Awesome paper list and repos of the paper "A comprehensive survey of embodied world models".

Natural Language Reinforcement Learning

Post-training with Tinker

trpc-agent-go is a powerful Go framework for building intelligent agent systems using large language models (LLMs) and tools.

A Survey of Reinforcement Learning for Large Reasoning Models

Verlog: A Multi-turn RL framework for LLM agents

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

[Embodied-AI-Survey-2025] Paper List and Resource Repository for Embodied AI

Training VLM agents with multi-turn reinforcement learning

Hierarchical Reasoning Model Official Release

[Lumina Embodied AI] 具身智能技术指南 Embodied-AI-Guide

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

Wan: Open and Advanced Large-Scale Video Generative Models

Text-audio foundation model from Boson AI

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

[ICCV 2025] Official code of "ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action Generation"

[NeurIPS 2025] AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning

Cosmos-RL is a flexible and scalable Reinforcement Learning framework specialized for Physical AI applications.

A Flexible Framework for Comprehensive Multimodal Model Evaluation

A Flexible Framework for Comprehensive Multimodal Model Evaluation

From Images to High-Fidelity 3D Assets with Production-Ready PBR Material

CALVIN - A benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks

Monitoring recent cross-research on LLM & RL on arXiv for control. If there are good papers, PRs are welcome.

🔥🔥🔥 [IEEE TCSVT] Latest Papers, Codes and Datasets on Vid-LLMs.

[CVPR'25] SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding

Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model