🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga…

[NAACL2024] Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey

计算机自学指南

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

A Library for Advanced Deep Time Series Models.

An offical implementation of PatchTST: "A Time Series is Worth 64 Words: Long-term Forecasting with Transformers." (ICLR 2023) https://arxiv.org/abs/2211.14730

Edge-MoE: Memory-Efficient Multi-Task Vision Transformer Architecture with Task-level Sparsity via Mixture-of-Experts

A professionally curated list of awesome resources (paper, code, data, etc.) on transformers in time series.

Official implementation of our ICLR 2023 paper "Crossformer: Transformer Utilizing Cross-Dimension Dependency for Multivariate Time Series Forecasting"

Approaching (Almost) Any Machine Learning Problem

the resources I use to learn computer science in my spare time

🎨 ML Visuals contains figures and templates which you can reuse and customize to improve your scientific writing.

System for AI Education Resource.