[ICML'26] VideoGPA is a self-supervised framework that enhances 3D consistency in Video Diffusion Models.
☆77Jun 6, 2026Updated 3 months ago
Alternatives and similar repositories for VideoGPA
Users that are interested in VideoGPA are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Synthetic Video hallucination and Mitigation☆25Sep 21, 2025Updated 11 months ago
- AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers☆165Sep 16, 2025Updated last year
- [CVPRW'26] A collection and survey of 3d dataset☆36Jun 4, 2026Updated 3 months ago
- grpo to train long form QA and instructions with long-form reward model☆17Jul 17, 2025Updated last year
- code for "GeoVideo: Introducing Geometric Regularization into Video Generation Models"☆21Jan 8, 2026Updated 8 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- [ICML 2026] Official codebase for "Flash-VAED: Plug-and-Play VAE Decoders for Efficient Video Generation"☆44Aug 5, 2026Updated last month
- COS-PLAY: Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Game Play☆31Jul 11, 2026Updated 2 months ago
- Official repo for: Epipolar Geometry Improves Video Generation Models☆95Oct 28, 2025Updated 10 months ago
- An easy python package to run quick basic QA evaluations. This package includes standardized QA evaluation metrics and semantic evaluatio…☆64Jul 18, 2025Updated last year
- Official implementation for WorldScore: A Unified Evaluation Benchmark for World Generation☆312Jul 23, 2026Updated last month
- [CVPR 2026 Highlight] tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction☆458Jun 10, 2026Updated 3 months ago
- [CVPR2026] Long-horizon, spatially consistent video generation enabled by persistent 3D scene point clouds and dynamic-static disentangle…☆234May 12, 2026Updated 4 months ago
- [ICLR 2026] FantasyWorld: Geometry-Consistent World Modeling via Unified Video and 3D Prediction☆446Feb 25, 2026Updated 6 months ago
- [NeurIPS 2025] Video World Models with Long-term Spatial Memory☆85May 11, 2026Updated 4 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- [CVPR 2026] Gen3R: 3D Scene Generation Meets Feed-Forward Reconstruction☆381Mar 20, 2026Updated 6 months ago
- [CVPR 2026] WorldStereo: Bridging Camera-Guided Video Generation and Scene Reconstruction via 3D Geometric Memories (WorldExpand of HY-Wo…☆227Apr 24, 2026Updated 4 months ago
- [ICML 2026] World-R1: Reinforcing 3D Constraints for Text-to-Video Generation☆426Jun 3, 2026Updated 3 months ago
- OneWorld: Taming Scene Generation with 3D Unified Representation Autoencoder☆63Sep 12, 2026Updated last week
- 🧂 [ECCV 2026] Salt: Self-Consistent Distribution Matching with Cache-Aware Training for Fast Video Generation☆21Aug 24, 2026Updated 3 weeks ago
- VerseCrafter: Dynamic Realistic Video World Model with 4D Geometric Control☆439Jul 20, 2026Updated 2 months ago
- HY-World 1.5: A Systematic Framework for Interactive World Modeling with Real-Time Latency and Geometric Consistency☆1,603Jun 10, 2026Updated 3 months ago
- Code implementation for: From Virtual Games to Real-World Play☆49Jun 23, 2025Updated last year
- ☆60Oct 19, 2025Updated 11 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- [ECCV 2026] Official implementation of "MemRoPE: Training-Free Infinite Video Generation via Evolving Memory Tokens"☆57Jun 24, 2026Updated 2 months ago
- A Minimal and Elegant Framework & Tutorial for Real-Time Interactive World Models☆830Sep 10, 2026Updated last week
- [CVPR2025] MAGE : Single Image to Material-Aware 3D via the Multi-View G-Buffer Estimation Model☆22Oct 9, 2025Updated 11 months ago
- Self-evolving vision language models from zero data☆83Mar 14, 2026Updated 6 months ago
- Real-Time Physical Action-Conditioned Video Generation☆228Mar 6, 2026Updated 6 months ago
- open-sourced video dataset with dynamic scenes and camera movements annotation☆101Apr 24, 2025Updated last year
- [ECCV 2026] Official Code of "Distribution Matching Distillation Meets Reinforcement Learning"☆298Feb 1, 2026Updated 7 months ago
- Official Repository of paper: "MotionEdit: Benchmarking and Learning Motion-Centric Image Editing"☆68Feb 28, 2026Updated 6 months ago
- [ICLR 2025 Oral] Official code for "LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias"☆559Aug 4, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- The first open-domain closed-loop revisited benchmark for evaluating memory consistency and action control in world models.☆81Jul 2, 2026Updated 2 months ago
- Light Transport Gaussian: Relightable 3D Gaussians Based on Precomputed Radiance Transfer☆38Aug 13, 2024Updated 2 years ago
- Official PyTorch implementation for "FlexWorld: Progressively Expanding 3D Scenes for Flexiable-View Synthesis".☆136Sep 11, 2025Updated last year
- [ICLR 2026 oral] Official code for VIST3A: Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generator☆147May 20, 2026Updated 4 months ago
- DreamX-World: A General-Purpose Interactive World Model☆771Jul 23, 2026Updated last month
- ☆310May 20, 2026Updated 4 months ago
- Code release for https://wonderzoom.github.io/☆206Apr 14, 2026Updated 5 months ago