A unified framework for 3D content generation.

NVIDIA Isaac GR00T N1.6 - A Foundation Model for Generalist Robots.

A data generation pipeline for creating semi-realistic synthetic multi-object videos with rich annotations such as instance segmentation masks, depth maps, and optical flow.

Stable Diffusion implemented from scratch in PyTorch

VPoser: Variational Human Pose Prior

Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition

Cosmos-Predict1 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications.

[NeurIPS 2025] Official code for JAFAR: Jack up Any Feature at Any Resolution

Benchmark for generative image models

Measuring the Mixing of Contextual Information in the Transformer

[CVPR'25] How Do I Do That? Synthesizing 3D Hand Motion and Contacts for Everyday Interactions

Data visualization and Information Design with Python and R

Exploratory Data Analysis in Scala

Azure Synapse Analytics Tutorials