GreatX3 / Playable-Game-Generation
An open-source lightweight game generation paradigm. It includes everything from data processing to model architecture design and playability-based evaluation methods. The game runs at 20 FPS on a single consumer-grade graphics card (RTX-2060) while maintaining high playability.
☆86Updated 4 months ago
Alternatives and similar repositories for Playable-Game-Generation:
Users that are interested in Playable-Game-Generation are comparing it to the libraries listed below
- ☆126Updated 4 months ago
- [ARXIV'25] GameFactory: Creating New Games with Generative Interactive Videos☆284Updated last month
- [ArXiv 2025] WORLDMEM: Long-term Consistent World Simulation with Memory☆93Updated this week
- Official repo of "Motion-Agent: A Conversational Framework for Human Motion Generation with LLMs"☆56Updated 2 months ago
- [ICML'25] The PyTorch implementation of paper: "AdaWorld: Learning Adaptable World Models with Latent Actions".☆64Updated last month
- Official implementation for WorldScore: A Unified Evaluation Benchmark for World Generation☆96Updated 2 weeks ago
- [World-Model-Survey-2024] Paper list and projects for World Model☆9Updated 6 months ago
- Official repository for "iVideoGPT: Interactive VideoGPTs are Scalable World Models" (NeurIPS 2024), https://arxiv.org/abs/2405.15223☆129Updated 2 months ago
- Video Generation, Physical Commonsense, Semantic Adherence, VideoCon-Physics☆93Updated this week
- An ML research template with good documentation by Boyuan Chen, an MIT PhD student☆69Updated 2 months ago
- The official implementation of work "REPARO: Compositional 3D Assets Generation with Differentiable 3D Layout Alignment".☆113Updated 7 months ago
- GenDoP: Auto-regressive Camera Trajectory Generation as a Director of Photography☆50Updated 3 weeks ago
- Code release for "PISA Experiments: Exploring Physics Post-Training for Video Diffusion Models by Watching Stuff Drop" (arXiv 2025)☆28Updated last month
- A comprehensive list of papers investigating physical cognition in video generation, including papers, codes, and related websites.☆79Updated last week
- [ICML2025] The code and data of Paper: Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation☆101Updated 6 months ago
- MetaSpatial leverages reinforcement learning to enhance 3D spatial reasoning in vision-language models (VLMs), enabling more structured, …☆112Updated last week
- ☆20Updated 5 months ago
- Physical laws underpin all existence, and harnessing them for generative modeling opens boundless possibilities for advancing science and…☆147Updated 2 weeks ago
- ☆71Updated last month
- EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Video Generation☆103Updated 5 months ago
- Official implementation of "Self-Improving Video Generation"☆66Updated last week
- Single-file implementation to advance vision-language-action (VLA) models with reinforcement learning.☆60Updated this week
- [arXiv: 2502.05178] QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation☆69Updated 2 months ago
- PhysGame Benchmark for Physical Commonsense Evaluation in Gameplay Videos☆43Updated 3 months ago
- PyTorch implementation of DiffMoE, TC-DiT, EC-DiT and Dense DiT☆76Updated 2 weeks ago
- (CVPR 2025 Highlight) The Scene Language: Representing Scenes with Programs, Words, and Embeddings☆191Updated 2 months ago
- DreamCinema: Cinematic Transfer with Free Camera and 3D Character☆93Updated 8 months ago
- [CVPR 2025] Science-T2I: Addressing Scientific Illusions in Image Synthesis☆51Updated last week
- [ICLR 2024 Spotlight] Unified Human-Scene Interaction via Prompted Chain-of-Contacts☆205Updated 3 weeks ago
- Official pytorch implementation of MotionLLaMA based on MMEngine☆60Updated 3 months ago