Skip to content

@thu-ml TSAIL group

Change the repository type filter

All

    Repositories list

    66 repositories

    • STAIR

      Public
      Official codebase for "STAIR: Improving Safety Alignment with Introspective Reasoning"
      MIT License
      •0•1•0•0•Updated Feb 4, 2025Feb 4, 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.
      cudatritonattentionquantizationvideo-generationinference-accelerationllm
      Cuda
      •
      Apache License 2.0
      •54•919•26•0•Updated Jan 30, 2025Jan 30, 2025

    • tianshou

      Public
      An elegant PyTorch deep reinforcement learning library.
      pytorchdqnpolicy-gradientrlcqlatariddpgimitation-learningsacdrl
      Python
      •
      MIT License
      •1.1k•8.2k•143•4•Updated Jan 26, 2025Jan 26, 2025

    • GFT

      Public
      MIT License
      •0•10•1•0•Updated Jan 26, 2025Jan 26, 2025

    • RoboticsDiffusionTransformer

      Public
      RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation
      Python
      •
      MIT License
      •78•834•13•3•Updated Dec 24, 2024Dec 24, 2024

    • Adaptive-Sparse-Trainer

      Public
      Official implementation for "Pruning Large Language Models with Semi-Structural Adaptive Sparse Training" (AAAI 2025)
      Python
      •
      Apache License 2.0
      •0•6•0•0•Updated Dec 22, 2024Dec 22, 2024

    • ReMoE

      Public
      Codebase for "ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing", built on Megatron-LM.
      Python
      •
      Other
      •0•54•0•0•Updated Dec 20, 2024Dec 20, 2024

    • tianshou-docs-zh_CN

      Public
      天授中文文档
      TeX
      •11•55•0•0•Updated Dec 10, 2024Dec 10, 2024

    • 2by4-pretrain-acc-examples

      Public
      Code for "Accelerating Transformer Pre-training with 2:4 Sparsity"
      Jupyter Notebook
      •
      BSD 3-Clause "New" or "Revised" License
      •0•17•0•0•Updated Dec 8, 2024Dec 8, 2024

    • CRM

      Public
      [ECCV 2024] Single Image to 3D Textured Mesh in 10 seconds with Convolutional Reconstruction Model.
      generative-modelreconstruction3dmultiviewdiffusion-modelsaigc
      Python
      •
      MIT License
      •53•622•24•1•Updated Nov 28, 2024Nov 28, 2024

    • CCA

      Public
      Codes accompanying the paper "Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment"
      Python
      •
      MIT License
      •0•23•0•0•Updated Nov 18, 2024Nov 18, 2024

    • DiffusionBridge

      Public
      Official codebase for "Diffusion Bridge Implicit Models" (ICLR 2025)
      Python
      •1•15•1•0•Updated Nov 18, 2024Nov 18, 2024

    • HiDe-PET

      Public
      Python
      •
      MIT License
      •1•1•0•0•Updated Nov 15, 2024Nov 15, 2024

    • HiDe-Prompt

      Public
      Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimality (NeurIPS 2023, Spotlight)
      Python
      •
      MIT License
      •7•79•3•0•Updated Nov 15, 2024Nov 15, 2024

    • Noise-Contrastive-Alignment

      Public
      Code accompanying the paper "Noise Contrastive Alignment of Language Models with Explicit Rewards" (NeurIPS 2024)
      Python
      •
      MIT License
      •4•44•1•0•Updated Nov 8, 2024Nov 8, 2024

    • MMTrustEval

      Public
      A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)
      benchmarkprivacytoolboxsafetymulti-modalfairnessrobustnessclaudegpt-4trustworthy-ai
      Python
      •
      Creative Commons Attribution Share Alike 4.0 International
      •8•123•3•0•Updated Nov 5, 2024Nov 5, 2024

    • Efficient-Diffusion-Alignment

      Public
      Official Codebase for "Aligning Diffusion Behaviors with Q-functions for Efficient Continuous Control" (NeurIPS 2024)
      Python
      •0•12•1•0•Updated Oct 29, 2024Oct 29, 2024

    • cond-image-leakage

      Public
      Official implementation for "Identifying and Solving Conditional Image Leakage in Image-to-Video Diffusion Model" (NeurIPS 2024)
      Apache License 2.0
      •23•244•6•0•Updated Oct 22, 2024Oct 22, 2024

    • CEURL

      Public
      Official implementation for "PEAC: Unsupervised Pre-training for Cross-Embodiment Reinforcement Learning" (NeurIPS 2024)
      reinforcement-learningunsupervised-reinforcement-learningembodied-aicross-embodiment-reinforcement-learningneurips24
      Python
      •
      MIT License
      •0•12•0•0•Updated Oct 13, 2024Oct 13, 2024

    • 3D_Corruptions_AD

      Public
      Benchmarking Robustness of 3D Object Detection to Common Corruptions in Autonomous Driving, CVPR 2023
      point-cloudself-driving-carautonomous-vehiclescvpr2023
      Python
      •
      MIT License
      •16•123•7•0•Updated Oct 9, 2024Oct 9, 2024

    • Jetfire-INT8Training

      Public
      Jupyter Notebook
      •3•32•2•0•Updated Jul 21, 2024Jul 21, 2024

    • Bridge-TTS

      Public
      Official codebase for "Schrodinger Bridges Beat Diffusion Models on Text-to-Speech Synthesis" (https://arxiv.org/abs/2312.03491).
      MIT License
      •1•125•4•0•Updated Jul 12, 2024Jul 12, 2024

    • conditional-image-leakage

      Public
      Official implementation for "Identifying and Solving Conditional Image Leakage in Image-to-Video Diffusion Model"
      Apache License 2.0
      •0•0•0•0•Updated Jun 23, 2024Jun 23, 2024

    • DPOT

      Public
      Code for "DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-Training"
      Python
      •6•41•0•0•Updated Jun 10, 2024Jun 10, 2024

    • IODF

      Public
      C++
      •
      MIT License
      •2•18•1•0•Updated Apr 17, 2024Apr 17, 2024

    • i-DODE

      Public
      Official code for "Improved Techniques for Maximum Likelihood Estimation for Diffusion ODEs" (ICML 2023)
      Python
      •
      Apache License 2.0
      •1•16•1•0•Updated Apr 9, 2024Apr 9, 2024

    • DPM-Solver-v3

      Public
      Official code for "DPM-Solver-v3: Improved Diffusion ODE Solver with Empirical Model Statistics" (NeurIPS 2023)
      Jupyter Notebook
      •
      MIT License
      •6•108•2•0•Updated Mar 25, 2024Mar 25, 2024

    • VCAS

      Public
      Official code for "Efficient Backpropagation with Variance Controlled Adaptive Sampling" (ICLR 2024)
      Python
      •
      Apache License 2.0
      •2•8•0•0•Updated Mar 8, 2024Mar 8, 2024

    • Attack-Bard

      Public
      Python
      •6•91•3•0•Updated Feb 16, 2024Feb 16, 2024

    • SRPO

      Public
      Codes accompanying the paper "Score Regularized Policy Optimization through Diffusion Behavior" (ICLR 2024).
      reinforcement-learningofflinerlgenerativediffusionscore-based-modelsd4rlsrpobehavior-regularization
      Python
      •
      MIT License
      •1•42•0•0•Updated Feb 10, 2024Feb 10, 2024