Pith. sign in

REVIEW 3 cited by

Spatially-Aware Transformer for Embodied Agents

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2402.15160 v3 pith:SJE567FC submitted 2024-02-23 cs.LG cs.AI

classification cs.LGcs.AI
keywords memoryspatialepisodicmodelsvariousapproachcognitivedemonstrate
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Episodic memory plays a crucial role in various cognitive processes, such as the ability to mentally recall past events. While cognitive science emphasizes the significance of spatial context in the formation and retrieval of episodic memory, the current primary approach to implementing episodic memory in AI systems is through transformers that store temporally ordered experiences, which overlooks the spatial dimension. As a result, it is unclear how the underlying structure could be extended to incorporate the spatial axis beyond temporal order alone and thereby what benefits can be obtained. To address this, this paper explores the use of Spatially-Aware Transformer models that incorporate spatial information. These models enable the creation of place-centric episodic memory that considers both temporal and spatial dimensions. Adopting this approach, we demonstrate that memory utilization efficiency can be improved, leading to enhanced accuracy in various place-centric downstream tasks. Additionally, we propose the Adaptive Memory Allocator, a memory management method based on reinforcement learning that aims to optimize efficiency of memory utilization. Our experiments demonstrate the advantages of our proposed model in various environments and across multiple downstream tasks, including prediction, generation, reasoning, and reinforcement learning. The source code for our models and experiments will be available at https://github.com/junmokane/spatially-aware-transformer.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Visual Embodied Brain: Let Multimodal Large Language Models See, Think, and Control in Spaces

    cs.CV 2025-05 reject novelty 6.0 of 10

    VeBrain unifies perception, spatial reasoning, and robot control in one MLLM by representing control as keypoint detection plus skill selection, with a robotic adapter for deployment.

  2. Spatially-informed transformers: Injecting geostatistical covariance biases into self-attention for spatio-temporal forecasting

    cs.LG 2025-12 reject novelty 5.0 of 10

    Adds a learnable Matérn covariance bias to self-attention; claims it recovers true spatial decay and beats GNNs, but the reported numbers conflict with the stated generative model and real-data results are absent.

  3. Mind Meets Space: Rethinking Agentic Spatial Intelligence from a Neuroscience-inspired Perspective

    cs.AI 2025-09 conditional novelty 4.0 of 10

    Agent spatial intelligence is organized into six neuroscience-inspired modules, and the field is reviewed through that lens without any experimental validation.

Pith tools