Official PyTorch implementation for "Large Language Diffusion Models"

Official Repo for Open-Reasoner-Zero

verl: Volcano Engine Reinforcement Learning for LLMs

A lightweight reproduction of DeepSeek-R1-Zero with indepth analysis of self-reflection behavior.

s1: Simple test-time scaling

Princeton University Ph.D. Dissertation Template

Simple RL training for reasoning

Fully open reproduction of DeepSeek-R1

Minimal reproduction of DeepSeek R1-Zero

Training Large Language Model to Reason in a Continuous Latent Space

Sky-T1: Train your own O1 preview model within $450

Code release for Best-of-N Jailbreaking

O1 Replication Journey

A series of technical report on Slow Thinking with LLM

Open-Sora: Democratizing Efficient Video Production for All

Recipes to scale inference-time compute of open models

PyTorch library for Active Fine-Tuning

NeurIPS 2024 tutorial on LLM Inference

Audio Large Language Models

A survey on harmful fine-tuning attack for large language model (ACM CSUR)

[ICLR 2025] On Evluating the Durability of Safegurads for Open-Weight LLMs

the LLM vulnerability scanner

Curated list of data science interview questions and answers

This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large Language Models" (NeurIPS2024)

LOFT: A 1 Million+ Token Long-Context Benchmark

This repo is meant to serve as a guide for Machine Learning/AI technical interviews.

Code and example data for the paper: Rule Based Rewards for Language Model Safety