An unified model that seamlessly integrates multimodal understanding, text-to-image generation, and image editing within a single powerful framework.

Implementation of paper "D2Match: Leveraging Deep Learning and Degeneracy for Subgraph Matching"

Stanford Network Analysis Platform (SNAP) is a general purpose network analysis and graph mining library.

A comprehensive multimodal circuit-focused benchmark for evaluating large language models (LLMs)

Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search

Towhee is a framework that is dedicated to making neural data processing pipelines simple and fast.

Code for "A Spectral Approach to Gradient Estimation for Implicit Distributions" (ICML'18)

Official Code for Incorporating Surrogate Gradient Norm to Improve Offline Optimization Techniques (NeurIPS 2024)

cadence原理图转visio绘图

[NeurIPS 2025 🔥] Official implementation for "Don't Just Chase “Highlighted Tokens” in MLLMs: Revisiting Visual Holistic Context Retention"

[ICLR 2025] Official Implementation of ParetoFlow: Guided Flows in Multi-Objective Optimization🧬🧬🧬

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

Towards Generalized and Efficient Blackbox Optimization System/Package (KDD 2021 & JMLR 2024)

All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.

🥢像老乡鸡🐔那样做饭。主要部分于2024年完工，非老乡鸡官方仓库。文字来自《老乡鸡菜品溯源报告》，并做归纳、编辑与整理。CookLikeHOC.

Deep Reinforcement Learning of Analog Circuit Designs

A scikit-learn-compatible library for estimating prediction intervals and controlling risks, based on conformal predictions.

Lightweight, useful implementation of conformal prediction on real data.

VisioFirm: Cross-Platform AI-assisted Annotation Tool for Computer Vision

LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence https://arxiv.org/abs/2509.03505

[ICCAD 2025] PPAAS: PVT and Pareto Aware Analog Sizing Analog Sizing via Goal-conditioned Reinforcement Learning

Framework for Easily Invertible Architectures

GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation

TuneTables is a tabular classifier that implements prompt tuning for frozen prior-fitted networks.