Official implementation of "Continuous Autoregressive Language Models"

Part-X-MLLM: Part-aware 3D Multimodal Large Language Model

Official Code Release of NeurIPS 2025 Paper: HoloScene: Simulation‑Ready Interactive 3D Worlds from a Single Video

The repository provides code for running inference with the SAM 3D Body Model (3DB), links for downloading the trained model checkpoints and datasets, and example notebooks that show how to use the…

HunyuanVideo-1.5: A leading lightweight video generation model

Vector (and Scalar) Quantization, in Pytorch

IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction

PyTorch implementation of JiT https://arxiv.org/abs/2511.13720

Depth Anything 3

[ICLR 2024] Code for LEAP: Liberate Sparse-view 3D Modeling from Camera Poses

An unofficial and simplified implementation of SIGGRAPH 2025 best paper nominate: CAST: Component-Aligned 3D Scene Reconstruction from an RGB Image, working in progress

[CVPR'25 Oral] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision

PhysWorld: From Real Videos to World Models of Deformable Objects via Physics-Aware Demonstration Synthesis

Native Multimodal Models are World Learners

Leetcode for Pytorch

WorldGrow: Generating Infinite 3D World [AAAI 2026 Oral]

ValueCell is a community-driven, multi-agent platform for financial applications.

A curated list of research papers, resources, and advancements on Diffusion Cache and related efficient diffusion model acceleration techniques.

Cupid: A 3D generator that links 2D image with camera

[NeurIPS'25] Official repository of Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations

Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Views

[CORL 2025 Oral]One View, Many Worlds: Single-Image to 3D Object Meets Generative Domain Randomization for One-Shot 6D Pose Estimation.

[Neurips DB 2025] PartNeXt: A Next-Generation Dataset for Fine-Grained and Hierarchical 3D Part Understanding

[ICCV 2025] InstaScene: Towards Complete 3D Instance Decomposition and Reconstruction from Cluttered Scenes

Contexts Optical Compression