AQuA-Qwen

     

This model is a fine-tuned version of Qwen2.5-VL-3B-Instruct on the AQuA dataset, trained to generate strategic responses to ambiguous visual questions.

Usage

import torch
from transformers import Qwen2_5_VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
    "jihyoung/AQuA-Qwen",
    torch_dtype=torch.bfloat16,
    attn_implementation="flash_attention_2",
    device_map="auto",
)

processor = AutoProcessor.from_pretrained("jihyoung/AQuA-Qwen")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "http://images.cocodataset.org/train2017/000000539311.jpg",
            },
            {"type": "text", "text": "What color is this bat?"},
        ],
    }
]

text = processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    return_tensors="pt",
)
inputs = inputs.to("cuda")

generated_ids = model.generate(**inputs, max_new_tokens=512)
generated_ids_trimmed = [
    out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_text[0].strip())

Citation

If you use this model in your research, please cite:

@inproceedings{
  jang2026aqua,
  title={{AQ}uA: Toward Strategic Response Generation for Ambiguous Visual Questions},
  author={Jihyoung Jang and Hyounghun Kim},
  booktitle={The Fourteenth International Conference on Learning Representations},
  year={2026},
  url={https://openreview.net/forum?id=7b1MpD6IF8}
}