Sana
SANA & Sol: Efficient Generative Models and Full-Stack Training & Inference Engines for Image, Video, and World Modeling
- 9.9k
- Python
- Apache-2.0
- 7 d ago
SANA & Sol: Efficient Generative Models and Full-Stack Training & Inference Engines for Image, Video, and World Modeling
A python library for self-supervised learning and latent world models on images.
Long Video Gen / World Model / World Action Model (Embodied) Infrastructure
NVIDIA Alpamayo 1 Nano is an open 10B reasoning VLA model for autonomous vehicles that pairs driving trajectories with Chain-of-Causation reasoning.
Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the future state of the world in the form of video.
Your AI Game Dev Hub. The ultimate resource hub for AI-powered game development tools. Discover cutting-edge LLMs, World Model, Agent, Code, Image, Texture, Shader, 3D Model, Animation, Video, Audio, Music, Singing Voice and Analytics. 🔥
RSI-Anything: Unlocking Recursive Self-Improvement with World Models
[ICML 2026] Official codebase for "Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation" & Causal Forcing++
Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence
Transformers are Sample-Efficient World Models. ICLR 2023, notable top 5%.
Generate large-scale explorable 3D scenes with high-quality panorama videos from a single image or text prompt.
Cosmos-Transfer2.5, built on top of Cosmos-Predict2.5, produces high-quality world simulations conditioned on multiple spatial control inputs.
A most Frontend Collection and survey of vision-language model papers, and models GitHub repository. Continuous updates.
A Curated List of Awesome Video World Models with AR Diffusion: Covering Algorithms, Applications, and Infrastructure, Aimed at Serving as a Comprehensive Resource for Researchers, Practitioners, and Enthusiasts.
high-performance inference and serving library for interactive autoregressive video and world models
Code as World: Agentic Discovery of Executable World Representations for Physical Reasoning
An open source code repository of driving world models, with training, inferencing, evaluation tools, and pretrained checkpoints.
JEPA-Anything: Learning Predictive Models across Different Worlds
A curated, searchable collection of research on AI and foundation models across the game lifecycle.
NVIDIA Alpamayo 2 Super is an open 34B multi-task foundation model designed to supercharge autonomous vehicle development.
NVIDIA Alpamayo 1.5 Nano is an open 10B reasoning VLA model for autonomous vehicles with reinforcement-learning enhanced reasoning, navigation guidance, and visual question answering.
[CVPR 2026 Highlight] A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens
INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models.
Developer Hub for NVIDIA Alpamayo, containing ready-to-use recipes for fine-tuning, reinforcement-learning post-training, quantization, and deployment.
[ICLR26] Official implementation of Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling
Benchmark for Physical AI generation and understanding
Runs in the browser on Hugging Face
World models physics benchmark, ranked by humans
Runs in the browser on Hugging Face
World models camera movement benchmark, ranked by humans
Runs in the browser on Hugging Face
World models realism benchmark, ranked by humans
Runs in the browser on Hugging Face
World models relative camera benchmark, ranked by humans
Runs in the browser on Hugging Face
Runs in the browser on Hugging Face