Skip to content

BASHLab/OWL

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Accepted at International Conference on Learning Representations (ICLR), 2026


🚀 Main Results

Comparison of OWL with closed- and open-source baselines on BiDepth across four task types: Type I (event detection), Type II (direction estimation), Type III (spatial reasoning), and Type IV (CoT reasoning). OWL consistently surpasses prior open-source models, with further gains from CoT supervision. Best results are in bold.

Zero-shot Performance of OWL on the SpatialSoundQA across perception and reasoning tasks. OWL consistently outperforms the baselines, with larger gains in spatial reasoning tasks, demonstrating the benefit of the SAGE and CoT instruction tuning. Best results are denoted in bold.

Installation

git clone https://github.com/BASHLab/OWL.git
cd OWL

python -m venv venv
source venv/bin/activate

git clone https://github.com/huggingface/transformers.git
cd transformers
git checkout tags/v4.35.2
pip install -e .

cd ..
git clone https://github.com/huggingface/peft.git
cd peft
git checkout tags/v0.6.0
pip install -e .

cd seld_cot/owl
pip install -r requirements.txt
cd ../../

pip install  -e .

📁 BiDepth Dataset

BiDepth

🍀 Model Zoo

Model Name
SAGE
OWL-LLaMA2-7B
OWL-LLaMA3.2-3B
OWL-Qwen2.5-7B-Instruct
OWL-LLaMA2.5-3B

👍 Acknowledgement

The codebase of OWL is adapted from SLAM-LLM. We are also grateful for their contribution.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors