Thanks to visit codestin.com
Credit goes to github.com

Skip to content

@ernie-research ERNIE Research

Change the repository type filter

All

    Repositories list

    5 repositories

    • CD-RLHF

      Public
      [ACL'25] Official code of curiosity-driven RLHF
      Python
      •
      MIT License
      •0•12•0•0•Updated Jun 22, 2025Jun 22, 2025

    • pixelgpt

      Public
      [EMNLP'24] Autoregressive Pre-Training on Pixels and Texts
      Python
      •
      MIT License
      •1•5•1•0•Updated Jun 6, 2025Jun 6, 2025

    • gptfluence

      Public
      [EMNLP'24 oral] On Training Data Influence of GPT Models
      Python
      •
      MIT License
      •0•8•0•0•Updated Jun 6, 2025Jun 6, 2025

    • Tool-Augmented-Reward-Model

      Public
      [ICLR'24 spotlight] Tool-Augmented Reward Modeling
      rlhfreward-modelsllm-training
      Python
      •
      MIT License
      •1•51•0•0•Updated Jun 6, 2025Jun 6, 2025

    • MA-RLHF

      Public
      [ICLR'25] MA-RLHF: Reinforcement Learning from Human Feedback with Macro Actions
      pporlhfllm-trainingma-rlhfposttrain
      Python
      •
      MIT License
      •0•9•0•0•Updated Jun 6, 2025Jun 6, 2025