Hunyuan-GameCraft-2
We are looking for self-motivated interns focused on building game world models. Contact: juliatang@tencent.com. PLAYGROUND Tap any scenario capsule to swap the teaser playback. Each button represents a different interaction rendered by Hunyuan-GameCraft-2. ABSTRACT Recent advances in generative world models have enabled remarkable progress in creating open-ended game environments, evolving from static scene synthesis toward dynamic, interactive simulation. However, current approaches remain limited by rigid action schemas and high annotation costs, restricting their ability to model diverse in-game interactions and player-driven dynamics. To address these challenges, we introduce Hunyuan-GameCraft-2, a new paradigm of instruction-driven interaction for generative game world modeling. Instead of relying on fixed keyboard inputs, our model allows users to control game video contents through natural language prompts, keyboard, or mouse signals, enabling flexible and semantically rich int
Abstract Recent advances in generative world models have enabled remarkable progress in creating open-ended game environments, evolving from static scene synthesis toward dynamic, interactive simulation. However, current approaches remain limited by rigid action schemas and high annotation costs, restricting their ability to model diverse in-game interactions and player-driven dynamics. To address these challenges, we introduce Hunyuan-GameCraft-2, a new paradigm of instruction-driven interaction for generative game world modeling. Instead of relying on fixed keyboard inputs, our model…
saved by
related reading
- Building the Infrastructure for AI-Native Games | Entropy AIentropygames.ai
- Seoul World Model: Grounding World Simulation Models in a Real-World Metropolisseoul-world-model.github.io
- [2412.03603] HunyuanVideo: A Systematic Framework For Large Video Generative Modelsarxiv.org
- Interaction Models: A Scalable Approach to Human-AI Collaboration - Thinking Machines Labthinkingmachines.ai
- [2304.03442] Generative Agents: Interactive Simulacra of Human Behaviorarxiv.org
- Yume 1.5: Text-Controlled Interactive World Generationstdstu12.github.io
- [2304.03442] Generative Agents: Interactive Simulacra of Human Behaviorarxiv.org
- Composer2.pdfcursor.com
- Multi-Agent Orchestration for Interactive Multimodal Storytelling in Visual-Novel-Style Adventure Gamesopenaccess.thecvf.com
- Genie 2: A large-scale foundation world modeldeepmind.google
- RT-2: Vision-Language-Action Modelsrobotics-transformer2.github.io
- [2509.24527] Training Agents Inside of Scalable World Modelsarxiv.org