PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Image (CVPR 2026)

[ICML 2026] WorldMirror: Fast and Universal 3D reconstruction model for versatile tasks

Native Multimodal Models are World Learners

[CVPR 2025] Ref-GS : Directional Factorization for 2D Gaussian Splatting

a comprehensive investigation of advanced physical aware AIGC works

The official repository for the paper "Optimal Flow Matching: Learning Straight Trajectories in Just One Step" (NeurIPS 2024)

[CVPR 2025 Highlight] VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step

[ECCV 2024] DreamReward: Text-to-3D Generation with Human Preference

[CVPR 2025] Official repository for “MagicArticulate: Make Your 3D Models Articulation-Ready”

[ICLR 2025] OmniPhysGS: 3D Constitutive Gaussians for General Physics-based Dynamics Generation

[CVPR 2025] Sparse Voxels Rasterization: Real-time High-fidelity Radiance Field Rendering

This is a simple demonstration of more advanced, agentic patterns built on top of the Realtime API.

Official PyTorch implementation of "A Unified Approach for Text- and Image-guided 4D Scene Generation", [CVPR 2024]

(CVPR 2025 Highlight) The Scene Language: Representing Scenes with Programs, Words, and Embeddings

DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 Spotlight.

[ICCV 2023] New framework: Domain adaptation using a single prompt. Main contribution: Prompt-driven Instance Normalization (PIN)

[NeurIPS 2024] HDR 3D Scene Editing!

Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

List of papers on 4D Generation.

[ICLR 2025] 3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting

[ICCV 2025 Highlight] MaGS: Reconstructing and Simulating Dynamic 3D Objects with Mesh-adsorbed Gaussian Splatting

[SIGGRAPH Asia'24 & TOG] Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenes

EMNLP 2023 Papers: Explore cutting-edge research from EMNLP 2023, the premier conference for advancing empirical methods in natural language processing. Stay updated on the latest in machine learni…

A Modular Framework for 3D Gaussian Splatting and Beyond

An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)

[CVPR 2024] S-DyRF: Reference-Based Stylized Radiance Fields for Dynamic Scenes

🌊 [ECCV'24 Oral] MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images