hlnull
Follow
Starred repositories
DriveLaW: Unifying Planning and Video Generation in a Latent Driving World
[ICLR 2026] FantasyWorld: Geometry-Consistent World Modeling via Unified Video and 3D Prediction
Our first fully AI generated deep learning system
Official implementation of MAD: Motion Appearance Decoupling for efficient Driving World Models.
VerseCrafter: Dynamic Realistic Video World Model with 4D Geometric Control
DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Driving
OpenVDB - Sparse volume data structure and tools
[ICCV 2025] InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models
Curated list of papers and resources focused on 3D Gaussian Splatting, intended to keep pace with the anticipated surge of research in the coming months.
A 3DGS framework for omni urban scene reconstruction and simulation.
Official Code for Epona: Autoregressive Diffusion World Model for Autonomous Driving (ICCV 2025)
Hackable and optimized Transformers building blocks, supporting a composable construction.
New repo collection for NVIDIA Cosmos: https://github.com/nvidia-cosmos
This package contains the original 2012 AlexNet code.
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.
A unified media (Image, Video, Audio, Text) diffusion repository, for education and learning.
An open source implementation of CLIP.
A generative world for general-purpose robotics & embodied AI learning.
A curated list for awesome discrete diffusion models resources.
The ultimate training toolkit for finetuning diffusion models
An automated pipeline for evaluating LLMs for role-playing.
Materials for the Learn PyTorch for Deep Learning: Zero to Mastery course.
Collection of LaTeX resources and examples.
Boost LaTeX typesetting efficiency with preview, compile, autocomplete, colorize, and more.