[NeurIPS 25 @ ER] Long-Context Modeling with Dynamic Hierarchical Sparse Attention for On-Device LLMs

A minimal implementation of a denoising diffusion model in PyTorch.

A unified framework for 3D content generation.

Mentis: A powerful multi-agent orchestration framework built on LangGraph.

Using machine learning to build a corpus of articles about social media privacy incidents.

Playwright MCP server

Unofficial implementation of "SODA: Bottleneck Diffusion Models for Representation Learning"

个人中文简历 Latex 源码 https://hijiangtao.github.io/

MiniTorch is an educational library that recreates core PyTorch features using only Python and NumPy. For more information, please read the README.md file.

经典机器学习算法的极简实现

AcadHomepage: A Modern and Responsive Academic Personal Homepage

Collection of Summer 2026 tech internships!

A curated list of resources for using LLMs to develop more competitive grant applications.

[NAACL 25 main] Awesome LLM Causal Reasoning is a collection of LLM-based casual reasoning works, including papers, codes and datasets.

🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!

official implementation of "Interpreting CLIP's Image Representation via Text-Based Decomposition"

本人的科研经验

[AAAI2024] FontDiffuser: One-Shot Font Generation via Denoising Diffusion with Multi-Scale Content Aggregation and Style Contrastive Learning

Pytorch implementation of Transfusion, "Predict the Next Token and Diffuse Images with One Multi-Modal Model", from MetaAI

Official implementation of MINDE: Mutual Information Neural Diffusion Estimation

PyTorch implementation for the ICLR 2020 paper "Understanding the Limitations of Variational Mutual Information Estimators"

Mutual information estimators and benchmark

Official implementation of MINDE: Mutual Information Neural Diffusion Estimation

Mutual information estimators and benchmark

A flexible, high-performance, user-friendly computer architecture simulator engine

基于Python的开源量化交易平台开发框架