TSAIL group

All

86 repositories

Motus
Public
Official code of Motus: A Unified Latent Action World Model
robotics diffusion-model video-generation robotic-manipulation world-model unidiffuser vision-language-action-model
Python
•
Apache License 2.0
•9•541•10•0•Updated Jan 5, 2026Jan 5, 2026
TurboDiffusion
Public
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
rcm distillation video-generation mlsystem diffusion-models inference-acceleration ai-infra consistency-model sageattention sparse-linear-attention
Python
•
Apache License 2.0
•206•3.1k•52•5•Updated Jan 5, 2026Jan 5, 2026
MLA-Trust
Public
A toolbox for benchmarking Multimodal LLM Agents trustworthiness across truthfulness, controllability, safety and privacy dimensions through 34 interactive tasks
agent benchmark privacy toolbox safety multi-modal controllability trustworthy-ai truthfulness
Python
•
MIT License
•4•61•2•0•Updated Jan 5, 2026Jan 5, 2026
SpargeAttn
Public
[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.
attention vit quantization video-generation mlsys inference-acceleration ai-infra vision-transformer sparse-attention llm
Cuda
•
Apache License 2.0
•77•885•53•3•Updated Dec 31, 2025Dec 31, 2025
SLA
Public
SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse–Linear Attention
transformer video-generation mlsys inference-acceleration ai-infra linear-attention sparse-attention diffusion-transformer train-acceleration sparse-linear-attention
Python
•
Apache License 2.0
•12•228•6•0•Updated Dec 28, 2025Dec 28, 2025
vidar-robotwin
Public
robotwin evaluation code for vidar.
Python
•
MIT License
•0•4•0•0•Updated Dec 22, 2025Dec 22, 2025
SageAttention
Public
[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.
cuda triton attention vit quantization video-generation mlsys inference-acceleration efficient-attention llm
Cuda
•
Apache License 2.0
•304•3k•143•17•Updated Dec 22, 2025Dec 22, 2025
vidar
Public
Official repo for vidar and vidarc: video foundation model for robotics.
Python
•0•29•1•0•Updated Dec 22, 2025Dec 22, 2025
DiT-Extrapolation
Public
Official implementation for "RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers" (ICML 2025) and "UltraViCo: Breaking Extrapolation Limits in Video Diffusion Transformers"
generative-model rope diffusion extrapolation dit video-generation position-embedding diffusion-models long-video-generation diffusion-transformer
Python
•
Apache License 2.0
•73•769•23•0•Updated Dec 4, 2025Dec 4, 2025
ultraimage.github.io
Public
JavaScript
•0•0•0•0•Updated Dec 3, 2025Dec 3, 2025
UltraViCo.github.io
Public
Project page for "UltraViCo"
JavaScript
•0•0•0•0•Updated Dec 3, 2025Dec 3, 2025
RDT2
Public
Official code of RDT 2
Python
•
Apache License 2.0
•30•616•9•1•Updated Dec 3, 2025Dec 3, 2025
tianshou
Public
An elegant PyTorch deep reinforcement learning library.
pytorch dqn policy-gradient rl cql atari ddpg imitation-learning sac drl
Python
•
MIT License
•1.2k•9k•130•1•Updated Dec 1, 2025Dec 1, 2025
UniCardio
Public
Versatile Cardiovascular Signal Generation with a Unified Diffusion Transformer
Python
•
MIT License
•1•32•1•0•Updated Oct 9, 2025Oct 9, 2025
FrameBridge
Public
FrameBridge: Improving Image-to-Video Generation with Bridge Models
Python
•0•2•0•0•Updated Oct 2, 2025Oct 2, 2025
RoboticsDiffusionTransformer
Public
RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation
Python
•
MIT License
•146•1.6k•36•4•Updated Sep 28, 2025Sep 28, 2025
DiffusionBridge
Public
Official codebase for "Diffusion Bridge Implicit Models" (ICLR 2025) and "Consistency Diffusion Bridge Models" (NeurIPS 2024)
Python
•10•100•5•0•Updated Sep 9, 2025Sep 9, 2025
SparseDM
Public
Python
•1•1•0•0•Updated Aug 24, 2025Aug 24, 2025
EmbodiedActiveDefense
Public
Official implementation for "Reinforced Embodied Active Defense: Exploiting Adaptive Interaction for Robust Visual Perception in Adversarial 3D Environments" (TPAMI 2025)
Python
•
MIT License
•0•9•0•0•Updated Jul 26, 2025Jul 26, 2025
oddefense
Public
Jupyter Notebook
•
MIT License
•2•5•0•0•Updated Jul 16, 2025Jul 16, 2025
Adaptive-Sparse-Trainer
Public
Official implementation for "Pruning Large Language Models with Semi-Structural Adaptive Sparse Training" (AAAI 2025)
Python
•
Apache License 2.0
•2•17•0•0•Updated Jul 1, 2025Jul 1, 2025
MMTrustEval
Public
A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)
benchmark privacy toolbox safety multi-modal fairness robustness claude gpt-4 trustworthy-ai
Python
•
Creative Commons Attribution Share Alike 4.0 International
•12•173•1•0•Updated Jun 27, 2025Jun 27, 2025
TetraJet-MXFP4Training
Public
Pytorch implementation of "Oscillation-Reduced MXFP4 Training for Vision Transformers" on DeiT Model Pre-training
Python
•
Apache License 2.0
•4•34•0•0•Updated Jun 20, 2025Jun 20, 2025
DDO
Public
Python
•
Other
•0•0•0•0•Updated Jun 16, 2025Jun 16, 2025
GFT
Public
Python
•
MIT License
•0•50•5•0•Updated Jun 13, 2025Jun 13, 2025
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
•22•256•8•0•Updated Apr 25, 2025Apr 25, 2025
i-DODE
Public
Official code for "Improved Techniques for Maximum Likelihood Estimation for Diffusion ODEs" (ICML 2023)
Python
•
Apache License 2.0
•1•18•1•0•Updated Mar 4, 2025Mar 4, 2025
STAIR
Public
Official codebase for "STAIR: Improving Safety Alignment with Introspective Reasoning"
Python
•
MIT License
•6•86•3•0•Updated Feb 26, 2025Feb 26, 2025
EffWRN-paddle
Public
Python
•
MIT License
•0•0•0•0•Updated Feb 24, 2025Feb 24, 2025
RIFLEx.github.io
Public
JavaScript
•0•0•0•0•Updated Feb 21, 2025Feb 21, 2025