene and commit to a high-level driving decision before candidate trajectories are revealed for grounding and verification.

This checkpoint is intended for research on autonomous-driving visual reasoning, candidate-grounded decision making, and reinforcement learning with verifiable rewards.

Resources

Code: github.com/hzx122/DEFT-RLVR
Dataset: hzxllll/AD-MCQ
Base model: Qwen/Qwen3-VL-8B-Instruct

Model Details

Table with columns: Item, Description
Item	Description
Architecture	Qwen3VLForConditionalGeneration
Base model	Qwen3-VL-8B-Instruct
Training method	DEFT-RLVR
Training task	Candidate-trajectory multiple-choice reasoning
Input	Multi-view driving visual context and text instructions
Output	Scene-grounded reasoning and candidate selection
License	Apache 2.0

Usage

Install a Transformers version that supports Qwen3-VL, then load the checkpoint with the standard Hugging Face API:

python
import torch
from transformers import AutoProcessor, Qwen3VLForConditionalGeneration

model_id = "hzxllll/DEFT-RLVR-model-HF"

processor = AutoProcessor.from_pretrained(model_id)
model = Qwen3VLForConditionalGeneration.from_pretrained(
    model_id,
    dtype=torch.bfloat16,
    device_map="auto",
)

messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "image": "path/to/driving_frame.jpg"},
            {"type": "text", "text": "Describe the driving scene and determine the appropriate high-level driving decision."},
        ],
    }
]

inputs = processor.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    return_dict=True,
    return_tensors="pt",
).to(model.device)

with torch.no_grad():
    generated_ids = model.generate(**inputs, max_new_tokens=512)

generated_ids = generated_ids[:, inputs.input_ids.shape[1]:]
print(processor.batch_decode(generated_ids, skip_special_tokens=True)[0])

For the paper's two-turn DEFT protocol and AD-MCQ candidate format, use the prompts and evaluation code provided in the project repository.

Intended Use

The checkpoint is released for research in:

autonomous-driving scene understanding and causal reasoning;
candidate-trajectory selection;
multimodal reasoning evaluation;
RLVR and process-supervised policy adaptation.

Citation

bibtex
@misc{huang2026deftrlvr,
  title        = {Deferred Exposure of Future Trajectories for Verifiable Reasoning in Autonomous Driving VLMs},
  author       = {Huang, Zixuan and Zhou, Yang and Wang, Kaixuan and Zhang, Guli and Xie, Hongyan and Zhu, Yakun and Geng, Hao and Ban, Yikun and Wang, Deqing},
  year         = {2026},
  howpublished = {Preprint}
}

Acknowledgements

This model is built on Qwen3-VL-8B-Instruct. We thank the Qwen team and the open-source community for their contributions.