A Research Group for AI+ Frameworks

All

3 repositories

DEEP-GRPO
Public
Deep Dense Exploration for LLM Reinforcement Learning via Pivot-Driven Resampling
reinforcement-learning reasoning llm
reinforcement-learning reasoning llm grpo
0•0•0•0•Updated Feb 24, 2026Feb 24, 2026
CorgiPile
Public
A New DataSet API with Efficient Shuffle Mechanism for PyTorch (SGD/Adam without Full Data Shuffle)
deep-learning pytorch shuffle
deep-learning pytorch shuffle
Python
•0•0•0•0•Updated Oct 20, 2025Oct 20, 2025
SPO
Public
Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models
framework reinforcement-learning llm
framework reinforcement-learning llm
Python
•
MIT License
•5•46•3•0•Updated Sep 19, 2025Sep 19, 2025

ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.

⚡