Official implementation of PrismWAM: Decoupling State Representations in World Action Models
☆64Oct 23, 2026Updated 3 weeks ago
Alternatives and similar repositories for PrismWAM
Users that are interested in PrismWAM are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- The official code implementation for RoboDoctor: Training-Free Recursive Self-Improvement for Robot Policies☆19Oct 23, 2026Updated 3 weeks ago
- [ECCV 2026] Towards Spatial Supersensing in the Wild☆23Jul 16, 2026Updated 4 months ago
- [ICML 2026] GameVerse: Can Vision-Language Models Learn from Video-based Reflection?☆55Oct 7, 2026Updated last month
- AMP1: Agentic Manipulation Policy☆71Nov 9, 2026Updated last week
- [CVPR 2026] Thinking in 360°: Humanoid Visual Search in the Wild☆150Sep 21, 2026Updated last month
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Official implementation of SG-WAM☆14Aug 2, 2026Updated 3 months ago
- ☆36Oct 22, 2026Updated 3 weeks ago
- Official implementation of Video Prediction Policy 2: Predict Better, Act Better☆376Oct 19, 2026Updated 3 weeks ago
- the official repository of the WorldArena benchmark☆18Mar 23, 2026Updated 7 months ago
- Official repository for "OpenWAM: An Open, Modular Exploration Towards Systematic World–Action Model Pretraining".☆1,204Updated this week
- Video-action policy for robot arms☆116Updated this week
- Towards Generalist Game Agents: A Survey of Foundation Models in Virtual Worlds☆56Nov 9, 2026Updated last week
- [ACM MM 2026] Official Repository of "TwinRL-VLA: Digital Twin-Driven Reinforcement Learning for Real-World Robotic Manipulation"☆32Jul 11, 2026Updated 4 months ago
- [AAAI 2025] Official implementation of QORT-Former: Query-optimized Real-time Transformer for Understanding Two Hands Manipulating Object…☆12Apr 14, 2025Updated last year
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- This is the official code release for the report: VLAFlow: A Unified Training Framework for Vision-Language-Action Models via Co-training…☆17Sep 24, 2026Updated last month
- DexTacWAM: A Visuo-Tactile World-Action Model for Dexterous Manipulation☆29Sep 30, 2026Updated last month
- [CVPR 2026 Highlight] Official implementation of PAD-Hand: Physics-Aware Diffusion for Hand Motion Recovery☆15Jun 3, 2026Updated 5 months ago
- DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation☆68Sep 7, 2026Updated 2 months ago
- ☆18Oct 9, 2026Updated last month
- Official code for "μ0: A Scalable 3D Interaction-Trace World Model" (CoRL 2026)☆72Oct 27, 2026Updated 3 weeks ago
- GPT-Policy: In-Context Robot Learning with VLM Agents☆364Oct 17, 2026Updated last month
- [IROS 26 ScaleInfra Workshop Best Tool Paper] Involving over 50 Advanced Manipulation Policies☆583Updated this week
- ActionPiece: Rethinking Action Tokenization for Autoregressive Vision-Language-Action Models☆19Sep 17, 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.
- Paper: "Ψ-0.6: Adaptive Streams of Thought in a Unified Vision- Language World Model"☆25Oct 26, 2026Updated 3 weeks ago
- Official code of Discrete Forcing☆16Oct 4, 2026Updated last month
- RoboQuest is a benchmark for goal-directed embodied exploration, in which a mobile manipulator must gather task-relevant information thro…☆11Oct 8, 2026Updated last month
- Flex-π: A multi-stream world-action model with compute flexibility: one checkpoint that deploys as a VLA, a full world model, or anything…☆239Updated this week
- A unified framework for building, evaluating, and recursively improving embodied agents. 🚀 Code release coming soon.☆801Updated this week
- Dream2Flow: Bridging Video Generation and Open-World Manipulation with 3D Object Flow☆49Mar 28, 2026Updated 7 months ago
- A Bimanual Manipulation Benchmark across Dexterous Hands with Simulated Visuo-Tactile Support☆108Updated this week
- Official repo of "FlowWAM: Optical Flow as a Unified Action Representation for World Action Models"☆55Jul 15, 2026Updated 4 months ago
- ☆41Sep 2, 2026Updated 2 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.
- Official implemetation of the paper "Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising".☆63Sep 24, 2026Updated last month
- [EMNLP 2026 Oral] RoboSPA Official Code Repo☆21Nov 7, 2026Updated last week
- [ICML 2026]☆21Jul 4, 2026Updated 4 months ago
- ☆34Apr 4, 2026Updated 7 months ago
- ODE Policy: Robot Learning via Action Dynamics, Not Actions (arXiv:2611.01729)☆122Updated this week
- V0.5: open-weight world action model for general-purpose industrial robotics☆26Nov 4, 2026Updated 2 weeks ago
- MobiAgent: Dual-Loop Recursive Policy Self-Improvement for Long-Horizon Mobile Manipulation☆18Oct 26, 2026Updated 3 weeks ago
Are these results useful?