存储北极学派的哲学，思考，教义repository

Public release of the code for "Accelerating Vision Transformers with Adaptive Patches"

Official implementation of ICLR26 (Oral): Decentralized Attention Fails Centralized Signals: Rethink Transformers for Medical Time Series

Tile primitives for speedy kernels

AI agents running research on single-GPU nanochat training automatically

Mantis: Lightweight Calibrated Foundation Model for User-Friendly Time Series Classification

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

The best ChatGPT that $100 can buy.

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

Minimalistic 4D-parallelism distributed training framework for education purpose

Python implementation of k-Shape

Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models

A course of learning LLM inference serving on Apple Silicon for systems engineers: build a tiny vLLM + Qwen.

Demystify RAG by building it from scratch. Local LLMs, no black boxes - real understanding of embeddings, vector search, retrieval, and context-augmented generation.

[ICLR 2024] Official implementation of " 🦙 Time-LLM: Time Series Forecasting by Reprogramming Large Language Models"

Source code and datasets for Ekya, a system for continuous learning on the edge.

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

NASBench: A Neural Architecture Search Dataset and Benchmark

[ICLR 2025] NeuroLM: A Universal Multi-task Foundation Model for Bridging the Gap between Language and EEG Signals

[ICLR 2025] BrainUICL: An Unsupervised Individual Continual Learning Framework for EEG Applications

Public repository associated with "Deep Learning for ECG Analysis: Benchmarks and Insights from PTB-XL"

[ICML'2025] From Token to Rhythm: A Multi-Scale Approach for ECG-Language Pretraining

Nano vLLM

[ICLR 2025] CBraMod: A Criss-Cross Brain Foundation Model for EEG Decoding

A fast GPU memory copy library based on NVIDIA GPUDirect RDMA technology

Perplexity GPU Kernels