End-to-End Context Compression at Scale

• URL: http://arxiv.org/abs/2606.09659v1
• Date: Mon, 08 Jun 2026 15:43:16 GMT
• Title: End-to-End Context Compression at Scale
• Abstract summary: Long-context language model inference is bottlenecked by memory, as the KV cache grows with context length.<n>Recent techniques to compress the KV cache fall short: they either degrade model quality substantially or require considerable time and compute to compress a single long prompt.<n>Existing approaches are not competitive with KV cache compression on the accuracy-efficiency frontier.
• Score: 81.70601323130997
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Long-context language model inference is bottlenecked by memory, as the KV cache grows with context length. Recent techniques to compress the KV cache fall short: they either degrade model quality substantially or require considerable time and compute to compress a single long prompt. Furthermore, many methods require the input to fit within the target model's context window, and are generally incompatible with modern production inference engines. Encoder-decoder compressors, which map a long token sequence to a shorter sequence of latent embeddings consumed by a decoder, are an appealing alternative in principle. However, existing approaches are not competitive with KV cache compression on the accuracy-efficiency frontier. In this work, we revisit encoder-decoder compression and close this gap. We first perform an architecture search, pre-training many variants from scratch to determine how best to design and train encoder-decoder compressors. Guided by our findings, we continually pre-train a family of 0.6B-encoder, 4B-decoder models on over 350B tokens each, at compression ratios of 1:4, 1:8, and 1:16. We introduce Latent Context Language Models (LCLMs), a family of compressors that improve the Pareto frontier across general-task performance, compression speed, and peak memory usage. We demonstrate that LCLMs serve as efficient backbones for long-horizon agents, letting the agent skim through a compressed long context and adaptively expand relevant segments on demand.

Related papers

• VoxZip: Semantic-Anchored Temporal KV Cache Compression for Long-Context Audio Inference [53.883871460875234]
  VoxZip is a semantic-anchored KV cache compression framework.<n>First stage uses automatic speech recognition (ASR) transcriptions as explicit semantic anchors to temporally align, compress, and fuse audio tokens.<n>Second stage employs a dynamic filtering strategy based on temporally decayed accumulated attention to evict non-essential tokens.
  arXiv  Detail & Related papers  (2026-08-09T08:17:18Z)
• One Token per Highly Selective Frame: Towards Extreme Compression for Long Video Understanding [51.08792182064565]
  Long video understanding is inherently challenging for vision-language models (VLMs) because of the extensive number of frames.<n>With each video frame typically expanding into tens or hundreds of tokens, the limited context length of large language models (LLMs) forces the VLMs to perceive the frames sparsely and lose temporal information.<n>We propose an extreme compression model for long video understanding, named XComp, achieving a significantly larger compression ratio and enabling denser frame sampling.
  arXiv  Detail & Related papers  (2026-04-15T17:59:52Z)
• EchoKV: Efficient KV Cache Compression via Similarity-Based Reconstruction [55.026048429595384]
  EchoKV is a flexible KV cache compression scheme that enables on-demand transitions between standard and compressed inference.<n>We introduce a two-stage fine-tuning strategy that allows for rapid, low-cost training.
  arXiv  Detail & Related papers  (2026-03-24T07:58:42Z)
• DeltaKV: Residual-Based KV Cache Compression via Long-Range Similarity [50.52392445266824]
  We propose a residual-based KV cache compression framework motivated by long-range inter-token similarity and highly shared latent components in KV representations.<n>Instead of discarding tokens, DeltaKV encodes semantic residuals relative to retrieved historical references, preserving fidelity while substantially reducing storage.<n>Experiments show that DeltaKV reduces KV cache memory to 29% of the original while maintaining near-lossless accuracy on LongBench, SCBench, and AIME.
  arXiv  Detail & Related papers  (2026-02-08T15:14:36Z)
• Cmprsr: Abstractive Token-Level Question-Agnostic Prompt Compressor [36.57824786347272]
  We present the first comprehensive LLM-as-a-compressor benchmark spanning 25 open- and closed-source models.<n>We improve the performance of the best overall vanilla compressor, with Textgrad-based compression meta-prompt optimization.<n>We call the resulting model Cmprsr and demonstrate its superiority over both extractive and vanilla abstractive compression.
  arXiv  Detail & Related papers  (2025-11-15T16:28:03Z)
• Compactor: Calibrated Query-Agnostic KV Cache Compression with Approximate Leverage Scores [37.41699761967978]
  KV cache is often the dominant resource bottleneck in real-world deployments.<n>We present Compactor, a parameter-free, query-agnostic KV compression strategy.<n>We show that Compactor achieves full KV performance on Longbench while reducing the KV memory burden by 63%, on average.
  arXiv  Detail & Related papers  (2025-07-10T20:03:35Z)
• KV-Distill: Nearly Lossless Learnable Context Compression for LLMs [37.0803484148612]
  We introduce KV-Distill, a Transformer compression framework that distills long context KV caches into significantly shorter representations.<n> KV-Distill can be trained as a parameter-efficient adaptor for pretrained models.<n>It can be fine-tuned on domain-specific contexts to reduce lengths by up to 99% while preserving downstream performance.
  arXiv  Detail & Related papers  (2025-03-13T13:15:28Z)
• QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache [67.84112700032007]
  Large Language Models (LLMs) are increasingly being deployed on edge devices for long-context settings.<n>In these scenarios, the Key-Value ( KV) cache is the primary bottleneck in terms of both GPU memory and latency.<n>We propose a novel self-speculative decoding framework, QuantSpec, where the draft model shares the architecture of the target model but employs a hierarchical 4-bit quantized KV cache and 4-bit quantized weights for acceleration.
  arXiv  Detail & Related papers  (2025-02-05T20:43:48Z)
• LoRC: Low-Rank Compression for LLMs KV Cache with a Progressive Compression Strategy [59.1298692559785]
  Key-Value ( KV) cache is crucial component in serving transformer-based autoregressive large language models (LLMs) Existing approaches to mitigate this issue include: (1) efficient attention variants integrated in upcycling stages; (2) KV cache compression at test time; and (3) KV cache compression at test time. We propose a low-rank approximation of KV weight matrices, allowing plug-in integration with existing transformer-based LLMs without model retraining. Our method is designed to function without model tuning in upcycling stages or task-specific profiling in test stages.
  arXiv  Detail & Related papers  (2024-10-04T03:10:53Z)

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.