English
Related papers

Related papers: Polynomial Context-Truncation Sensitivity in Autor…

200 papers

Due to limited communication resources at the client and a massive number of model parameters, large-scale distributed learning tasks suffer from communication bottleneck. Gradient compression is an effective method to reduce communication…

Machine Learning · Computer Science 2021-11-17 Kai Liang , Huiru Zhong , Haoning Chen , Youlong Wu

While there is much recent interest in studying why Transformer-based large language models make predictions the way they do, the complex computations performed within each layer have made their behavior somewhat opaque. To mitigate this…

Computation and Language · Computer Science 2023-06-06 Byung-Doh Oh , William Schuler

Autoregressive Transformers adopted in Large Language Models (LLMs) are hard to scale to long sequences. Despite several works trying to reduce their computational cost, most of LLMs still adopt attention layers between all pairs of tokens…

Computation and Language · Computer Science 2024-06-03 Sotiris Anagnostidis , Dario Pavllo , Luca Biggio , Lorenzo Noci , Aurelien Lucchi , Thomas Hofmann

Vision-Language Models suffer severe KV cache pressure at inference, as a single image often encodes into thousands of tokens. Most existing methods exploit token sparsity through token pruning, but permanently discarding visual content…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Beomseok Kang , Dongwon Jo , Jiwon Song , Donghwee Son , Jae-Joon Kim

Existing key-value (KV) cache compression methods for large language models (LLMs) often rely on token eviction, which risks losing critical local information in both long prefilling and decoding scenarios. When extrapolating beyond the…

Computation and Language · Computer Science 2026-01-30 Jushi Kai , Yixuan Wang , Boyi Zeng , Haoli Bai , Bo Jiang , Ziwei He , Zhouhan Lin

Are low-attention visual tokens truly redundant in vision-language reasoning? Existing pruning methods often assume so, ranking visual tokens by shallow text-to-image attention and discarding low-scoring patches to accelerate LVLM…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Jie Ma , Yihang Liu , Zhike Qiu , Jiayi Ji , Xiaoshuai Sun

The Key-Value (KV) cache of Large Language Models (LLMs) is prefix-based, making it highly inefficient for processing contexts retrieved in arbitrary order. Position-Independent Caching (PIC) has been proposed to enable KV reuse without…

Machine Learning · Computer Science 2026-02-03 Shiju Zhao , Junhao Hu , Jiaqi Zheng , Guihai Chen

Existing key-value (KV) cache compression methods typically rely on heuristics, such as uniform cache allocation across layers or static eviction policies, however, they ignore the critical interplays among layer-specific feature patterns…

Machine Learning · Computer Science 2025-09-11 Bohan Yu , Yekun Chai

Large Language Models (LLMs) are increasingly deployed in scenarios demanding ultra-long context reasoning, such as agentic workflows and deep research understanding. However, long-context inference is constrained by the KV cache, a…

Hardware Architecture · Computer Science 2026-03-11 Jianlong Lei , Shashikant Ilager

Large Language Models (LLMs) are increasingly expected to operate over long contexts, yet standard softmax attention incurs a KV cache that grows linearly with sequence length, quickly becoming the bottleneck for long context inference. A…

Computation and Language · Computer Science 2026-05-26 Xintong Yang , Hao Gu , Binxing Xu , Lujun Li , Bei Liu , Jiacheng Liu , Qiyuan Zhu , Sirui Han , Yike Guo

Vision-Language Models (VLMs) face a bottleneck of prohibitive computational costs arising from massive visual token sequences during inference. Existing vision token reduction methods alleviate this burden, but they unintentionally…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Yulin Zhao , Yun Wang , Dehua Zheng , Borui jiang , Zheng Zhang

Large Language Models (LLMs) excel across a variety of language tasks yet are constrained by limited input lengths and high computational costs. Existing approaches\textemdash such as relative positional encodings (e.g., RoPE, ALiBi) and…

Computation and Language · Computer Science 2025-02-18 Kun-Hui Lee , Eunhwan Park , Donghoon Han , Seung-Hoon Na

A key limitation of autoregressive Transformers is the large memory needed at inference-time to cache all previous key-value (KV) embeddings. Prior works address this by compressing the KV cache, but often assume specific structural…

Data Structures and Algorithms · Computer Science 2025-02-25 Themistoklis Haris , Krzysztof Onak

Transformers predict over a representation of a sequence. The same data can be written as bytes, characters, or subword tokens, and these representations may be lossless. Yet, under a fixed context window, they need not expose the same…

Machine Learning · Computer Science 2026-05-14 Amirmehdi Jafari Fesharaki , Mohammadamin Rami , Aslan Tchamkerten

In autoregressive modeling for tensor-valued time series, Tucker decomposition, when applied to the coefficient tensor, provides a clear interpretation of supervised factor modeling but loses its efficiency rapidly with increasing tensor…

Methodology · Statistics 2025-06-03 Yuxi Cai , Lan Li , Yize Wang , Guodong Li

We consider lossy compression of an information source when the decoder has lossless access to a correlated one. This setup, also known as the Wyner-Ziv problem, is a special case of distributed source coding. To this day, real-world…

Information Theory · Computer Science 2023-05-09 Ezgi Ozyilkan , Johannes Ballé , Elza Erkip

Large Language Models (LLMs) require substantial computational resources during generation. While the Key-Value (KV) cache significantly accelerates this process by storing attention intermediates, its memory footprint grows linearly with…

Computation and Language · Computer Science 2025-08-05 Yi Su , Quantong Qiu , Yuechi Zhou , Juntao Li , Qingrong Xia , Ping Li , Xinyu Duan , Zhefeng Wang , Min Zhang

KV cache in autoregressive LLMs eliminates redundant recomputation but has emerged as the dominant memory and bandwidth bottleneck during inference, notably with long contexts and test-time scaling. KV quantization is a key lever for…

Machine Learning · Computer Science 2026-02-03 Ji Zhang , Yiwei Li , Shaoxiong Feng , Peiwen Yuan , Xinglin Wang , Jiayi Shi , Yueqi Zhang , Chuyi Tan , Boyuan Pan , Yao Hu , Kan Li

Top-$k$ decoding is a widely used method for sampling from LLMs: at each token, only the largest $k$ next-token-probabilities are kept, and the next token is sampled after re-normalizing them to sum to unity. Top-$k$ and other sampling…

Artificial Intelligence · Computer Science 2026-02-24 Georgy Noarov , Soham Mallick , Tao Wang , Sunay Joshi , Yan Sun , Yangxinyu Xie , Mengxin Yu , Edgar Dobriban

Large multimodal models (LMMs) have advanced significantly by integrating visual encoders with extensive language models, enabling robust reasoning capabilities. However, compressing LMMs for deployment on edge devices remains a critical…

Artificial Intelligence · Computer Science 2025-07-29 Te Zhang , Yuheng Li , Junxiang Wang , Lujun Li
‹ Prev 1 3 4 5 6 7 10 Next ›