Compressing Sequences in the Latent Embedding Space: $K$-Token Merging for Large Language Models

• URL: http://arxiv.org/abs/2604.15153v2
• Date: Wed, 22 Apr 2026 01:59:13 GMT
• Title: Compressing Sequences in the Latent Embedding Space: $K$-Token Merging for Large Language Models
• Abstract summary: Large Language Models incur significant computational and memory costs when processing long prompts.<n>We propose K-Token Merging, a latent-space compression framework that merges each contiguous block of K token embeddings into a single embedding.<n>Experiments show that K-Token Merging achieves up to 75% input length reduction with minimal performance degradation.
• Score: 35.95256971588258
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) incur significant computational and memory costs when processing long prompts, as full self-attention scales quadratically with input length. Token compression aims to address this challenge by reducing the number of tokens representing inputs. However, existing prompt-compression approaches primarily operate in token space and overlook inefficiencies in the latent embedding space. In this paper, we propose K-Token Merging, a latent-space compression framework that merges each contiguous block of K token embeddings into a single embedding via a lightweight encoder. The compressed sequence is processed by a LoRA-adapted LLM, while generation remains in the original vocabulary. Experiments on structural reasoning (Textualized Tree), sentiment classification (Amazon Reviews), and code editing (CommitPackFT) show that K-Token Merging lies on the Pareto frontier of performance vs. compression, achieving up to 75% input length reduction with minimal performance degradation. Code is available at https://github.com/shsjxzh/K-Token-Merging.

Related papers

• Meta-Soft: Leveraging Composable Meta-Tokens for Context-Preserving KV Cache Compression [12.589754555104768]
  KV cache used in large language models has linearly growing time complexity.<n>Current KV Cache eviction methods rely on a static parameter set as the query to evaluate the importance of KV pairs.<n>We propose Meta-Soft, a dynamic compression framework based on probe-driven context integration.
  arXiv  Detail & Related papers  (2026-05-21T11:24:46Z)
• Elastic-dLLM: Position Preserving Context Compression and Augmentation of Diffusion LLMs [21.48723638711438]
  We revisit dLLM's redundancy from the perspective of [MASK] tokens.<n>We propose position-preserving [MASK] token compression and terminal-aware augmentation.
  arXiv  Detail & Related papers  (2026-05-18T10:09:10Z)
• Large Language Model as Token Compressor and Decompressor [13.847845643427119]
  We show that an off-the-shelf LLM can function as an excellent token compressor and decompressor.<n>We use a self-expressive autoencoding learning framework to translate long texts into a compact internal language of discrete, variable-length latent codes, termed Z-tokens.
  arXiv  Detail & Related papers  (2026-03-26T11:30:44Z)
• CORE: Compact Object-centric REpresentations as a New Paradigm for Token Merging in LVLMs [29.08277140543501]
  We introduce CORE (Compact Object-centric REpresentations), a new paradigm for visual token compression.<n> CORE leverages an efficient segmentation decoder to generate object masks, which serve as a high-level semantic prior to guide the merging of visual tokens.<n>Experiments show that CORE not only establishes a new state-of-the-art on six authoritative benchmarks for fixed-rate compression, but also achieves dramatic efficiency gains in adaptive-rate settings.
  arXiv  Detail & Related papers  (2025-11-18T03:02:23Z)
• R1-Compress: Long Chain-of-Thought Compression via Chunk Compression and Search [61.4807238517108]
  Chain-of-Thought (CoT) reasoning enhances large language models (LLMs) by enabling step-by-step problem-solving.<n>CoT's extension to Long-CoT introduces substantial computational overhead due to increased token length.<n>We propose R1-Compress, a two-stage chunk-level compression framework that preserves both local information and coherence.
  arXiv  Detail & Related papers  (2025-05-22T16:06:59Z)
• VQToken: Neural Discrete Token Representation Learning for Extreme Token Reduction in Video Large Language Models [35.38573641029626]
  We introduce the novel task of Extreme Short Token Reduction, which aims to represent entire videos using a minimal set of discrete tokens.<n>On the Extreme Short Token Reduction task, our VQToken compresses sequences to just 0.07 percent of their original length while incurring only a 0.66 percent drop in accuracy on the NextQA-MC benchmark.
  arXiv  Detail & Related papers  (2025-03-21T09:46:31Z)
• Vision-centric Token Compression in Large Language Model [51.92055188780033]
  Vision Centric Token Compression (Vist) is a slow-fast compression framework that mirrors human reading.<n>On eleven in-context learning benchmarks, Vist achieves the same accuracy with 2.3 times fewer tokens, cutting FLOPs by 16% and memory by 50%.
  arXiv  Detail & Related papers  (2025-02-02T13:10:06Z)
• ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference [61.412894960600205]
  Large Language Models (LLMs) require significant GPU memory when processing long texts.<n>ChunkKV reimagines KV cache compression by treating semantic chunks as basic compression units.<n>Result: ChunkKV outperforms state-of-the-art methods by up to 8.7% in precision.
  arXiv  Detail & Related papers  (2025-02-01T03:49:47Z)
• Compressing KV Cache for Long-Context LLM Inference with Inter-Layer Attention Similarity [24.118503938098307]
  textscPoD allocates memory according to token importance.<n>textscPoD reduces KV cache memory usage by up to 35% without compromising performance.
  arXiv  Detail & Related papers  (2024-12-03T08:29:27Z)
• Training LLMs over Neurally Compressed Text [55.11828645767342]
  This paper explores the idea of training large language models (LLMs) over highly compressed text.<n>We propose Equal-Info Windows, a novel compression technique whereby text is segmented into blocks that each compress to the same bit length.<n>We demonstrate effective learning over neurally compressed text that improves with scale, and outperforms byte-level baselines by a wide margin on perplexity and inference speed benchmarks.
  arXiv  Detail & Related papers  (2024-04-04T17:48:28Z)
• Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference [78.65321721142624]
  We focus on a memory bottleneck imposed by the key-value ( KV) cache. Existing KV cache methods approach this problem by pruning or evicting large swaths of relatively less important KV pairs. We propose LESS, a simple integration of a constant sized cache with eviction-based cache methods.
  arXiv  Detail & Related papers  (2024-02-14T18:54:56Z)
• Context Compression for Auto-regressive Transformers with Sentinel Tokens [37.07722536907739]
  We propose a plug-and-play approach that is able to incrementally compress the intermediate activation of a specified span of tokens into compact ones. Experiments on both in-domain language modeling and zero-shot open-ended document generation demonstrate the advantage of our approach.
  arXiv  Detail & Related papers  (2023-10-12T09:18:19Z)

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.