# REMI: Reconstructing Episodic Memory During Internally Driven Path Planning

arXiv: https://arxiv.org/abs/2507.02064 · HTML: https://mlsanity.com/paper/2507.02064/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 78 references that are in the map.
- First posted on arXiv 2 Jul 2025.

## Builds on (most cited first, 13 of 13)

- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [Habitat 2.0: Training Home Assistants to Rearrange their Habitat](https://mlsanity.com/paper/2106.14405/) (2021)
- [Successor Features for Transfer in Reinforcement Learning](https://mlsanity.com/paper/1606.05312/) (2016)
- [Habitat Synthetic Scenes Dataset (HSSD-200): An Analysis of 3D Scene Scale and Realism Tradeoffs for ObjectGoal Navigation](https://mlsanity.com/paper/2306.11290/) (2023)
- [Emergence of grid-like representations by training recurrent neural networks to perform spatial localization](https://mlsanity.com/paper/1803.07770/) (2018)
- [The Sense of Place: Grid Cells in the Brain and the Transcendental Number e](https://mlsanity.com/paper/1304.0031/) (2013)
- [Self-Supervised Learning of Representations for Space Generates Multi-Modular Grid Cells](https://mlsanity.com/paper/2311.02316/) (2023)
- [On Conformal Isometry of Grid Cells: Learning Distance-Preserving Position Embedding](https://mlsanity.com/paper/2405.16865/) (2024)
- [Time Makes Space: Emergence of Place Fields in Networks Encoding Temporally Continuous Sensory Experiences](https://mlsanity.com/paper/2408.05798/) (2024)
- [A geometric attractor mechanism for self-organization of entorhinal grid modules](https://mlsanity.com/paper/1806.00975/) (2018)

## Built on by (most cited first, 2 of 2)

- [When and Where: A Model Hippocampal Network Unifies Formation of Time Cells and Place Cells](https://mlsanity.com/paper/2604.00036/) (2026)
- [LASAR: Towards Spatio-temporal Reasoning with Latent Cognitive Map](https://mlsanity.com/paper/2605.16899/) (2026)

## Abstract (arXiv)

Grid cells in the medial entorhinal cortex (MEC) and place cells in the hippocampus (HC) both form spatial representations. Grid cells fire in triangular grid patterns, while place cells fire at specific locations and respond to contextual cues. How do these interacting systems support not only spatial encoding but also internally driven path planning, such as navigating to locations recalled from cues? Here, we propose a system-level theory of MEC-HC wiring that explains how grid and place cell patterns could be connected to enable cue-triggered goal retrieval, path planning, and reconstruction of sensory experience along planned routes. We suggest that place cells autoassociate sensory inputs with grid cell patterns, allowing sensory cues to trigger recall of goal-location grid patterns. We show analytically that grid-based planning permits shortcuts through unvisited locations and generalizes local transitions to long-range paths. During planning, intermediate grid states trigger place cell pattern completion, reconstructing sensory experiences along the route. Using a single-layer RNN modeling the HC-MEC loop with a planning subnetwork, we demonstrate these effects in both biologically grounded navigation simulations using RatatouGym and visually realistic navigation tasks using Habitat Sim.