3DLLM-Mem: Long-Term Spatial-Temporal Memory for Embodied 3D Large Language Model

• URL: http://arxiv.org/abs/2505.22657v1
• Date: Wed, 28 May 2025 17:59:13 GMT
• Title: 3DLLM-Mem: Long-Term Spatial-Temporal Memory for Embodied 3D Large Language Model
• Authors: Wenbo Hu, Yining Hong, Yanjun Wang, Leison Gao, Zibu Wei, Xingcheng Yao, Nanyun Peng, Yonatan Bitton, Idan Szpektor, Kai-Wei Chang,
• Abstract summary: Humans excel at performing complex tasks by leveraging long-term memory across temporal and spatial experiences.<n>Current Large Language Models (LLMs) struggle to effectively plan and act in dynamic, multi-room 3D environments.<n>We propose 3DLLM-Mem, a novel dynamic memory management and fusion model for embodied spatial-temporal reasoning and actions.
• Score: 83.70640091897947
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Humans excel at performing complex tasks by leveraging long-term memory across temporal and spatial experiences. In contrast, current Large Language Models (LLMs) struggle to effectively plan and act in dynamic, multi-room 3D environments. We posit that part of this limitation is due to the lack of proper 3D spatial-temporal memory modeling in LLMs. To address this, we first introduce 3DMem-Bench, a comprehensive benchmark comprising over 26,000 trajectories and 2,892 embodied tasks, question-answering and captioning, designed to evaluate an agent's ability to reason over long-term memory in 3D environments. Second, we propose 3DLLM-Mem, a novel dynamic memory management and fusion model for embodied spatial-temporal reasoning and actions in LLMs. Our model uses working memory tokens, which represents current observations, as queries to selectively attend to and fuse the most useful spatial and temporal features from episodic memory, which stores past observations and interactions. Our approach allows the agent to focus on task-relevant information while maintaining memory efficiency in complex, long-horizon environments. Experimental results demonstrate that 3DLLM-Mem achieves state-of-the-art performance across various tasks, outperforming the strongest baselines by 16.5% in success rate on 3DMem-Bench's most challenging in-the-wild embodied tasks.

Related papers

• Occupancy Learning with Spatiotemporal Memory [39.41175479685905]
  We propose a scene-level occupancy representation learning framework that effectively learns 3D occupancy feature with temporal consistency.<n>Our method significantly enhances thetemporal representation learned for 3D occupancy prediction tasks by exploiting the temporal dependency between multi-frame inputs.
  arXiv  Detail & Related papers  (2025-08-06T17:59:52Z)
• FindingDory: A Benchmark to Evaluate Memory in Embodied Agents [49.89792845476579]
  We introduce a new benchmark for long-range embodied tasks in the Habitat simulator.<n>This benchmark evaluates memory-based capabilities across 60 tasks requiring sustained engagement and contextual awareness.
  arXiv  Detail & Related papers  (2025-06-18T17:06:28Z)
• Long-Context State-Space Video World Models [66.28743632951218]
  We propose a novel architecture leveraging state-space models (SSMs) to extend temporal memory without compromising computational efficiency.<n>Central to our design is a block-wise SSM scanning scheme, which strategically trades off spatial consistency for extended temporal memory.<n>Experiments on Memory Maze and Minecraft datasets demonstrate that our approach surpasses baselines in preserving long-range memory.
  arXiv  Detail & Related papers  (2025-05-26T16:12:41Z)
• MLLM-For3D: Adapting Multimodal Large Language Model for 3D Reasoning Segmentation [87.30919771444117]
  Reasoning segmentation aims to segment target objects in complex scenes based on human intent and spatial reasoning.<n>Recent multimodal large language models (MLLMs) have demonstrated impressive 2D image reasoning segmentation.<n>We introduce MLLM-For3D, a framework that transfers knowledge from 2D MLLMs to 3D scene understanding.
  arXiv  Detail & Related papers  (2025-03-23T16:40:20Z)
• InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions [104.90258030688256]
  This project introduces disentangled streaming perception, reasoning, and memory mechanisms, enabling real-time interaction with streaming video and audio input.<n>This project simulates human-like cognition, enabling multimodal large language models to provide continuous and adaptive service over time.
  arXiv  Detail & Related papers  (2024-12-12T18:58:30Z)
• 3D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning [65.40458559619303]
  We propose 3D-Mem, a novel 3D scene memory framework for embodied agents.<n>3D-Mem employs informative multi-view images, termed Memory Snapshots, to represent the scene.<n>It further integrates frontier-based exploration by introducing Frontier Snapshots-glimpses of unexplored areas-enabling agents to make informed decisions.
  arXiv  Detail & Related papers  (2024-11-23T09:57:43Z)
• KARMA: Augmenting Embodied AI Agents with Long-and-short Term Memory Systems [12.461941212597877]
  Embodied AI agents often face difficulties with in-context memory, leading to inefficiencies and errors in task execution.<n>We introduce KARMA, an innovative memory system that integrates long-term and short-term memory modules.<n>Our memory-augmented embodied AI agent improves success rates by 1.3x and 2.3x in Composite Tasks and Complex Tasks.
  arXiv  Detail & Related papers  (2024-09-23T11:02:46Z)
• End-to-End Egospheric Spatial Memory [32.42361470456194]
  We propose a parameter-free module, Egospheric Spatial Memory (ESM), which encodes the memory in an ego-sphere around the agent. ESM can be trained end-to-end via either imitation or reinforcement learning. We show applications to semantic segmentation on the ScanNet dataset, where ESM naturally combines image-level and map-level inference modalities.
  arXiv  Detail & Related papers  (2021-02-15T18:59:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.