R$^3$Mem: Bridging Memory Retention and Retrieval via Reversible Compression

• URL: http://arxiv.org/abs/2502.15957v1
• Date: Fri, 21 Feb 2025 21:39:00 GMT
• Title: R$^3$Mem: Bridging Memory Retention and Retrieval via Reversible Compression
• Authors: Xiaoqiang Wang, Suyuchen Wang, Yun Zhu, Bang Liu,
• Abstract summary: We propose R$3$Mem, a memory network that optimize both information Retention and Retrieval.<n>R$3$Mem employs virtual memory tokens to compress and encode infinitely long histories, further enhanced by a hierarchical compression strategy.<n>Experiments demonstrate that our memory design achieves state-of-the-art performance in long-context language modeling and retrieval-augmented generation tasks.
• Score: 24.825945729508682
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Memory plays a key role in enhancing LLMs' performance when deployed to real-world applications. Existing solutions face trade-offs: explicit memory designs based on external storage require complex management and incur storage overhead, while implicit memory designs that store information via parameters struggle with reliable retrieval. In this paper, we propose R$^3$Mem, a memory network that optimizes both information Retention and Retrieval through Reversible context compression. Specifically, R$^3$Mem employs virtual memory tokens to compress and encode infinitely long histories, further enhanced by a hierarchical compression strategy that refines information from document- to entity-level for improved assimilation across granularities. For retrieval, R$^3$Mem employs a reversible architecture, reconstructing raw data by invoking the model backward with compressed information. Implemented via parameter-efficient fine-tuning, it can integrate seamlessly with any Transformer-based model. Experiments demonstrate that our memory design achieves state-of-the-art performance in long-context language modeling and retrieval-augmented generation tasks. It also significantly outperforms conventional memory modules in long-horizon interaction tasks like conversational agents, showcasing its potential for next-generation retrieval systems.

Related papers

• Rethinking Memory in AI: Taxonomy, Operations, Topics, and Future Directions [55.19217798774033]
  Memory is a fundamental component of AI systems, underpinning large language models (LLMs) based agents. We introduce six fundamental memory operations: Consolidation, Updating, Indexing, Forgetting, Retrieval, and Compression. This survey provides a structured and dynamic perspective on research, benchmark datasets, and tools related to memory in AI.
  arXiv  Detail & Related papers  (2025-05-01T17:31:33Z)
• Cognitive Memory in Large Language Models [8.059261857307881]
  This paper examines memory mechanisms in Large Language Models (LLMs), emphasizing their importance for context-rich responses, reduced hallucinations, and improved efficiency. It categorizes memory into sensory, short-term, and long-term, with sensory memory corresponding to input prompts, short-term memory processing immediate context, and long-term memory implemented via external databases or structures.
  arXiv  Detail & Related papers  (2025-04-03T09:58:19Z)
• Improving Factuality with Explicit Working Memory [68.39261790277615]
  Large language models can generate factually inaccurate content, a problem known as hallucination.<n>We introduce EWE (Explicit Working Memory), a novel approach that enhances factuality in long-form text generation by integrating a working memory that receives real-time feedback from external resources.
  arXiv  Detail & Related papers  (2024-12-24T00:55:59Z)
• Memory Layers at Scale [67.00854080570979]
  This work takes memory layers beyond proof-of-concept, proving their utility at contemporary scale.<n>On downstream tasks, language models augmented with our improved memory layer outperform dense models with more than twice the budget, as well as mixture-of-expert models when matched for both compute and parameters.<n>We provide a fully parallelizable memory layer implementation, demonstrating scaling laws with up to 128B memory parameters, pretrained to 1 trillion tokens, comparing to base models with up to 8B parameters.
  arXiv  Detail & Related papers  (2024-12-12T23:56:57Z)
• $\text{Memory}^3$: Language Modeling with Explicit Memory [22.572376536612015]
  We equip large language models (LLMs) with explicit memory, a memory format cheaper than model parameters and text retrieval-augmented generation (RAG) As a preliminary proof of concept, we train from scratch a 2.4B LLM, which achieves better performance than much larger LLMs and RAG models. We introduce a memory circuitry theory to support the externalization of knowledge, and present novel techniques including a memory sparsification mechanism that makes storage tractable.
  arXiv  Detail & Related papers  (2024-07-01T11:07:23Z)
• Empowering Working Memory for Large Language Model Agents [9.83467478231344]
  This paper explores the potential of applying cognitive psychology's working memory frameworks to large language models (LLMs) An innovative model is proposed incorporating a centralized Working Memory Hub and Episodic Buffer access to retain memories across episodes. This architecture aims to provide greater continuity for nuanced contextual reasoning during intricate tasks and collaborative scenarios.
  arXiv  Detail & Related papers  (2023-12-22T05:59:00Z)
• Recurrent Action Transformer with Memory [39.58317527488534]
  This paper proposes a novel model architecture that incorporates a recurrent memory mechanism designed to regulate information retention. We conduct experiments on memory-intensive environments (ViZDoom-Two-Colors, T-Maze, Memory Maze, Minigrid-Memory), classic Atari games, and MuJoCo control environments. The results show that using memory can significantly improve performance in memory-intensive environments, while maintaining or improving results in classic environments.
  arXiv  Detail & Related papers  (2023-06-15T19:29:08Z)
• SCM: Enhancing Large Language Model with Self-Controlled Memory Framework [54.33686574304374]
  Large Language Models (LLMs) are constrained by their inability to process lengthy inputs, resulting in the loss of critical historical information. We propose the Self-Controlled Memory (SCM) framework to enhance the ability of LLMs to maintain long-term memory and recall relevant information.
  arXiv  Detail & Related papers  (2023-04-26T07:25:31Z)
• Recurrent Dynamic Embedding for Video Object Segmentation [54.52527157232795]
  We propose a Recurrent Dynamic Embedding (RDE) to build a memory bank of constant size. We propose an unbiased guidance loss during the training stage, which makes SAM more robust in long videos. We also design a novel self-correction strategy so that the network can repair the embeddings of masks with different qualities in the memory bank.
  arXiv  Detail & Related papers  (2022-05-08T02:24:43Z)
• Neural Storage: A New Paradigm of Elastic Memory [4.307341575886927]
  Storage and retrieval of data in a computer memory plays a major role in system performance. We introduce Neural Storage (NS), a brain-inspired learning memory paradigm that organizes the memory as a flexible neural memory network. NS achieves an order of magnitude improvement in memory access performance for two representative applications.
  arXiv  Detail & Related papers  (2021-01-07T19:19:25Z)
• Memformer: A Memory-Augmented Transformer for Sequence Modeling [55.780849185884996]
  We present Memformer, an efficient neural network for sequence modeling. Our model achieves linear time complexity and constant memory space complexity when processing long sequences.
  arXiv  Detail & Related papers  (2020-10-14T09:03:36Z)
• Distributed Associative Memory Network with Memory Refreshing Loss [5.5792083698526405]
  We introduce a novel Distributed Associative Memory architecture (DAM) with Memory Refreshing Loss (MRL) Inspired by how the human brain works, our framework encodes data with distributed representation across multiple memory blocks. MRL enables MANN to reinforce an association between input data and task objective by reproducing input data from stored memory contents.
  arXiv  Detail & Related papers  (2020-07-21T07:34:33Z)

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.