Lists (1)
Sort Name ascending (A-Z)
Stars
[EMNLP 2024 & AAAI 2026] A powerful toolkit for compressing large models including LLM, VLM, and video generation models.
[NeurIPS 2025] Official Implementation of ViSpec: Accelerating Vision-Language Models with Vision-Aware Speculative Decoding.
A high-throughput and memory-efficient inference and serving engine for LLMs
An lite version of facebook folly, contains fbvector and fbstring only.
[NeurIPS 2025] PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers
🚀 Efficient implementations of state-of-the-art linear attention models
FlashMLA: Efficient Multi-head Latent Attention Kernels
A lightweight tool for camera pose visualization
Tensors and Dynamic neural networks in Python with strong GPU acceleration
[ICCV2023] DETR Doesn’t Need Multi-Scale or Locality Design
🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
Toolkits for the synthetic multiview cattle 3D detection and action recognition dataset, MultiviewC.
Multiview 3D object detection on MultiviewC dataset through moft3d.
Toolkits for the synthetic multiview pedestrian detection dataset, MultiviewX.
3D detection and tracking viewer (visualization) for kitti & waymo dataset
A library to parse and convert PMML models into Scikit-learn estimators.
An awesome iTerm2 backend for Matplotlib, so you can plot directly in your terminal.
This is the official code for MobileSAM project that makes SAM lightweight for mobile applications and beyond!
Official PyTorch implementation of SparseTrack
A playbook for systematically maximizing the performance of deep learning models.
Code for paper on ICRA 2022 workshop on Deformable Object Manipulation. In this work we learn keypoints from synthetic data for robotic cloth folding.
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
This is the official implementation of TransCenter (TPAMI). The code and pretrained models are now available here: https://gitlab.inria.fr/yixu/TransCenter_official.
Clean Code Collection books-写代码的艺术--但是也不能死读书,照搬理论实践
detrex is a research platform for DETR-based object detection, segmentation, pose estimation and other visual recognition tasks.
Implementation of Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fields