Fr0zenCrane/UniCoT
[ICLR 2026] Uni-CoT: Towards Unified Chain-of-Thought Reasoning Across Text and Vision
This project helps people who need to create images or understand complex visual information by providing a system that can think through problems step-by-step using both text and images. You provide it with a prompt and possibly some images, and it will generate an image or provide a detailed explanation of a visual scenario. This tool is for researchers and developers working on advanced AI models that need to perform complex reasoning tasks involving both language and visuals.
214 stars.
Use this if you are a researcher or AI developer working on multimodal large language models and need a framework for interpretable, step-by-step reasoning that integrates both textual and visual information for tasks like image generation, editing, or complex visual analysis.
Not ideal if you are looking for an off-the-shelf application for simple image generation or editing, or if you do not have experience with advanced AI model development.
Stars
214
Forks
4
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 11, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/Fr0zenCrane/UniCoT"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
SimonAytes/SoT
Official code repository for Sketch-of-Thought (SoT)
xuyige/SoftCoT
ACL'2025: SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs. and preprint:...
logikon-ai/cot-eval
A framework for evaluating the effectiveness of chain-of-thought reasoning in language models.
nicolay-r/THOR-ECAC
The official fork of THoR Chain-of-Thought framework, enhanced and adapted for Emotion Cause...
andrewginns/CoT-at-Home
Who needs o1 anyways. Add CoT to any OpenAI compatible endpoint.