Use Codex from Claude Code to review code or delegate tasks.

AI agents running research on single-GPU nanochat training automatically

全网最全Stable Diffusion全套教程，从入门到进阶，耗时三个月制作

Segmented Code Adjustment Quantization (SAQ)

Supplementary Code for Unsupervised Neural Quantization for Compressed-Domain Similarity Search

Batch Finder is a powerful utility package that helps you determine the optimal batch size, number of documents, and sequence length for your PyTorch models. It uses binary search to efficiently fi…

Residual Quantization with Implicit Neural Codebooks

[ICLR 2024 spotlight] Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCI

🚀 Efficient implementations for emerging model architectures

Code for the paper "Neuro-GPT: Towards a Foundation Model for EEG"

Official code repository for the paper 'EEGPT: Pretrained Transformer for Universal and Reliable Representation of EEG Signals' [NIPS 2024].

I put here tools that I use in different projects all the time, so I have them all centralized

Critical difference diagram with Wilcoxon-Holm post-hoc analysis.

Python Overleaf API and simple CLI

InterpretDL: Interpretation of Deep Learning Models，基于『飞桨』的模型可解释性算法库。

An anomaly detection library comprising state-of-the-art algorithms and features such as experiment management, hyper-parameter optimization, and edge inference.

Official implementation of our paper "Unsupervised Active Learning via Natural Feature Progressive Framework", currently under review at IEEE Transactions on Pattern Analysis and Machine Intelligen…

vEpiSet: An EEG dataset for interictal epileptiform discharge with spatial distribution information

Collaborative documentation for and from Jean Zay users. Official Jean Zay documentation: http://www.idris.fr/en/docs/jean-zay/nouvel-utilisateur

[ICML 2024] A novel, efficient lightweight approach combining convolutional operations with adaptive spectral analysis as a foundation model for different time series tasks

Graph Embedding for Interpretable Time Series Clustering

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

A curated list of papers and resources about the distribution shift in machine learning.

(Under Review)