GeoMind: A Benchmark for Spatial Understanding in Robotic Manipulation
cs.RO, cs.AI
Submitted: 2026-11-09
Updated: 2026-11-09
Code: https://github.com/Notfound-JH/GEOMIND-ben
Terminology
Sources
- World Action Models are Zero-shot Policies
- OpenWAM: An Open Framework for Composable World-Action Models
- ASPIRE: Agentic /Skills Discovery for Robotics
- ENPIRE: Agentic Robot Policy Self-Improvement in the Real World
- InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy
- RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation
- Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces
- CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks
- Evaluating Real-World Robot Manipulation Policies in Simulation
- ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI
- RMBench: Memory-Dependent Robotic Manipulation Benchmark with Insights into Policy Design
- RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies
- MEMOBench: A Process Level Memory Benchmark for Robotic Manipulation
- BEHAVIOR-Spatial Benchmark: Evaluating Spatial Understanding for Robotics
- VABench: Measuring Embodied Spatial Intelligence through Visual Demonstrations, Active Perception, and Metric Control
- RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics
- ESPIRE: A Diagnostic Benchmark for Embodied Spatial Reasoning of Vision-Language Models
- DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modeling
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