andrewliao11/LongPerceptualThoughts
[COLM'25] The official implementation of "LongPerceptualThoughts: Distilling System-2 Reasoning for System-1 Perception"
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.
Stars
11
Forks
2
Language
Python
License
Apache-2.0
Category
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.
Higher-rated alternatives
cvs-health/uqlm
UQLM: Uncertainty Quantification for Language Models, is a Python package for UQ-based LLM...
PRIME-RL/TTRL
[NeurIPS 2025] TTRL: Test-Time Reinforcement Learning
sapientinc/HRM
Hierarchical Reasoning Model Official Release
tigerchen52/query_level_uncertainty
query-level uncertainty in LLMs
reasoning-survey/Awesome-Reasoning-Foundation-Models
✨✨Latest Papers and Benchmarks in Reasoning with Foundation Models