Next Forcing: World Action Modeling with Multi-Chunk Prediction (MCP)
☆103Jul 12, 2026Updated this week
Alternatives and similar repositories for next-forcing
Users that are interested in next-forcing are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Zero-WAM, an in-context world model for zero-shot robotic task generalization☆30Updated this week
- Code for RepWAM: World Action Modeling with Representation Visual-Action Tokenizers☆56Jun 14, 2026Updated last month
- Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence☆782Updated this week
- Infinite Worlds with Versatile Interactions☆1,092Updated this week
- Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models☆264Apr 29, 2026Updated 2 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Galaxea's first diffusion policy release☆41Aug 18, 2025Updated 10 months ago
- Official code and data from DexWM ("World Models Can Leverage Human Videos for Dexterous Manipulation").☆93Jun 23, 2026Updated 3 weeks ago
- Official implementation of MTM☆21Aug 30, 2023Updated 2 years ago
- Self-supervised learning for spatial perception☆765Updated this week
- A Minimal and Elegant Framework & Tutorial for Real-Time Interactive World Models☆709Jun 15, 2026Updated 3 weeks ago
- ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?☆129Updated this week
- ☆61Jul 3, 2026Updated last week
- ☆21Jun 29, 2026Updated 2 weeks ago
- Official codebase for Fast-WAM: Do World Action Models Need Test-time Future Imagination?☆1,146Apr 3, 2026Updated 3 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.
- ☆106Jun 12, 2026Updated last month
- ☆298May 20, 2026Updated last month
- From Foundation to Application☆531Updated this week
- ☆52Jun 19, 2026Updated 3 weeks ago
- A curated list of academic papers and resources on Vision-Language-Action (VLA) and World Action Models (WAM)☆30Updated this week
- ICCV 2025 | TesserAct: Learning 4D Embodied World Models☆401Aug 4, 2025Updated 11 months ago
- [ICCV 23] A Simple Vision Transformer for Weakly Semi-supervised 3D Object Detection☆13Apr 12, 2024Updated 2 years ago
- [CVPR 2026] ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training☆461Jun 11, 2026Updated last month
- [ECCV 2026] One4D: Unified 4D Generation and Reconstruction☆113Jun 18, 2026Updated 3 weeks ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- high-performance inference and serving library for interactive autoregressive video and world models☆389Updated this week
- RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation☆58Updated this week
- Official repo for paper "Echo-Infinity: Learnable Evolving Memory for Real-Time Infinite Video Generation"☆103Jun 4, 2026Updated last month
- [ECCV 2024] Make Your ViT-based Multi-view 3D Detectors Faster via Token Compression☆53Sep 21, 2024Updated last year
- Reasoning in Space via Grounding in the World (ICLR 2025)☆56Nov 3, 2025Updated 8 months ago
- 【ICML 2026】GemDepth: Geometry-Embedded Features for 3D-Consistent Video Depth☆167Jul 7, 2026Updated last week
- [ICML 2026] World-R1: Reinforcing 3D Constraints for Text-to-Video Generation☆407Jun 3, 2026Updated last month
- Implementation of D4RT, Efficiently Reconstructing Dynamic Scenes, from Deepmind☆73Jun 20, 2026Updated 3 weeks ago
- HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation☆64May 1, 2026Updated 2 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.
- UniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous Driving☆211Apr 14, 2026Updated 3 months ago
- [ICCV 2025] DASH: 4D Hash Encoding with Self-Supervised Decomposition for Real-Time Dynamic Scene Rendering☆27Apr 13, 2026Updated 3 months ago
- On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators☆127Updated this week
- Unified World Model Inference & Evaluation Infrastructure☆195Updated this week
- Official Implementation of "Kinema4D: Kinematic4D World Modeling for Spatiotemporal Embodied Simulation"☆76May 21, 2026Updated last month
- Flow Map OPD for AnyStep Video Diffusion☆392May 23, 2026Updated last month
- Official implementation of Aurora☆86Sep 20, 2023Updated 2 years ago