English
Related papers

Related papers: Nacrith: Neural Lossless Compression via Ensemble …

200 papers

State-of-the-art trainable machine translation evaluation metrics like xCOMET achieve high correlation with human judgment but rely on large encoders (up to 10.7B parameters), making them computationally expensive and inaccessible to…

Computation and Language · Computer Science 2024-11-11 Daniil Larionov , Mikhail Seleznyov , Vasiliy Viskov , Alexander Panchenko , Steffen Eger

Large Language Models (LLMs) face significant computational challenges when processing long contexts due to the quadratic complexity of self-attention. While soft context compression methods, which map input text to smaller latent…

Computation and Language · Computer Science 2025-09-24 Gabriele Berton , Jayakrishnan Unnikrishnan , Son Tran , Mubarak Shah

Large language models deliver strong generative performance but at the cost of massive parameter counts, memory use, and decoding latency. Prior work has shown that pruning and structured sparsity can preserve accuracy under substantial…

Computation and Language · Computer Science 2026-04-17 Andrew Kiruluta

Recent advances in large language model (LLM) pretraining have led to high-quality LLMs with impressive abilities. By compressing such LLMs via quantization to 3-4 bits per parameter, they can fit into memory-limited devices such as laptops…

Repository-level code intelligence tasks require large language models (LLMs) to process long, multi-file contexts. Such inputs introduce three challenges: crucial context can be obscured by noise, truncated due to limited windows, and…

Software Engineering · Computer Science 2026-04-16 Jia Feng , Zhanyue Qin , Cuiyun Gao , Ruiqi Wang , Chaozheng Wang , Yingwei Ma , Xiaoyuan Xie

Motivated by the high costs of using black-box Large Language Models (LLMs), we introduce a novel prompt compression paradigm, under which we use smaller LLMs to compress inputs for the larger ones. We present the first comprehensive…

Computation and Language · Computer Science 2026-01-12 Ivan Zakazov , Berke Argin , Oussama Gabouj , Kamel Charaf , Alexander Sharipov , Alexi Semiz , Lorenzo Drudi , Nicolas Baldwin , Robert West

Large language models (LLMs) have triggered a new stream of research focusing on compressing the context length to reduce the computational cost while ensuring the retention of helpful information for LLMs to answer the given question.…

Computation and Language · Computer Science 2024-12-20 Barys Liskavets , Maxim Ushakov , Shuvendu Roy , Mark Klibanov , Ali Etemad , Shane Luke

During the training of Large Language Models (LLMs), tensor data is periodically "checkpointed" to persistent storage to allow recovery of work done in the event of failure. The volume of data that must be copied during each checkpoint,…

Machine Learning · Computer Science 2025-05-16 Daniel Waddington , Cornel Constantinescu

As Large Language Models (LLMs) continue to grow in size, storing and transmitting them on edge devices becomes increasingly challenging. Traditional methods like quantization and pruning struggle to achieve extreme compression of LLMs…

Machine Learning · Computer Science 2025-11-25 Ye Tian , Chengcheng Wang , Jing Han , Yehui Tang , Kai Han

As cutting-edge large language models (LLMs) continue to transform various industries, their fast-growing model size and sequence length have led to memory traffic and capacity challenges. Recently, AMD, Arm, Intel, Meta, Microsoft, NVIDIA,…

Hardware Architecture · Computer Science 2024-12-31 Yun-Chen Lo , Gu-Yeon Wei , David Brooks

The efficiency of Large Language Model~(LLM) inference is often constrained by substantial memory bandwidth and capacity demands. Existing techniques, such as pruning, quantization, and mixture of experts/depth, reduce memory capacity…

Hardware Architecture · Computer Science 2025-04-23 Rui Xie , Asad Ul Haq , Linsen Ma , Yunhua Fang , Zirak Burzin Engineer , Liu Liu , Tong Zhang

Soft context compression reduces the computational workload of processing long contexts in LLMs by encoding long context into a smaller number of latent tokens. However, existing frameworks apply uniform compression ratios, failing to…

Computation and Language · Computer Science 2026-03-30 Yijiong Yu , Shuai Yuan , Jie Zheng , Huazheng Wang , Ji Pei

Large Language Models (LLMs) deliver powerful reasoning and generation capabilities but incur substantial run-time costs when operating in agentic workflows that chain together lengthy prompts and process rich data streams. We introduce…

Artificial Intelligence · Computer Science 2025-10-22 Joong Ho Choi , Jiayang Zhao , Jeel Shah , Ritvika Sonawane , Vedant Singh , Avani Appalla , Will Flanagan , Filipe Condessa

Communication has emerged as a critical bottleneck in the distributed training of large language models (LLMs). While numerous approaches have been proposed to reduce communication overhead, the potential of lossless compression has…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-01 Wenxiang Lin , Xinglin Pan , Ruibo Fan , Shaohuai Shi , Xiaowen Chu

We present OmniVLM, a sub-billion-parameter vision-language model for efficient on-device inference. OmniVLM introduces a token compression mechanism that reduces visual token sequence length from 729 to 81 tokens, significantly reducing…

Computer Vision and Pattern Recognition · Computer Science 2024-12-30 Wei Chen , Zhiyuan Li , Shuo Xin

As large language models (LLMs) continue to be deployed and utilized across domains, the volume of LLM-generated data is growing rapidly. This trend highlights the increasing importance of effective and lossless compression for such data in…

Machine Learning · Computer Science 2025-05-13 Yu Mao , Holger Pirk , Chun Jason Xue

We conceptualize the process of understanding as information compression, and propose a method for ranking large language models (LLMs) based on lossless data compression. We demonstrate the equivalence of compression length under…

Artificial Intelligence · Computer Science 2024-06-21 Peijia Guo , Ziguang Li , Haibo Hu , Chao Huang , Ming Li , Rui Zhang

Hollow-core fibers offer superior loss and latency characteristics compared to solid-core alternatives, yet the geometric complexity of nested antiresonance nodeless fibers (NANFs) makes traditional optimization computationally prohibitive.…

Machine Learning · Computer Science 2026-03-17 Rania A. Eltaieb , Sophie LaRochelle , Leslie A. Rusch

The rapid scaling of Large Language Models (LLMs) elevates inference costs and compounds substantial deployment barriers. While quantization to 8 or 4 bits mitigates this, sub-3-bit methods face severe accuracy, scalability, and efficiency…

Deep learning models have become state of the art for natural language processing (NLP) tasks, however deploying these models in production system poses significant memory constraints. Existing compression methods are either lossy or…

Machine Learning · Computer Science 2018-11-05 Anish Acharya , Rahul Goel , Angeliki Metallinou , Inderjit Dhillon