English
Related papers

Related papers: Hierarchical Token Prepending: Enhancing Informati…

200 papers

We study offline scheduling for large language model (LLM) serving under a fixed KV-cache memory budget, where requests have heterogeneous prompt (prefill) and response (decode) lengths. Prompt tokens determine initial KV usage, and each…

Optimization and Control · Mathematics 2026-02-11 Meixuan Wang , Yinyu Ye , Zijie Zhou

Long-context Large Language Model (LLM) inference faces increasing compute bottlenecks as attention calculations scale with context length, primarily due to the growing KV-cache transfer overhead that saturates High Bandwidth Memory (HBM).…

Hardware Architecture · Computer Science 2025-08-13 Ming-Yen Lee , Faaiq Waqar , Hanchen Yang , Muhammed Ahosan Ul Karim , Harsono Simka , Shimeng Yu

Deep pre-trained language models (e,g. BERT) are effective at large-scale text retrieval task. Existing text retrieval systems with state-of-the-art performance usually adopt a retrieve-then-reranking architecture due to the high…

Information Retrieval · Computer Science 2022-05-24 Yanzhao Zhang , Dingkun Long , Guangwei Xu , Pengjun Xie

Token reduction is an effective way to accelerate long-video vision-language models (VLMs), but most existing methods are designed for dense Transformers and do not directly account for hybrid architectures that interleave attention with…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Jindong Jiang , Amala Sanjay Deshmukh , Kateryna Chumachenko , Karan Sapra , Zhiding Yu , Guilin Liu , Andrew Tao , Pavlo Molchanov , Jan Kautz , Wonmin Byeon

Reasoning in Large Language Models incurs significant inference-time compute, yet the token-level information structure of reasoning traces remains underexplored. We observe that reasoning tokens split into two functional types: low-entropy…

Computation and Language · Computer Science 2026-05-06 Zhenyu Zhao , Sander Land , Daniel M. Bikel , Waseem Alshikh

Following the remarkable success of Large Language Models (LLMs) in NLP tasks, there is increasing interest in extending their capabilities to speech -- the most common form of communication. The most widespread approach to integrating…

Computation and Language · Computer Science 2025-02-11 Tsz Kin Lam , Marco Gaido , Sara Papi , Luisa Bentivogli , Barry Haddow

Pipeline parallelism has emerged as a predominant approach for deploying large language models (LLMs) across distributed nodes, owing to its lower communication overhead compared to tensor parallelism. While demonstrating high throughput in…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-05-29 Tianyu Guo , Xianwei Zhang , Jiangsu Du , Zhiguang Chen , Nong Xiao , Yutong Lu

Decoding-free reranking methods that read relevance signals directly from LLM attention weights offer significant latency advantages over autoregressive approaches, yet suffer from attention score homogenization: middle-context documents…

Information Retrieval · Computer Science 2026-05-20 Juyuan Wang , Chenxing Wang , Yuchen Fang , Huiyun Hu , Junwu Du , Aolin Li , Shunlin Rong , Haijun Wu , Jin Xu , Ligang Liu , Dongliang Liao

Graph Transformers, leveraging the global attention to capture long-range dependencies in graph structures, have significantly advanced graph machine learning, but face prohibitive computational complexity. Tokenized Graph Learning Models…

Machine Learning · Computer Science 2025-05-23 Zhibiao Wang , Yunlong Zhou , Ziwei Zhang , Mengmei Zhang , Shirui Pan , Chunming Hu , Xiao Wang

We systematically investigate multi-token prediction (MTP) capabilities within LLMs pre-trained for next-token prediction (NTP). We first show that such models inherently possess MTP capabilities via numerical marginalization over…

Computation and Language · Computer Science 2025-02-14 Somesh Mehra , Javier Alonso Garcia , Lukas Mauch

Hierarchical Text Classification (HTC) is a natural language processing task with the objective to classify text documents into a set of classes from a structured class hierarchy. Many HTC approaches have been proposed which attempt to…

Information Retrieval · Computer Science 2024-12-02 Jaco du Toit , Herman Redelinghuys , Marcel Dunaiski

Pre-training of Large Language Models is often prohibitively expensive and inefficient at scale, requiring complex and invasive modifications in order to achieve high data throughput. In this work, we present Token-Superposition Training…

Computation and Language · Computer Science 2026-05-20 Bowen Peng , Théo Gigant , Jeffrey Quesnelle

The exponential expansion of context windows in LLMs has unlocked capabilities for long-document understanding but introduced severe bottlenecks in inference latency and information utilization. Existing compression methods often suffer…

Computation and Language · Computer Science 2026-03-23 Zhengpei Hu , Kai Li , Dapeng Fu , Chang Zeng , Yue Li , Yuanhao Tang , Jianqiang Huang

Optimizing training performance in large language models (LLMs) remains an essential challenge, particularly in improving model performance while maintaining computational costs. This work challenges the conventional approach of training…

Computation and Language · Computer Science 2025-11-04 Chun-Hao Yang , Bo-Han Feng , Tzu-Yuan Lai , Yan Yu Chen , Yin-Kai Dean Huang , Shou-De Lin

Recent advancements in large language models (LLMs) have enabled their successful application to a broad range of tasks. However, in information-intensive tasks, the prompt length can grow fast, leading to increased computational…

Computation and Language · Computer Science 2025-10-13 Weronika Łajewska , Momchil Hardalov , Laura Aina , Neha Anna John , Hang Su , Lluís Màrquez

Transformer-based large language models (LLMs) are now deployed to hundreds of millions of users. LLM inference is commonly performed on batches of sequences that share a prefix, such as few-shot examples or a chatbot system prompt.…

Machine Learning · Computer Science 2024-05-14 Jordan Juravsky , Bradley Brown , Ryan Ehrlich , Daniel Y. Fu , Christopher Ré , Azalia Mirhoseini

High load latency that results from deep cache hierarchies and relatively slow main memory is an important limiter of single-thread performance. Data prefetch helps reduce this latency by fetching data up the hierarchy before it is…

Hardware Architecture · Computer Science 2021-03-30 Majid Jalili , Mattan Erez

Hierarchical neural architectures are often used to capture long-distance dependencies and have been applied to many document-level tasks such as summarization, document segmentation, and sentiment analysis. However, effective usage of such…

Computation and Language · Computer Science 2019-01-29 Ming-Wei Chang , Kristina Toutanova , Kenton Lee , Jacob Devlin

Hierarchical text classification (HTC) is essential for various real applications. However, HTC models are challenging to develop because they often require processing a large volume of documents and labels with hierarchical taxonomy.…

Computation and Language · Computer Science 2023-11-08 SangHun Im , Gibaeg Kim , Heung-Seon Oh , Seongung Jo , Donghwan Kim

The adaptation of large language models (LLMs) to specialized reasoning tasks is fundamentally constrained by computational resources. Parameter-Efficient Fine-Tuning (PEFT) methods have emerged as a powerful solution, yet the landscape of…

Computation and Language · Computer Science 2025-09-15 Brennen Hill
‹ Prev 1 8 9 10 Next ›