SHI Labs

All

65 repositories

NATTEN
Public
Fast Multi-dimensional Sparse Attention
cuda pytorch sparse-attention
cuda pytorch sparse-attention neighborhood-attention
C++
•
MIT License
•57•722•15•7•Updated Feb 26, 2026Feb 26, 2026
physical-ai-bench
Public
[CVPR 2026] PAI-Bench: A Comprehensive Benchmark for Physical AI
benchmark world-model physical-ai
benchmark world-model physical-ai
Python
•
MIT License
•2•55•1•0•Updated Feb 21, 2026Feb 21, 2026
MapReduce-LoRA
Public
MapReduce LoRA: Advancing the Pareto Front in Multi-Preference Optimization for Generative Models
Python
•
MIT License
•0•3•0•0•Updated Feb 12, 2026Feb 12, 2026
Forget-Me-Not
Public
Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Models, 2023
Python
•
MIT License
•8•138•7•0•Updated Oct 22, 2025Oct 22, 2025
VisPer-LM
Public
[NeurIPS 2025] Elevating Visual Perception in Multimodal LLMs with Visual Embedding Distillation
Python
•1•71•2•0•Updated Oct 17, 2025Oct 17, 2025
T2I-Copilot
Public
T2I-Copilot: A Training-Free Multi-Agent Text-to-Image System for Enhanced Prompt Interpretation and Interactive Generation (ICCV'25)
Jupyter Notebook
•
MIT License
•2•45•0•0•Updated Oct 6, 2025Oct 6, 2025
shi-labs.github.io
Public
CSS
•0•0•0•0•Updated Oct 5, 2025Oct 5, 2025
IMG-Multimodal-Diffusion-Alignment
Public
IMG: Calibrating Diffusion Models via Implicit Multimodal Guidance, ICCV 2025
Python
•3•30•1•0•Updated Oct 1, 2025Oct 1, 2025
StyleNAT
Public
New flexible and efficient image generation framework that sets new SOTA on FFHQ-256 with FID 2.05, 2022
gan image-generation neighborhood-attention
gan image-generation neighborhood-attention
Python
•
MIT License
•12•101•0•0•Updated Jun 26, 2025Jun 26, 2025
Slow-Fast-Video-Multimodal-LLM
Public
Python
•1•28•2•0•Updated Apr 8, 2025Apr 8, 2025
Diffusion-Driven-Test-Time-Adaptation-via-Synthetic-Domain-Alignment
Public
Everything to the Synthetic: Diffusion-driven Test-time Adaptation via Synthetic-Domain Alignment, arXiv 2024 / CVPR 2025
diffusion-models test-time-adaptation
diffusion-models test-time-adaptation
Python
•2•40•1•0•Updated Mar 1, 2025Mar 1, 2025
Compact-Transformers
Public
Escaping the Big Data Paradigm with Compact Transformers, 2021 (Train your Vision Transformers in 30 mins on CIFAR-10 with a single GPU!)
Python
•
Apache License 2.0
•84•536•7•2•Updated Nov 5, 2024Nov 5, 2024
OneFormer
Public
[CVPR 2023] OneFormer: One Transformer to Rule Universal Image Segmentation
transformer coco image-segmentation
transformer coco image-segmentation semantic-segmentation cityscapes instance-segmentation ade20k panoptic-segmentation universal-segmentation oneformer
Jupyter Notebook
•
MIT License
•149•1.7k•43•4•Updated Oct 3, 2024Oct 3, 2024
Smooth-Diffusion
Public
Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models arXiv 2023 / CVPR 2024
Python
•
MIT License
•7•355•13•0•Updated Sep 24, 2024Sep 24, 2024
FineStyle
Public
FineStyle: Fine-grained Controllable Style Personalization for Text-to-image Models
MIT License
•0•6•0•0•Updated Sep 4, 2024Sep 4, 2024
Agriculture-Vision
Public
[CVPR 2020 & 2021 & 2022 & 2023] Agriculture-Vision Dataset, Prize Challenge and Workshop: A joint effort with many great collaborators to bring Agriculture and…
39•250•2•1•Updated Jul 27, 2024Jul 27, 2024
CuMo
Public
CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts
Python
•
Apache License 2.0
•8•162•0•1•Updated Jun 8, 2024Jun 8, 2024
Neighborhood-Attention-Transformer
Public
Neighborhood Attention Transformer, arxiv 2022 / CVPR 2023. Dilated Neighborhood Attention Transformer, arxiv 2022
pytorch neighborhood-attention
pytorch neighborhood-attention
Python
•
MIT License
•89•1.2k•5•0•Updated May 15, 2024May 15, 2024
CompactNet
Public
Jupyter Notebook
•0•32•0•0•Updated May 5, 2024May 5, 2024
VCoder
Public
[CVPR 2024] VCoder: Versatile Vision Encoders for Multimodal Large Language Models
Python
•
Apache License 2.0
•16•279•4•1•Updated Apr 17, 2024Apr 17, 2024
FcF-Inpainting
Public
[WACV 2023] Keys to Better Image Inpainting: Structure and Texture Go Hand in Hand
pytorch image-inpainting stylegan2
pytorch image-inpainting stylegan2 fast-fourier-convolution fcfgan
Jupyter Notebook
•
Other
•15•195•7•0•Updated Apr 3, 2024Apr 3, 2024
Rethinking-Text-Segmentation
Public
[CVPR 2021] Rethinking Text Segmentation: A Novel Dataset and A Text-Specific Refinement Approach
Python
•29•271•13•0•Updated Dec 2, 2023Dec 2, 2023
Matting-Anything
Public
Matting Anything Model (MAM), an efficient and versatile framework for estimating the alpha matte of any instance in an image with flexible and interactive visu…
Python
•
MIT License
•49•699•8•1•Updated Nov 18, 2023Nov 18, 2023
Prompt-Free-Diffusion
Public
Prompt-Free Diffusion: Taking "Text" out of Text-to-Image Diffusion Models, arxiv 2023 / CVPR 2024
Python
•
MIT License
•38•758•15•1•Updated Nov 16, 2023Nov 16, 2023
VIM
Public
Python
•
MIT License
•4•63•4•0•Updated Nov 8, 2023Nov 8, 2023
Versatile-Diffusion
Public
Versatile Diffusion: Text, Images and Variations All in One Diffusion Model, arXiv 2022 / ICCV 2023
Python
•
MIT License
•84•1.3k•9•1•Updated Aug 10, 2023Aug 10, 2023
OneFormer-Colab
Public
[Colab Demo Code] OneFormer: One Transformer to Rule Universal Image Segmentation.
transformer coco image-segmentation
transformer coco image-segmentation semantic-segmentation cityscapes instance-segmentation ade20k panoptic-segmentation universal-segmentation oneformer
Python
•
MIT License
•10•14•1•0•Updated May 24, 2023May 24, 2023
PAIR-Diffusion
Public
PAIR-Diffusion: Object-Level Image Editing with Structure-and-Appearance Paired Diffusion Models, 2023
Python
•
MIT License
•21•3•0•0•Updated May 19, 2023May 19, 2023
Text2Video-Zero
Public
a copy of "Text-to-Image Diffusion Models are Zero-Shot Video Generators", ICCV 2023
Python
•
Other
•388•2•0•0•Updated May 6, 2023May 6, 2023
Text2Video-Zero-sd-webui
Public
Python
•
Other
•15•82•6•0•Updated Apr 10, 2023Apr 10, 2023