Skip to content
@thu-ml

TSAIL group

Tsinghua Statistical Artificial Intelligence & Learning Group

Pinned Loading

  1. zhusuan Public

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

    Python 2.2k 421

  2. SageAttention Public

    Quantized Attention achieves speedup of 2-5x and 3-11x compared to FlashAttention and xformers, without lossing end-to-end metrics across language, image, and video models.

    Cuda 2.2k 189

  3. unidiffuser Public

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

    Python 1.4k 89

  4. prolificdreamer Public

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

    Python 1.5k 46

  5. ares Public

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

    Python 513 87

  6. tianshou Public

    An elegant PyTorch deep reinforcement learning library.

    Python 8.7k 1.2k

Repositories

Showing 10 of 78 repositories
  • SpargeAttn Public

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

    Cuda 681 Apache-2.0 52 31 4 Updated Aug 13, 2025
  • tianshou Public

    An elegant PyTorch deep reinforcement learning library.

    Python 8,700 MIT 1,170 136 (1 issue needs help) 5 Updated Aug 6, 2025
  • SageAttention Public

    Quantized Attention achieves speedup of 2-5x and 3-11x compared to FlashAttention and xformers, without lossing end-to-end metrics across language, image, and video models.

    Cuda 2,207 Apache-2.0 189 84 11 Updated Aug 5, 2025
  • EmbodiedActiveDefense Public

    Official implementation for "Reinforced Embodied Active Defense: Exploiting Adaptive Interaction for Robust Visual Perception in Adversarial 3D Environments" (TPAMI 2025)

    Python 3 MIT 0 0 0 Updated Jul 26, 2025
  • oddefense Public
    Jupyter Notebook 3 MIT 1 0 0 Updated Jul 16, 2025
  • SparseDM Public
    Python 1 0 0 0 Updated Jul 7, 2025
  • Adaptive-Sparse-Trainer Public

    Official implementation for "Pruning Large Language Models with Semi-Structural Adaptive Sparse Training" (AAAI 2025)

    Python 12 Apache-2.0 1 0 0 Updated Jul 1, 2025
  • MLA-Trust Public

    A toolbox for benchmarking Multimodal LLM Agents trustworthiness across truthfulness, controllability, safety and privacy dimensions through 34 interactive tasks

    Python 47 MIT 4 1 0 Updated Jun 30, 2025
  • MMTrustEval Public

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

    Python 159 CC-BY-SA-4.0 10 1 0 Updated Jun 27, 2025
  • TetraJet-MXFP4Training Public

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

    Python 24 Apache-2.0 3 0 0 Updated Jun 20, 2025