Pinned Loading

1. RLR-Optimizer RLR-Optimizer Public

   Official implementation of "Half-order Fine-Tuning for Diffusion Model: A Recursive Likelihood Ratio Optimizer", accepted by ICLR 2026 (oral presentation)

   Python 14 1

2. FLOPS-Forward-Learning-with-OPtimal-Sampling FLOPS-Forward-Learning-with-OPtimal-Sampling Public

   Official implementation of "FLOPS: Forward Learning with OPtimal Sampling", accepted by ICLR 2025

   Python 8 1

3. RiskPO RiskPO Public

   Official implementation of 'RiskPO: Risk-based Policy Optimization via Verifiable Reward for LLM Post-Training', accepted by ICLR 2026

   Python 17 1