English
Related papers

Related papers: LEXI: Lossless Exponent Coding for Efficient Inter…

200 papers

Recent advances in 1-bit Large Language Models (LLMs), such as BitNet and BitNet b1.58, present a promising approach to enhancing the efficiency of LLMs in terms of speed and energy consumption. These developments also enable local LLM…

Computation and Language · Computer Science 2024-10-24 Jinheng Wang , Hansong Zhou , Ting Song , Shaoguang Mao , Shuming Ma , Hongyu Wang , Yan Xia , Furu Wei

Large Language Models (LLMs) possess a theoretical capability to model information density far beyond the limits of classical statistical methods (e.g., Lempel-Ziv). However, utilizing this capability for lossless compression involves…

Information Theory · Computer Science 2026-03-27 Marcus Armstrong , ZiWei Qiu , Huy Q. Vo , Arjun Mukherjee

Transformers, the standard implementation for large language models (LLMs), typically consist of tens to hundreds of discrete layers. While more layers can lead to better performance, this approach has been challenged as far from efficient,…

Machine Learning · Computer Science 2025-05-21 Yen-Chen Wu , Feng-Ting Liao , Meng-Hsi Chen , Pei-Chen Ho , Farhang Nabiei , Da-shan Shiu

Long-context LLM agents often struggle with growing token, memory, and latency costs, making efficient context compression essential for practical deployment. Existing LLM-as-a-compressor methods remain noticeably inferior to using the full…

Computation and Language · Computer Science 2026-05-22 Jiangnan Ye , Hanqi Yan , Zhenyi Shen , Heng Chang , Ye Mao , Yulan He

Large Language Models (LLMs) based on autoregressive, decoder-only Transformers generate text one token at a time, where a token represents a discrete unit of text. As each newly produced token is appended to the partial output sequence,…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-05-06 Dimitrios Kafetzis , Ramin Khalili , Iordanis Koutsopoulos

Large Language Model (LLM) inference is hard. The autoregressive Decode phase of the underlying Transformer model makes LLM inference fundamentally different from training. Exacerbated by recent AI trends, the primary challenges are memory…

Hardware Architecture · Computer Science 2026-02-10 Xiaoyu Ma , David Patterson

Large Language Models (LLMs) fine-tuning technologies have achieved remarkable results. However, traditional LLM fine-tuning approaches face significant challenges: they require large Floating Point (FP) computation, raising privacy…

Machine Learning · Computer Science 2025-05-30 Sifan Zhou , Shuo Wang , Zhihang Yuan , Mingjia Shi , Yuzhang Shang , Dawei Yang

Channel state information (CSI) reporting is important for multiple-input multiple-output (MIMO) transmitters to achieve high capacity and energy efficiency in frequency division duplex (FDD) mode. CSI reporting for massive MIMO systems…

Information Theory · Computer Science 2019-12-24 Zhenyu Liu , Lin Zhang , Zhi Ding

Large language models (LLMs), based on transformer architectures, have revolutionized numerous domains within artificial intelligence, science, and engineering due to their exceptional scalability and adaptability. However, the exponential…

Hardware Architecture · Computer Science 2025-07-04 Wenzhe Guo , Joyjit Kundu , Uras Tos , Weijiang Kong , Giuliano Sisto , Timon Evenblij , Manu Perumkunnil

Transformer-based Large Language Models (LLMs) have significantly advanced AI capabilities but pose considerable challenges for deployment on edge devices due to high computational demands, memory bandwidth constraints, and energy…

Hardware Architecture · Computer Science 2025-04-25 Maoyang Xiang , Ramesh Fernando , Bo Wang

As large language models (LLMs) are trained on increasingly diverse and extensive multilingual corpora, they demonstrate cross-lingual transfer capabilities. However, these capabilities often fail to effectively extend to low-resource…

Computation and Language · Computer Science 2025-09-23 Wenhao Zhuang , Yuan Sun , Xiaobing Zhao

Large language models (LLMs) have demonstrated state-of-the-art performance across various tasks. However, the latency of inference and the large GPU memory consumption of LLMs restrict their deployment performance. Recently, there have…

Machine Learning · Computer Science 2024-02-29 Yi Zhang , Fei Yang , Shuang Peng , Fangyu Wang , Aimin Pan

Despite the increasing prevalence of large language models (LLMs), we still have a limited understanding of how their representational spaces are structured. This limits our ability to interpret how and what they learn or relate them to…

In a large class of deep learning models, including vector embedding models such as word and database embeddings, we observe that floating point exponent values cluster around a few unique values, permitting entropy based data compression.…

Machine Learning · Computer Science 2022-02-04 Rajesh Bordawekar , Bulent Abali , Ming-Hung Chen

LLM inference is increasingly limited by memory bandwidth, and the bottleneck worsens at long context as the KV cache grows. CXL memory adds capacity to offload weights and KV, but its link and device-side DDR bandwidth are far below HBM,…

Hardware Architecture · Computer Science 2026-02-02 Rui Xie , Asad Ul Haq , Yunhua Fang , Linsen Ma , Zirak Burzin Engineer , Liu Liu , Tong Zhang

Secure inference enables privacy-preserving machine learning by leveraging cryptographic protocols that support computations on sensitive user data without exposing it. However, integrating cryptographic protocols with large language models…

Cryptography and Security · Computer Science 2025-09-12 Zhiyu He , Maojiang Wang , Xinwen Gao , Yuchuan Luo , Lin Liu , Shaojing Fu

Small Language Models (SLMs, or on-device LMs) have significantly fewer parameters than Large Language Models (LLMs). They are typically deployed on low-end devices, like mobile phones and single-board computers. Unlike LLMs, which rely on…

Computation and Language · Computer Science 2025-06-17 Mingxue Xu , Yao Lei Xu , Danilo P. Mandic

We provide new estimates of an asymptotic upper bound on the entropy of English using the large language model LLaMA-7B as a predictor for the next token given a window of past tokens. This estimate is significantly smaller than currently…

Current methods for compressing neural network weights, such as decomposition, pruning, quantization, and channel simulation, often overlook the inherent symmetries within these networks and thus waste bits on encoding redundant…

Information Theory · Computer Science 2024-10-03 Jiajun He , Gergely Flamich , José Miguel Hernández-Lobato

Current LLM structured pruning methods typically involve two steps: (1) compression with calibration data and (2) costly continued pretraining on billions of tokens to recover lost performance. This second step is necessary as the first…

Machine Learning · Computer Science 2024-12-31 Yaya Sy , Christophe Cerisara , Irina Illina