Stars
This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."
A live reading list for LLM data synthesis (Updated to July, 2025).
[ICLR 2025] Official implementation for "SafeWatch: An Efficient Safety-Policy Following Video Guardrail Model with Transparent Explanations"
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
Official Repository of Absolute Zero Reasoner
[ICML2022] G-Mixup: Graph Data Augmentation for Graph Classification
label-smooth, amsoftmax, partial-fc, focal-loss, triplet-loss, lovasz-softmax. Maybe useful
Graph Neural Network Library for PyTorch
Beyond Accuracy: What Matters in Designing Well-Behaved Models?
PyTorch implementation of image classification models for CIFAR-10/CIFAR-100/MNIST/FashionMNIST/Kuzushiji-MNIST/ImageNet
Framework for evaluating Graph Neural Network models on semi-supervised node classification task
Codes for paper GETS: Nodewise Ensemble Calibration for Graph Neural Networks
[ICML 2024] TrustLLM: Trustworthiness in Large Language Models
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
FlashMLA: Efficient Multi-head Latent Attention Kernels
Practice on cifar100(ResNet, DenseNet, VGG, GoogleNet, InceptionV3, InceptionV4, Inception-ResNetv2, Xception, Resnet In Resnet, ResNext,ShuffleNet, ShuffleNetv2, MobileNet, MobileNetv2, SqueezeNet…
Calibrating LLMs with Information-Theoretic Evidential Deep Learning (ICLR 2025)
Awesome LLM Books: Curated list of books on Large Language Models
Official code repo for the O'Reilly Book - "Hands-On Large Language Models"
A simple way to calibrate your neural network.
Wrapper for a PyTorch classifier which allows it to output prediction sets. The sets are theoretically guaranteed to contain the true class with high probability (via conformal prediction).
Recommend new arxiv papers of your interest daily according to your Zotero libarary.
Official Python client library for the OpenReview API
The net:cal calibration framework is a Python 3 library for measuring and mitigating miscalibration of uncertainty estimates, e.g., by a neural network.
A high-throughput and memory-efficient inference and serving engine for LLMs
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.