English
Related papers

Related papers: Compression Barriers for Autoregressive Transforme…

200 papers

Large language models (LLMs) have demonstrated exceptional capabilities in generating text, images, and video content. However, as context length grows, the computational cost of attention increases quadratically with the number of tokens,…

Computation and Language · Computer Science 2025-04-23 Neusha Javidnia , Bita Darvish Rouhani , Farinaz Koushanfar

Large language models have revolutionized natural language processing but face significant challenges of high storage and runtime costs, due to the transformer architecture's reliance on self-attention, particularly the large KV cache for…

Computation and Language · Computer Science 2026-05-29 Yuan Feng , Junlin Lv , Haoyu Guo , Yukun Cao , S Kevin Zhou , Xike Xie

Long-context ability, has become one of the most important iteration direction of next-generation Large Language Models, particularly in semantic understanding/reasoning, code agentic intelligence and recommendation system. However, the…

To manage the complexity of transformers in video compression, local attention mechanisms are a practical necessity. The common approach of partitioning frames into patches, however, creates architectural flaws like irregular receptive…

Image and Video Processing · Electrical Eng. & Systems 2025-10-07 Alexander Kopte , André Kaup

Large Language Models struggle with memory demands from the growing Key-Value (KV) cache as context lengths increase. Existing compression methods homogenize head dimensions or rely on attention-guided token pruning, often sacrificing…

Computation and Language · Computer Science 2025-06-16 Xiaoran Liu , Siyang He , Qiqi Wang , Ruixiao Li , Yuerong Song , Zhigeng Liu , Linlin Li , Qun Liu , Zengfeng Huang , Qipeng Guo , Ziwei He , Xipeng Qiu

Large Language Models (LLMs) have made significant strides in natural language processing and generation, yet their ability to handle long-context input remains constrained by the quadratic complexity of attention computation and…

Computation and Language · Computer Science 2025-06-16 Manlai Liang , Wanyi Huang , Mandi Liu , Huaijun Li , Jinlong Li

This work studies how to adaptively recompute key-value (KV) caches for diffusion large language models (DLMs) to maximize prediction accuracy while minimizing decoding latency. Prior methods' decoders recompute QKV for all tokens at every…

Computation and Language · Computer Science 2025-12-30 Quan Nguyen-Tri , Mukul Ranjan , Zhiqiang Shen

With the advancements in long-context inference capabilities of large language models (LLMs), the KV cache has become one of the foundational components. However, its substantial GPU memory consumption makes KV cache compression a key…

Computation and Language · Computer Science 2025-03-28 Youhui Zuo , Sibo Wei , Chen Zhang , Zhuorui Liu , Wenpeng Lu , Dawei Song

The inference process for large language models is slow and memory-intensive, with one of the most critical bottlenecks being excessive Key-Value (KV) cache accesses. This paper introduces "Double Sparsity," a novel post-training sparse…

Machine Learning · Computer Science 2024-08-20 Shuo Yang , Ying Sheng , Joseph E. Gonzalez , Ion Stoica , Lianmin Zheng

A range of recent works addresses the problem of compression of sequence of tokens into a shorter sequence of real-valued vectors to be used as inputs instead of token embeddings or key-value cache. These approaches are focused on reduction…

Computation and Language · Computer Science 2025-06-24 Yuri Kuratov , Mikhail Arkhipov , Aydar Bulatov , Mikhail Burtsev

Transformer architectures have led to remarkable progress in many state-of-art applications. However, despite their successes, modern transformers rely on the self-attention mechanism, whose time- and space-complexity is quadratic in the…

Machine Learning · Computer Science 2022-09-13 Feyza Duman Keles , Pruthuvi Mahesakya Wijewardena , Chinmay Hegde

Efficient key-value (KV) cache management is crucial for the practical deployment of large language models (LLMs), yet existing compression techniques often incur a trade-off between performance degradation and computational overhead. We…

Machine Learning · Computer Science 2026-02-10 Jang-Hyun Kim , Dongyoon Han , Sangdoo Yun

The Key-Value (KV) cache is crucial for efficient Large Language Models (LLMs) inference, but excessively long contexts drastically increase KV cache memory footprint. Existing KV cache compression methods typically rely on input-side…

Computation and Language · Computer Science 2026-03-13 Zhenxu Tian , Yi Su , Juntao Li , Min Zhang

Large Language Models (LLMs) use key-value (KV) cache to reduce redundant computation in autoregressive generation. However, the KV cache size increases linearly during generation, leading to excessive memory usage, especially for long…

Computation and Language · Computer Science 2025-03-04 Jian Yuan , Ziwei He , Haoli Bai , Jingwen Leng , Bo Jiang

The impressive capabilities of Large Language Models (LLMs) come at the cost of substantial computational resources during deployment. While KV Cache can significantly reduce recomputation during inference, it also introduces additional…

Computation and Language · Computer Science 2025-05-19 Yi Su , Yuechi Zhou , Quantong Qiu , Juntao Li , Qingrong Xia , Ping Li , Xinyu Duan , Zhefeng Wang , Min Zhang

Token compression is essential for reducing the computational and memory requirements of transformer models, enabling their deployment in resource-constrained environments. In this work, we propose an efficient and hardware-compatible token…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Junzhu Mao , Yang Shen , Jinyang Guo , Yazhou Yao , Xiansheng Hua

Transformer-based models have achieved dominant performance in numerous NLP tasks. Despite their remarkable successes, pre-trained transformers such as BERT suffer from a computationally expensive self-attention mechanism that interacts…

Computation and Language · Computer Science 2024-06-04 Jungmin Yun , Mihyeon Kim , Youngbin Kim

Transformer attention scales quadratically with sequence length O(n^2), limiting long-context use. We propose Adaptive Retention, a probabilistic, layer-wise token selection mechanism that learns which representations to keep under a strict…

Computation and Language · Computer Science 2025-10-13 S M Rafiuddin , Muntaha Nujat Khan

Serving large language models (LLMs) at scale necessitates efficient key-value (KV) cache management. KV caches can be reused across conversation turns via shared-prefix prompts that are common in iterative code editing and chat. However,…

Computation and Language · Computer Science 2026-03-12 Konrad Staniszewski , Adrian Łańcucki

KV cache eviction has emerged as an effective solution to alleviate resource constraints faced by LLMs in long-context scenarios. However, existing token-level eviction methods often overlook two critical aspects: (1) their irreversible…

Machine Learning · Computer Science 2026-01-21 Yi Zhao , Yajuan Peng , Cam-Tu Nguyen , Zuchao Li , Xiaoliang Wang , Hai Zhao , Xiaoming Fu