mlsanityData to 14 Oct 2026

LongSpace: Exploring Long-Horizon Spatial Memory from Perception to Recall in Video

arXiv 2606.05677 ↗First posted 4 Jun 2026cs.CV cs.AI cs.CLcited by 0

On the map: Multimodal LLMs / vision-language models → Embodied and 3D vision-language models

Abstract (arXiv)

Multimodal Large Language Models (MLLMs) have advanced image and video understanding and can increasingly handle longer visual inputs. Long-horizon tasks such as autonomous driving and robotic navigation require more than recognizing the current view, as models must remember and retrieve previously observed spatial layouts, routes, viewpoint changes, and object states. To evaluate this capability, we introduce LongSpace-Bench, a room-tour video benchmark for long-horizon spatial memory, covering scene perception, spatial relations, and spatial memory. In this work, we further propose LongSpace, a memory framework for long-video spatial reasoning. LongSpace models long videos as sequential chunks, incorporates 3D structural cues into early decoder layers, and constructs layer-aware memory for question-guided retrieval. Experiments on multiple spatial reasoning benchmarks show that LongSpace improves long-video spatial understanding, further demonstrating explicit spatial memory as a key capability for long-horizon video MLLMs.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 15 of its 24 references that are in the map. First posted on arXiv 4 Jun 2026.

Builds on

15 of 24 references.

Closest ancestors · 8

Same direction, newest first

  1. 2026OnlineSI: Taming Large Language Model for Online 3D Understanding and Grounding23 Jan
  2. 2025Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors30 May
  3. 2025MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence29 May
  4. 2025Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence29 May
  5. 2025STI-Bench: Are MLLMs Ready for Precise Spatial-Temporal World Understanding?31 Mar
  6. 2025From Flatland to Space: Teaching Vision-Language Models to Perceive and Reason in 3D29 Mar
  7. 2024Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces18 Dec
  8. 2024SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities22 Jan

Other references · 7

  1. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,719
  2. 2024Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMscited by 838
  3. 2023VILA: On Pre-training for Visual Language Modelscited by 692
  4. 2024Long Context Transfer from Language to Visioncited by 515
  5. 2024LongVILA: Scaling Long-Context Visual Language Models for Long Videoscited by 309
  6. 20243D-Mem: 3D Scene Memory for Embodied Exploration and Reasoningcited by 75
  7. 2025Vision to Geometry: 3D Spatial Memory for Sequential Embodied MLLM Reasoning and Explorationcited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Spatial Memory Intelligence: Endowing World Models with Understanding-Driven Long-Term Memory
  2. 2025Vision-Language Memory for Spatial Reasoning
  3. 2026Q-GeoMem: Question-Guided Geometric Memory for Video Spatial Reasoning
  4. 2025Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks
  5. 2026ViSTR-Bench: Can MLLMs Reason from Continuous Visual Cues in Dynamic Scenes?
  6. 2025Why Do MLLMs Struggle with Spatial Understanding? A Systematic Analysis from Data to Architecture
  7. 2026Seeing the Scene Matters: Revealing Forgetting in Video Understanding Models with a Scene-Aware Long-Video Benchmark
  8. 2025LAST: LeArning to Think in Space and Time for Generalist Vision-Language Models