Official repository of Text-Image Conditioned 3D Generation (TIGON, CVPR 2026)

Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding

[CVPR 2026] LongVideo-R1: Smart Navigation for Low-cost Long Video Understanding

Sharp Monocular View Synthesis in Less Than a Second

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

UniLat3D: Geometry-Appearance Unified Latents for Single-Stage 3D Generation

A Curated List of Awesome Works in World Modeling, Aiming to Serve as a One-stop Resource for Researchers, Practitioners, and Enthusiasts Interested in World Modeling.

Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"

[ICLR 2026]QeRL enables RL for 32B LLMs on a single H100 GPU.

[CVPR 2025 Highlight] GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control

Long Video Gen Infrastructure

[AAAI 2026] Few-step Flow for 3D Generation via Marginal-Data Transport Distillation

Cameras as Relative Positional Encoding

High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

Segment Anything in 3D with NeRFs (NeurIPS 2023 & IJCV 2025)

Tackling View-Dependent Semantics in 3D Language Gaussian Splatting (ICML 2025)

A Modular Framework for 3D Generation and Beyond [WIP]

SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling

TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models

Dereflection Any Image with Diffusion Priors and Diversified Data [AAAI 2026]

[CVPR 2025 Best Paper Nomination] FoundationStereo: Zero-Shot Stereo Matching

GaussianObject: High-Quality 3D Object Reconstruction from Four Views with Gaussian Splatting (SIGGRAPH Asia 2024, TOG)

[NeurIPS 2024] Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer

GaussianDreamerPro: Text to Manipulable 3D Gaussians with Highly Enhanced Quality

[CVPR 2025 Oral] Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models

[CVPR 2025] Prompt Depth Anything

LiftImage3D: Lifting Any Single Image to 3D Gaussians with Video Generation Priors

Simulation platform for general-purpose robotics & embodied AI learning.

[ICLR'25] SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints

Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).