Pinned Loading

1. OPA-DPO OPA-DPO Public

   [CVPR 2025 (Oral)] Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key

   Python 106 4

2. DMBP DMBP Public

   [ICLR 2024] DMBP: Diffusion Model-Based Predictor for Robust Offline Reinforcement Learning against State Observations Perturbations.

   Python 17 1

3. AR-Lopti AR-Lopti Public

   [ICLR 2026] Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs

   Python 41 2