Skip to content

Pinned Loading

  1. understand-r1-zero Public

    Understanding R1-Zero-Like Training: A Critical Perspective

    Python 882 42

  2. zero-bubble-pipeline-parallelism Public

    Forked from NVIDIA/Megatron-LM

    Zero Bubble Pipeline Parallelism

    Python 385 24

  3. lorahub Public

    [COLM 2024] LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition

    Python 628 39

  4. envpool Public

    C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.

    C++ 1.1k 108

  5. EditAnything Public

    Edit anything in images powered by segment-anything, ControlNet, StableDiffusion, etc. (ACM MM)

    Python 3.4k 197

  6. Adan Public

    Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models

    Python 789 67

Repositories

Showing 10 of 85 repositories
  • FlowReasoner Public
    Python 76 6 0 0 Updated Apr 23, 2025
  • jrystal Public

    A JAX-based Differentiable Density Functional Theory Framework for Materials

    Python 12 Apache-2.0 1 5 3 Updated Apr 22, 2025
  • Python 27 1 0 0 Updated Apr 22, 2025
  • LightTrans Public

    The official implementation of "LightTransfer: Your Long-Context LLM is Secretly a Hybrid Model with Effortless Adaptation"

    Python 19 0 0 0 Updated Apr 22, 2025
  • oat Public

    🌾 OAT: A research-friendly framework for LLM online alignment, including preference learning, reinforcement learning, etc.

    Python 331 Apache-2.0 22 4 2 Updated Apr 20, 2025
  • TreeMeshGPT Public

    [CVPR 2025] TreeMeshGPT: Artistic Mesh Generation with Autoregressive Tree Sequencing

    Python 131 MIT 6 3 0 Updated Apr 16, 2025
  • ActivePRM Public
    Jupyter Notebook 15 0 0 0 Updated Apr 16, 2025
  • understand-r1-zero Public

    Understanding R1-Zero-Like Training: A Critical Perspective

    Python 882 MIT 42 4 0 Updated Apr 15, 2025
  • dice Public

    Official implementation of Bootstrapping Language Models via DPO Implicit Rewards

    Python 43 MIT 3 0 0 Updated Apr 15, 2025
  • oat-zero Public

    A lightweight reproduction of DeepSeek-R1-Zero with indepth analysis of self-reflection behavior.

    Python 229 MIT 10 0 0 Updated Apr 15, 2025

Top languages

Loading…

Most used topics

Loading…