Stars
Unified Spatial-Channel Representation Learning with Group-Efficient Mamba for LiDAR-based 3D Object Detection
EgoFSD: Ego-Centric Fully Sparse Paradigm for End-to-End Self-Driving
[ICML 2025] This is the official PyTorch implementation of "OmniBal: Towards Fast Instruction-Tuning for Vision-Language Models via Omniverse Computation Balance".
Built upon Megatron-Deepspeed and HuggingFace Trainer, EasyLLM has reorganized the code logic with a focus on usability. While enhancing usability, it also ensures training efficiency.
FewX is an open-source toolbox on top of Detectron2 for data-limited instance-level recognition tasks.
Pytorch implementation of deep image matting
🙃 A delightful community-driven (with 2,500+ contributors) framework for managing your zsh configuration. Includes 300+ optional plugins (rails, git, macOS, hub, docker, homebrew, node, php, python…
Visual tracking library based on PyTorch.
Deep Learning papers reading roadmap for anyone who are eager to learn this amazing tech!
[ECCV2018] Distractor-aware Siamese Networks for Visual Object Tracking
Package to make C++ libraries available in Julia
Package to call Python functions from the Julia language
Tensors and Dynamic neural networks in Python with strong GPU acceleration
auto-tuning momentum SGD optimizer