Fix bug and add a new task

ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation

RoboFactory: Exploring Embodied Agent Collaboration with Compositional Constraints

Situational Awareness Dataset

Public repository containing METR's DVC pipeline for eval data analysis

R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization

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

An Open-source RL System from ByteDance Seed and Tsinghua AIR

Extend OpenRLHF to support LMM RL training for reproduction of DeepSeek-R1 on multimodal tasks.

An Easy-to-use, Scalable and High-performance RLHF Framework designed for Multimodal Models.

MM-EUREKA: Exploring Visual Aha Moment with Rule-based Large-scale Reinforcement Learning

Explore the Multimodal “Aha Moment” on 2B Model

Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking

Ola: Pushing the Frontiers of Omni-Modal Language Model

[Official Repo] CrossEarth: Geospatial Vision Foundation Model for Cross-Domain Generalization in Remote Sensing Semantic Segmentation

Awesome Large Reasoning Model(LRM) Safety.This repository is used to collect security-related research on large reasoning models such as DeepSeek-R1 and OpenAI o1, which are currently very popular.

Official implementation of paper: SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training

Official codebase for "STAIR: Improving Safety Alignment with Introspective Reasoning"

Awesome RL-based LLM Reasoning

This repository provides valuable reference for researchers in the field of multimodality, please start your exploratory travel in RL-based Reasoning MLLMs!

TrustEval: A modular and extensible toolkit for comprehensive trust evaluation of generative foundation models (GenFMs)

Code for Paper: Teaching Language Models to Critique via Reinforcement Learning

Code for "Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate"

Official Repo for Open-Reasoner-Zero

A fork to add multimodal model training to open-r1