Build AI teams, not just agents. Hard rails, soft power, shared mission.

Benchmark Everything Everywhere All at Once, a fully autonomous agentic system for benchmark construction and customization.

SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.

Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception

整理目前开源的最优表格识别模型，完善前后处理，模型转换为ONNX

RAFConv: Innovating Spatital Attention and Standard Convolutional Operation

Deep Splitting and Merging for Table Structure Decomposition

Tensorflow implementation of Swin Transformer model.

implement of Multi-Attention Multi-Class Constraint for Fine-grained Image Recognition with keras

ctcloss + centerloss crnn text recognition

Tensorflow ShuffleNet v2 implementation

the multi-GPUs implementation of mobilenet v3 in tensorflow with tf.layers

Set of methods to ensemble boxes from different object detection models, including implementation of "Weighted boxes fusion (WBF)" method.

Change smooth L1 loss to GIoU loss for RetinaNet

PointRend for instance segmentation on TensorFlow

CenterNet (Objects as Points) implementation in Keras and Tensorflow

FCOS (Fully Convolutional One-Stage Object Detection) implementation in Keras and Tensorflow

Keras上700行代码复现YOLOv3！使用DIOU loss。支持将模型导出为pytorch模型。

Code for: S.R. Qasim, H. Mahmood, and F. Shafait, Rethinking Table Recognition using Graph Neural Networks (2019)

Keras Implementation of EfficientNets

英语单词纠错

String Distance using cython

String Distance using cython

超轻量级中文ocr，支持竖排文字识别, 支持ncnn推理 , psenet(8.5M) + crnn(6.3M) + anglenet(1.5M) 总模型仅17M

This is a tensorflow re-implementation of Faster R-CNN: Towards Real-Time ObjectDetection with Region Proposal Networks.

Focal Loss for Dense Rotation Object Detection