Remembering What Matters for Long-Horizon Robotic World Models
cs.RO, cs.CV
Submitted: 2026-10-10
Updated: 2026-10-10
Comments: 35 pages
Code: https://github.com/Alexander-wu/ReCAP
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Qwen3-VL Technical Report
- Why do LLMs attend to the first token?
- RT-1: Robotics Transformer for Real-World Control at Scale
- Long-Context Autoregressive Video Modeling with Next-Frame Prediction
- World Models
- Mastering Diverse Domains through World Models
- WorldArena: A Unified Benchmark for Evaluating Perception and Functional Utility of Embodied World Models
- BridgeData V2: A Dataset for Robot Learning at Scale
- RoboAlign-R1: Distilled Multimodal Reward Alignment for Robot Video World Models
- RLVR-World: Training World Models with Reinforcement Learning
- RoboDreamer: Learning Compositional World Models for Robot Imagination
- InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- ARC: A Reasoning Recipe for Robot Foundation Models
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies