SEER-Bench
Vision to Geometry: 3D Spatial Memory for Sequential Embodied MLLM Reasoning and Exploration
Zhongyi Cai, Yi Du, Chen Wang, Yu Kong · 2026-03-18
- Modality
- Embodied & 3D
- Data
- Simulated
- Task · ground truth
- QA/Plan/Act. · Ans.+State+Act.
- Scope
- Memory-specific benchmark
What it tests
- CECross-modal evidenceDirectly evaluated
- LELong-range evidenceDirectly evaluated
- SCState changesDirectly evaluated
- CFConflicting memoriesNot evaluated
- UQUnanswerable queriesNot evaluated
- MAMemory-grounded actionDirectly evaluated
- SMSpatial memoryDirectly evaluated
- OSObject-state trackingDirectly evaluated
- TSTask-state trackingDirectly evaluated
Survey notes
Sequential navigation and questions evaluate reuse of scene experience over multiple goals.