CoMeT: Collaborative Memory Transformer for Efficient Long Context Modeling

• URL: http://arxiv.org/abs/2602.01766v1
• Date: Mon, 02 Feb 2026 07:49:44 GMT
• Title: CoMeT: Collaborative Memory Transformer for Efficient Long Context Modeling
• Authors: Runsong Zhao, Shilei Liu, Jiwei Tang, Langming Liu, Haibin Chen, Weidong Zhang, Yujin Yuan, Tong Xiao, Jingbo Zhu, Wenbo Su, Bo Zheng,
• Abstract summary: We introduce a novel architecture that enables LLMs to handle arbitrarily long sequences with constant memory usage and linear time complexity.<n>CoMeT can be integrated into pre-trained models with only minimal fine-tuning.<n>A model equipped with CoMeT and fine-tuned on 32k contexts can accurately retrieve a passkey from any position within a 1M token sequence.
• Score: 40.705016911274
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The quadratic complexity and indefinitely growing key-value (KV) cache of standard Transformers pose a major barrier to long-context processing. To overcome this, we introduce the Collaborative Memory Transformer (CoMeT), a novel architecture that enables LLMs to handle arbitrarily long sequences with constant memory usage and linear time complexity. Designed as an efficient, plug-in module, CoMeT can be integrated into pre-trained models with only minimal fine-tuning. It operates on sequential data chunks, using a dual-memory system to manage context: a temporary memory on a FIFO queue for recent events, and a global memory with a gated update rule for long-range dependencies. These memories then act as a dynamic soft prompt for the next chunk. To enable efficient fine-tuning on extremely long contexts, we introduce a novel layer-level pipeline parallelism strategy. The effectiveness of our approach is remarkable: a model equipped with CoMeT and fine-tuned on 32k contexts can accurately retrieve a passkey from any position within a 1M token sequence. On the SCROLLS benchmark, CoMeT surpasses other efficient methods and achieves performance comparable to a full-attention baseline on summarization tasks. Its practical effectiveness is further validated on real-world agent and user behavior QA tasks. The code is available at: https://anonymous.4open.science/r/comet-B00B/

Related papers

• Memory Caching: RNNs with Growing Memory [56.25483647131372]
  We introduce Memory Caching (MC), a technique that enhances recurrent models by caching checkpoints of memory states (a.k.a. hidden states)<n>We propose four variants of MC, including gated aggregation and sparse selective mechanisms, and discuss their implications on both linear and deep memory modules.<n>The results indicate that while Transformers achieve the best accuracy, our MC variants show competitive performance, close the gap with Transformers, and performs better than state-of-the-art recurrent models.
  arXiv  Detail & Related papers  (2026-02-27T18:53:41Z)
• Gated Associative Memory: A Parallel O(N) Architecture for Efficient Sequence Modeling [0.0]
  Gated Associative Memory (GAM) network is a novel, fully parallel architecture for sequence modeling.<n>We implement GAM from scratch and conduct a rigorous comparative analysis against a standard Transformer model and a modern linear-time baseline.<n>Our experiments demonstrate that GAM is consistently faster, outperforming both baselines on training speed, and achieves a superior or competitive final validation perplexity across all datasets.
  arXiv  Detail & Related papers  (2025-08-30T20:59:46Z)
• Compress, Gather, and Recompute: REFORMing Long-Context Processing in Transformers [58.98923344096319]
  REFORM is a novel inference framework that efficiently handles long contexts through a two-phase approach.<n>It achieves over 50% and 27% performance gains on RULER and BABILong respectively at 1M context length.<n>It also outperforms baselines on Infinite-Bench and MM-NIAH, demonstrating flexibility across diverse tasks and domains.
  arXiv  Detail & Related papers  (2025-06-01T23:49:14Z)
• Sliding Window Attention Training for Efficient Large Language Models [55.56483740523027]
  We introduce SWAT, which enables efficient long-context handling via Sliding Window Attention Training.<n>This paper first attributes the inefficiency of Transformers to the attention sink phenomenon.<n>We replace softmax with the sigmoid function and utilize a balanced ALiBi and Rotary Position Embedding for efficient information compression and retention.
  arXiv  Detail & Related papers  (2025-02-26T05:31:44Z)
• MoM: Linear Sequence Modeling with Mixture-of-Memories [11.7218875689111]
  We introduce a novel architecture called Mixture-of-Memories (MoM)<n>MoM utilizes multiple independent memory states, with a router network directing input tokens to specific memory states.<n>MoM performs exceptionally well on recall-intensive tasks, surpassing existing linear sequence modeling techniques.
  arXiv  Detail & Related papers  (2025-02-19T12:53:55Z)
• Logarithmic Memory Networks (LMNs): Efficient Long-Range Sequence Modeling for Resource-Constrained Environments [0.0]
  This paper introduces Logarithmic Memory Networks (LMNs), a novel architecture that leverages a hierarchical logarithmic tree structure to efficiently store and retrieve past information.<n>LMNs dynamically summarize historical context, significantly reducing the memory footprint and computational complexity of attention mechanisms.<n>These features make LMNs a robust and scalable solution for processing long-range sequences in resource-constrained environments.
  arXiv  Detail & Related papers  (2025-01-14T07:50:09Z)
• Mini-Sequence Transformer: Optimizing Intermediate Memory for Long Sequences Training [78.93900796545523]
  Mini-Sequence Transformer (MsT) is a methodology for highly efficient and accurate LLM training with extremely long sequences. MsT partitions input sequences and iteratively processes mini-sequences to reduce intermediate memory usage. integrated with the huggingface library, MsT successfully extends the maximum context length of Qwen, Mistral, and Gemma-2 by 12-24x.
  arXiv  Detail & Related papers  (2024-07-22T01:52:30Z)
• Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs [61.40047491337793]
  We present Hierarchical cOntext MERging (HOMER), a new training-free scheme designed to overcome the limitations of large language models. HomeR uses a divide-and-conquer algorithm, dividing long inputs into manageable chunks. A token reduction technique precedes each merging, ensuring memory usage efficiency.
  arXiv  Detail & Related papers  (2024-04-16T06:34:08Z)
• UniPT: Universal Parallel Tuning for Transfer Learning with Efficient Parameter and Memory [69.33445217944029]
  PETL is an effective strategy for adapting pre-trained models to downstream domains. Recent PETL works focus on the more valuable memory-efficient characteristic. We propose a new memory-efficient PETL strategy, Universal Parallel Tuning (UniPT)
  arXiv  Detail & Related papers  (2023-08-28T05:38:43Z)

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.