RoboColosseum: Evaluating Physical Intelligence at Scale In-The-Wild
cs.RO, cs.AI
Submitted: 2026-11-02
Updated: 2026-11-02
Terminology
Sources
- Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
- RoboArena: Distributed Real-World Evaluation of Generalist Robot Policies
- GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
- RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies
- MolmoAct2: Action Reasoning Models for Real-world Deployment
- DataComp: In search of the next generation of multimodal datasets
- VLA-REPLICA: A Low-Cost, Reproducible Benchmark for Real-World Evaluation of Vision-Language-Action Models
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
- OpenVLA: An Open-Source Vision-Language-Action Model
- MolmoSpaces: A Large-Scale Open Ecosystem for Robot Navigation and Manipulation
- MolmoAct: Action Reasoning Models that can Reason in Space
- Evaluating Real-World Robot Manipulation Policies in Simulation
- Code as Policies: Language Model Programs for Embodied Control
- G0.5: One Autoregressive Stream for Robot Reasoning and Action
- THE COLOSSEUM: A Benchmark for Evaluating Generalization for Robotic Manipulation
- Gemini Robotics: Bringing AI into the Physical World
- Octo: An Open-Source Generalist Robot Policy
- RoboEval: Where Robotic Manipulation Meets Structured and Scalable Evaluation
- RoboPlayground: Democratizing Robotic Evaluation through Structured Physical Domains
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation