Lists (1)
Stars
Development repository for the Triton language and compiler
(AAAI 2023 Oral) Pytorch implementation of "CF-ViT: A General Coarse-to-Fine Method for Vision Transformer"
The official implementation of "2024NeurIPS Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation"
Fast Vision Mamba : Pool your Spatial Dimensions for Accelerated Processing
[NeurIPS2022] This is the official implementation of the paper "Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuning" for SAM.
Merging Context Clustering with Visual State Space Models for Medical Image Segmentation
Python code for ICLR 2022 spotlight paper EViT: Expediting Vision Transformers via Token Reorganizations
Official Pytorch implementation of Dynamic-Token-Pruning (ICCV2023)
Code for paper LocalMamba: Visual State Space Model with Windowed Selective Scan
The codes for TCFormer in paper: Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer
[CVPR 2025] Spectral State Space Model for Rotation-Invariant Visual Representation Learning
A method to increase the speed and lower the memory footprint of existing vision transformers.
[CVPR 2025 Oral] OverLoCK: An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernels
Official repo for Adaptive Rectangular Convolution
Give us minutes, we give back a faster Mamba. The official implementation of "Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training".
[Official Repo] Visual Mamba: A Survey and New Outlooks
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…
[ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model
[NeurIPS 2021] [T-PAMI] DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification
Integrate the DeepSeek API into popular softwares
AiLearning：数据分析+机器学习实战+线性代数+PyTorch+NLTK+TF2
Easily fine-tune, evaluate and deploy Qwen3, DeepSeek-R1, Llama 4 or any open source LLM / VLM!
🧑🚀 全世界最好的LLM资料总结（视频生成、Agent、辅助编程、数据处理、模型训练、模型推理、o1 模型、MCP、小语言模型、视觉语言模型） | Summary of the world's best LLM resources.