MagicPaste: intent-aware, smarter clipboard | 你的剪贴板，一键智能

Code for paper: Post-Completion Learning for Language Models

ContextOS: AI-Centric Proactive Agent Framework

MCP-Zero: Active Tool Discovery for Autonomous LLM Agents

Official implementation of paper: Advancing Sequential Numerical Prediction in Autoregressive Models

像吴恩达课程一样学习 Transformer 架构 | Learning to write Transformer series architectures like Andrew Ng's lessons.

Dataset and codebase for MCTBench

Code for RepAn: Enhanced Annealing through Re-parameterization

A dynamic network framework based on PyTorch.

PyTorch implementation of BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models

archive for RMI-NAS. Standalone code from XNAS.

PaddlePaddle implement of EC-DARTS: Inducing Equalized and Consistent Optimization into DARTS