andrewliao11/LongPerceptualThoughts

[COLM'25] The official implementation of "LongPerceptualThoughts: Distilling System-2 Reasoning for System-1 Perception"

35
/ 100
Emerging

This project offers a data engine to create extensive 'Chain-of-Thoughts' (CoTs) datasets specifically designed for training visual reasoning models. It takes image-caption datasets as input and generates multiple-choice questions along with detailed reasoning paths. This tool is for researchers and machine learning engineers developing or evaluating AI systems that need to understand and explain visual information.

No commits in the last 6 months.

Use this if you need to generate complex, step-by-step reasoning data to improve the perceptual and analytical capabilities of your visual AI models.

Not ideal if you are looking for a pre-trained, ready-to-use visual reasoning model rather than a tool to generate training data.

visual reasoning AI model training explainable AI computer vision large language models
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

11

Forks

2

Language

Python

License

Apache-2.0

Last pushed

Aug 04, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/andrewliao11/LongPerceptualThoughts"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.