WayneJin0918/SRUM
Official repo of paper "SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models". A post-training framework that creates a cost-effective, self-iterative optimization loop.
SRUM is a post-training framework designed to improve the generative abilities of existing large multimodal models. It takes an already-trained multimodal model and fine-tunes it, using its own understanding capabilities to enhance its generation. The result is a more capable model that can generate higher quality outputs, making it useful for AI researchers and machine learning engineers who work with multimodal AI.
Use this if you are an AI researcher or machine learning engineer looking to enhance the generative performance of unified multimodal models after their initial training.
Not ideal if you are an end-user without experience in AI model fine-tuning or looking for a ready-to-use application.
Stars
96
Forks
6
Language
Python
License
Apache-2.0
Category
Last pushed
Nov 26, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/WayneJin0918/SRUM"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
agentscope-ai/Trinity-RFT
Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement...
OpenRLHF/OpenRLHF
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO &...
zjunlp/EasyEdit
[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.
huggingface/alignment-handbook
Robust recipes to align language models with human and AI preferences
hyunwoongko/nanoRLHF
nanoRLHF: from-scratch journey into how LLMs and RLHF really work.