[CVPR 2024] Exploiting Diffusion Prior for Generalizable Dense Prediction

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

[ICCV 2025] GameFactory: Creating New Games with Generative Interactive Videos

[AAAI 2025] Few-step Flow for 3D Generation via Marginal-Data Transport Distillation

LL3M writes Python code that generates 3D assets in Blender.

Official code repository of "DNF: Unconditional 4D Generation with Dictionary-based Neural Fields" @ CVPR 2025

Official repository for the paper "CAP4D: Creating Animatable 4D Portrait Avatars with Morphable Multi-View Diffusion Models"

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

This repo contains the code for 1D tokenizer and generator

[NeurIPS 2025 Spotlight] Official repository for “Puppeteer: Rig and Animate Your 3D Models”

Reference PyTorch implementation and models for DINOv3

Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model

ViPE: Video Pose Engine for Geometric 3D Perception

Official Repo of TexVerse: A Universe of 3D Objects with High-Resolution Textures

A unified inference and post-training framework for accelerated video generation.

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.

[ICLR'25 Oral] Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think

[ICCV'25 oral] Official Code for "LoftUp: Learning a Coordinate-Based Feature Upsampler for Vision Foundation Models"

Code for "Scaling Language-Free Visual Representation Learning" paper (Web-SSL).

Wan: Open and Advanced Large-Scale Video Generative Models

GPT-IMAGE-EDIT-1.5M: A Million-Scale, GPT-Generated Image Dataset

Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels with Hunyuan3D World Model

Make your wildest 3D ConvNet dream architectures come true

[NeurIPS 2025] PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers

[ICCV 2025] SpatialTrackerV2: 3D Point Tracking Made Easy

PhysX: Physical-Grounded 3D Asset Generation (NeurIPS 2025, Spotlight)