Stars
RLinf is a flexible and scalable open-source infrastructure designed for post-training foundation models (LLMs, VLMs, VLAs) via reinforcement learning.
Models and examples built with TensorFlow
Detect Anything via Next Point Prediction (Based on Qwen2.5-VL-3B)
tensorboard for pytorch (and chainer, mxnet, numpy, ...)
A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
Solve Visual Understanding with Reinforced VLMs
The Incredible PyTorch: a curated list of tutorials, papers, projects, communities and more relating to PyTorch.
A simple, fully convolutional model for real-time instance segmentation.
shreyashampali / ho3d
Forked from lmb-freiburg/freihandA dataset for pose estimation of hand when interacting with object and severe occlusions.
Bidirectional Mapping between Action Physical-Semantic Space
Image-to-Image Translation in PyTorch
MANO hand model in PyTorch (anatomy consistent, anchors, etc)
Rex-Thinker: Grounded Object Refering via Chain-of-Thought Reasoning
SenseTime Research platform for single object tracking, implementing algorithms like SiamRPN and SiamMask.
Point2Skeleton: Learning Skeletal Representations from Point Clouds (CVPR2021)
PointNetGPD is an end-to-end grasp evaluation model to address the challenging problem of localizing robot grasp configurations directly from the point cloud.
Large dataset of hand-object contact, hand- and object-pose, and 2.9 M RGB-D grasp images.
Awesome work on hand pose estimation/tracking
Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-迁移学习
[CVPR19/TPAMI23] SiamMask: A Framework for Fast Online Object Tracking and Segmentation
A fork to add multimodal model training to open-r1
PyTorch implementation of PoseLSTM and PoseNet