Multimodal Agent MemorySubmit a paper

SceneGraphGrounder

SceneGraphGrounder: Zero-Shot 3D Visual Grounding via Structured Scene Graph Matching

Xuefei Sun, Xujia Zhang, Brendan Crowe, Doncey Albin, Christoffer Heckman · 2026-05-20

Read the paperPDF

Management
T1 Static Memory
Memory is built once and reused without change during deployment.
Primary modality
Embodied & 3D
Also: text, Image, video
Representation
Hybrid
Distinct operative representation paths are deliberately linked or jointly consumed by downstream reasoning, generation, or control.

How experience becomes memory

Each path is one memory component, traced from what is stored to how it is found again.

  1. persistent 3D scene graph of objects, relations, and spatial attributes built from RGB-D streams

    1. Represented asModality-specific encodings & geometric stateSource- and modality-specific
    2. Stored inGraph / relational store
    3. Retrieved byStructure traversal
    4. Source evidenceRetained but not accessible to the agent
    Scene graph nodes (objects) and edges (relations) with spatial attributes; query-graph parsings. language queries are parsed into a query graph and matched against the persistent scene graph.Full-paper method / memory representation and retrieval · PDF p. 3 · Figure 1 / method overview

  2. persistent 3D scene graph of objects, relations, and spatial attributes built from RGB-D streams

    1. Represented asSpatial, temporal & cross-modal structured memoryCross-represented explicit
    2. Stored inGraph / relational store
    3. Retrieved byStructure traversal
    4. Source evidenceSource not retained
    Scene graph nodes (objects) and edges (relations) with spatial attributes; query-graph parsings. language queries are parsed into a query graph and matched against the persistent scene graph.Full-paper method / memory representation and retrieval · PDF p. 3 · Figure 1 / method overview

Related systems