[CVPR 2026 Highlight] A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens
☆275Jul 17, 2026Updated 3 months ago
Alternatives and similar repositories for deltatok
Users that are interested in deltatok are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Official implementation of "Planning in 8 Tokens: A Compact Discrete Tokenizer for Latent World Model" (CVPR 2026)☆82Mar 9, 2026Updated 7 months ago
- World Modeling by Forecasting Vision Foundation Model Features☆59Jul 25, 2026Updated 3 months ago
- Single-stage End-to-End Training for Tokenization and Generation☆122Mar 24, 2026Updated 7 months ago
- A Minimal and Elegant Framework & Tutorial for Real-Time Interactive World Models☆867Sep 10, 2026Updated last month
- Official Implemenation for RAEv2: Improved Baselines with Representation Autoencoders☆337May 21, 2026Updated 5 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.
- Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"☆2,101Feb 25, 2026Updated 8 months ago
- LVMT: Video Mask Transformer for Long-term Video Segmentation☆20Oct 8, 2026Updated 3 weeks ago
- Cameras as Relative Positional Encoding☆768Dec 18, 2025Updated 10 months ago
- [NeurIPS 2025] Official Implementation of DINO-Foresight: Looking into the Future with DINO☆179Updated this week
- Official PyTorch Implementation of Unified Video Action Model (RSS 2025)☆415Aug 21, 2026Updated 2 months ago
- Foundation models for 4D spatial and temporal vision tasks.☆408Oct 19, 2026Updated last week
- [CVPR 2026 Workshop] Official code and models for Plain Mask Transformer (PMT).☆71Sep 4, 2026Updated last month
- [ICML 2026] code & model for arxiv paper "Autoregressive Image Generation with Masked Bit Modeling"☆59May 1, 2026Updated 6 months ago
- [ICLR 2026 Oral] Latent Particle World Models official repository☆143Mar 19, 2026Updated 7 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- A Minimalist, Batteries-included Repository for Advancing World Model Science.☆767Sep 14, 2026Updated last month
- Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders☆266Feb 13, 2026Updated 8 months ago
- Official codebase for Fast-WAM: Do World Action Models Need Test-time Future Imagination?☆1,631Aug 20, 2026Updated 2 months ago
- WorldReel: 4D Video Generation with Consistent Geometry and Motion Modeling☆21Apr 11, 2026Updated 6 months ago
- Metis: A Generalizable and Efficient World-Action Model for Autonomous Driving and Urban Navigation☆18Jun 16, 2026Updated 4 months ago
- Flow Map OPD for AnyStep Video Diffusion☆447Aug 14, 2026Updated 2 months ago
- VideoFlexTok: Flexible-Length Coarse-to-Fine Video Tokenization☆56Sep 11, 2026Updated last month
- [NeurIPS 2025] WorldMem: Long-term Consistent World Simulation with Memory☆401Feb 21, 2026Updated 8 months ago
- [CVPR 2026] Visual Geometry Transformer for Autonomous Driving☆372Jun 10, 2026Updated 4 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- ☆579May 1, 2026Updated 6 months ago
- An Agent Harness for Inverse Physics of Dynamic Scenes☆32Oct 21, 2026Updated last week
- Official implementation of Tuna-2: Pixel Embeddings Beat Vision Encoders for Unified Understanding and Generation☆763Jul 22, 2026Updated 3 months ago
- [CoRL 2026] Code for "FACT: Failure-Aware Causal Training for World‑Action Models"☆107Sep 15, 2026Updated last month
- NVIDIA FastGen: Fast Generation from Diffusion Models☆1,098Updated this week
- [Tech Report] Context Scaling: Scaling Properties of Text Conditioning in Visual Generation☆188Aug 7, 2026Updated 2 months ago
- Code for ICCV'2025 (Best student paper honorable mention) "RayZer: A Self-supervised Large View Synthesis Model"☆449Nov 24, 2025Updated 11 months ago
- Official implementation of "Repurposing Geometric Foundation Models for Multi-view Diffusion"☆277Jul 24, 2026Updated 3 months ago
- Code for the paper "Remember to be Curious: Episodic Context and Persistent Worlds for 3D Exploration"☆61May 22, 2026Updated 5 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆88Jul 13, 2026Updated 3 months ago
- [ICLR 2025 Oral] Official code for "LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias"☆570Aug 4, 2025Updated last year
- Code to pretrain, fine-tune, and evaluate DreamZero and run sim & real-world evals☆2,747Apr 19, 2026Updated 6 months ago
- ☆101Apr 14, 2026Updated 6 months ago
- Public code for XFactor: Introduces the first geometry-free model to achieve true self-supervised / pose-free Novel View Synthesis (NVS) …☆167May 11, 2026Updated 5 months ago
- Sekai2: From World Exploration to Interactive World Modeling☆77Sep 9, 2026Updated last month
- [ICLR 2026] A simple state update rule to enhance length generalization for CUT3R☆739May 11, 2026Updated 5 months ago