transformer

[ECCV2022] MOTR: End-to-End Multiple-Object Tracking with TRansformer

"Structure-Aware Sparse-View X-ray 3D Reconstruction" (CVPR 2024) - A Toolbox for CT reconstruction and X-ray Novel View Synthesis

Semantic Segmentation for Remote Sensing

[CVPR'22 Oral] GMFlow: Learning Optical Flow via Global Matching

[TNSRE 23] EEG Transformer 2.0. i. Convolutional Transformer for EEG Decoding. ii. Novel visualization - Class Activation Topography.

[Mamba-Survey-2024] Paper list for State-Space-Model/Mamba and it's Applications

Cameras as Relative Positional Encoding

Tevatron - Unified Document Retrieval Toolkit across Scale, Language, and Modality. Demo in SIGIR 2023, SIGIR 2025.

Implementation of plug in and play Attention from "LongNet: Scaling Transformers to 1,000,000,000 Tokens"

[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization

[ICCV'21] Learning Spatio-Temporal Transformer for Visual Tracking

Minimalist NMT for educational purposes

[ICML 2025] Official PyTorch Implementation of "History-Guided Video Diffusion"

Export Hugging Face models to Core ML and TensorFlow Lite

[ECCV] Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration. Advances in Image Manipulation (AIM) workshop ECCV 2022. Try it out! over 3.3M runs https://replicate.com/mv-lab/swin2sr

Accurate, large-scale, and extensible simulator for LLM inference Systems

[CoRL 2022] InterFuser: Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformer

This code accompanies the the paper Trading with the Momentum Transformer: An Intelligent and Interpretable Architecture (https://arxiv.org/pdf/2112.08534.pdf).

TransMorph: Transformer for Unsupervised Medical Image Registration (PyTorch)

Achieve the llama3 inference step-by-step, grasp the core concepts, master the process derivation, implement the code.

Multimodal model for text and tabular data with HuggingFace transformers as building block for text data

multilspy is a lsp client library in Python intended to be used to build applications around language servers.

[CVPR 2021, Oral] PREDATOR: Registration of 3D Point Clouds with Low Overlap.

臺灣大學 (NTU) 李宏毅教授「機器學習 (Machine Learning) 2021 Spring 」課程筆記

[ICLR2025 Spotlight🔥] Official Implementation of TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters

NLP Paper

Collection of awesome parameter-efficient fine-tuning resources.

历年ICLR论文和开源项目合集，包含ICLR2021、ICLR2022、ICLR2023、ICLR2024、ICLR2025.

Framework of fast implementation data processing and operating pipelines

Democratization of RT-2 "RT-2: New model translates vision and language into action"