Skip to content
@thu-ml

TSAIL group

Tsinghua Statistical Artificial Intelligence & Learning Group

Pinned Loading

  1. zhusuan zhusuan Public

    A probabilistic programming library for Bayesian deep learning, generative models, based on Tensorflow

    Python 2.2k 419

  2. unidiffuser unidiffuser Public

    Code and models for the paper "One Transformer Fits All Distributions in Multi-Modal Diffusion"

    Python 1.4k 88

  3. prolificdreamer prolificdreamer Public

    ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation (NeurIPS 2023 Spotlight)

    Python 1.5k 45

  4. SageAttention SageAttention Public

    Quantized Attention that achieves speedups of 2.1-3.1x and 2.7-5.1x compared to FlashAttention2 and xformers, respectively, without lossing end-to-end metrics across various models.

    Cuda 1k 64

  5. ares ares Public

    A Python library for adversarial machine learning focusing on benchmarking adversarial robustness.

    Python 499 87

  6. tianshou tianshou Public

    An elegant PyTorch deep reinforcement learning library.

    Python 8.2k 1.1k

Repositories

Showing 10 of 72 repositories
  • MMTrustEval Public

    A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)

    thu-ml/MMTrustEval’s past year of commit activity
    Python 131 CC-BY-SA-4.0 8 3 0 Updated Mar 3, 2025
  • RIFLEx Public

    Official implementation for "RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers"

    thu-ml/RIFLEx’s past year of commit activity
    Python 232 Apache-2.0 25 7 0 Updated Mar 3, 2025
  • TetraJet-MXFP4Training Public

    Pytorch implementation of "Oscillation-Reduced MXFP4 Training for Vision Transformers" on DeiT Model Pre-training

    thu-ml/TetraJet-MXFP4Training’s past year of commit activity
    Python 5 Apache-2.0 0 0 0 Updated Mar 3, 2025
  • tianshou Public

    An elegant PyTorch deep reinforcement learning library.

    thu-ml/tianshou’s past year of commit activity
    Python 8,237 MIT 1,136 144 (1 issue needs help) 4 Updated Mar 3, 2025
  • SpargeAttn Public

    SpargeAttention: A training-free sparse attention that can accelerate any model inference.

    thu-ml/SpargeAttn’s past year of commit activity
    Cuda 203 Apache-2.0 5 8 0 Updated Mar 1, 2025
  • SageAttention Public

    Quantized Attention that achieves speedups of 2.1-3.1x and 2.7-5.1x compared to FlashAttention2 and xformers, respectively, without lossing end-to-end metrics across various models.

    thu-ml/SageAttention’s past year of commit activity
    Cuda 1,044 Apache-2.0 64 34 1 Updated Feb 28, 2025
  • STAIR Public

    Official codebase for "STAIR: Improving Safety Alignment with Introspective Reasoning"

    thu-ml/STAIR’s past year of commit activity
    Python 22 MIT 1 0 0 Updated Feb 26, 2025
  • EffWRN-paddle Public
    thu-ml/EffWRN-paddle’s past year of commit activity
    Python 0 MIT 0 0 0 Updated Feb 24, 2025
  • thu-ml/RIFLEx.github.io’s past year of commit activity
    JavaScript 0 0 0 0 Updated Feb 21, 2025
  • oddefense Public
    thu-ml/oddefense’s past year of commit activity
    Jupyter Notebook 1 MIT 0 0 0 Updated Feb 14, 2025