- Beijing, China
- https://yilingui.xyz
Starred repositories
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Implements a LLM similar to Meta's Llama 2 from the ground up in PyTorch, for educational purposes.
AIGC-interview/CV-interview/LLMs-interview面试问题与答案集合仓,同时包含工作和科研过程中的新想法、新问题、新资源与新项目
Official repository for our work on micro-budget training of large-scale diffusion models.
A Telegram bot to recommend arXiv papers
[IROS 2023] "Streaming Motion Forecasting for Autonomous Driving"
[CVPR 2024] Test-Time Training of Trajectory Prediction via Masked Autoencoder and Actor-specific Token Memory
SGLang is a fast serving framework for large language models and vision language models.
Nullboard is a minimalist kanban board, focused on compactness and readability.
Utils for streaming large files (S3, HDFS, gzip, bz2...)
Deep Learning Fundamentals -- Code material and exercises
Non-destructive, node based 2D graphics editor focused on simplicity, speed, elegance, and usability
A cross platform lightweight single-header simple-to-use window abstraction library for creating graphical programs or libraries.
Powerful automatic differentiation in C++ and Python
A passive recording project allows you to have complete control over your data. Automatically take screenshots of all your screens, index them, and save them locally.
The standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.
Code release for book "Efficient Training in PyTorch"
[NeurIPS 2024] DeMo: Decoupling Motion Forecasting into Directional Intentions and Dynamic States
文本盲水印:把信息隐匿到文本中,put invisible blind watermark into a text.
[ECCV 2024] OPEN: Object-wise Position Embedding for Multi-view 3D Object Detection
Common repo for our ongoing research on motion forecasting for self-driving cars
Sharing both practical insights and theoretical knowledge about LLM evaluation that we gathered while managing the Open LLM Leaderboard and designing lighteval!
Optimization-based real-time path planning for vehicles.