An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models

This repository contains all necessary meta information, results and source files to reproduce the results in the publication Eric Müller-Budack, Kader Pustu-Iren, Ralph Ewerth: "Geolocation Estima…

Simple RL training for reasoning

[NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards

GeoGuessr benchmark for language models

EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

Machine Learning and Computer Vision Engineer - Technical Interview Questions

Continuous Thought Machines, because thought takes time and reasoning is a process.

[COLM'25] The official implementation of "LongPerceptualThoughts: Distilling System-2 Reasoning for System-1 Perception"

The simplest, fastest repository for training/finetuning small-sized VLMs.

Witness the aha moment of VLM with less than $3.

RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.

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

Understanding R1-Zero-Like Training: A Critical Perspective

Embodied Reasoning Question Answer (ERQA) Benchmark

Repository of Jupyter notebook tutorials for teaching the Deep Learning Course at the University of Amsterdam (MSc AI), Fall 2023

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

[TMLR 25] SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models

Eagle: Frontier Vision-Language Models with Data-Centric Strategies

A fork to add multimodal model training to open-r1

Collection of awesome parameter-efficient fine-tuning resources.

A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.

List of papers on Self-Correction of LLMs.

PushWorld: A benchmark for manipulation planning with tools and movable obstacles

A collection of PDDL generators, some of which have been used to generate benchmarks for the International Planning Competition (IPC).

Official release of the benchmark in paper "VSP: Diagnosing the Dual Challenges of Perception and Reasoning in Spatial Planning Tasks for MLLMs"

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

A bibliography and survey of the papers surrounding o1

Efficient LLM inference on Slurm clusters.

A high-throughput and memory-efficient inference and serving engine for LLMs