Official code for Echo-Memory: a controlled study of memory in action-conditioned video world models (Context, Compression, Spatial, State-Space).
-
Updated
Aug 16, 2026 - Python
Official code for Echo-Memory: a controlled study of memory in action-conditioned video world models (Context, Compression, Spatial, State-Space).
mindmap: Spatial Memory in Deep Feature Maps for 3D Action Policies
Spatial field location memory for document processing pipelines. Learns field positions, validates extractions, identifies document types by layout, detects drift, and monitors template health. Zero dependencies, pure Python.
Long-term memory infrastructure for .NET AI agents with semantic, temporal, spatial and robotics memory, hybrid retrieval, and pluggable providers.
A Spatial Retrieval-Augmented Generation system for latent world models, designed for embodied spatial intelligence in robotics, autonomous navigation, and embodied AI. Features ROS2 integration, real-time inference @ 25Hz, and complete robot build guide.
A Machine Learning Aware Spatial Data Re-partitioning Framework for Spatial Datasets
Spatial Metaphors for LLM Memory: A Critical Analysis of the MemPalace Architecture — Full paper, benchmarks, experiment data, and reproduction scripts
Spatial memory for hierarchical VLA policies (extends MemER)
End-to-End Egospheric Spatial Memory (ESM) encodes the memory in an ego-sphere around the agent.
Spatial memory layer for AI agents — RGB-D / point clouds to a persistent, queryable, LLM-native 3D scene graph. Mem0 for 3D space.
ADHD-friendly visual planning with draggable timelines, planned-versus-actual tracking, and map-based memories.
Control architecture for an agent that perceives, plans, learns, and acts in a 3D MMORPG. Evolved from a monolith through reactive rules, state machines, and utility scoring to GOAP planning. JPS/A* pathfinding, DDA line-of-sight, Bayesian adaptation. Pure Python 3.14 (free-threaded), zero dependencies.
mindmap
A simple spatial memory game
指针空间:轻量原生 macOS 空间文件画布,用稳定位置快速找到真实文件。
associative memory in mixed reality
An embodied agent that builds confidence-weighted spatial memory and detects when that memory becomes unreliable under environmental change or noisy perception. Extended with CLIP-based language grounding.
Data and code for Beardsworth et al. (2021) Is habitat selection shaped by individual-level cognitive biases in orientation strategy? Ecology Letters
Spatial scene graphs and belief state for embodied agents
학습 자료의 의미 구조를 걸어다닐 수 있는 3D 기억의 궁전으로 변환하는 AI 학습 서비스
To associate your repository with the spatial-memory topic, visit your repo's landing page and select "manage topics."