English
Related papers

Related papers: Inference-Time Distillation: Cost-Efficient Agents…

200 papers

LLM-based web agents have recently made significant progress, but much of it has occurred in closed-source systems, widening the gap with open-source alternatives. Progress has been held back by two key challenges: first, a narrow focus on…

With the wide adoption of language models for IR -- and specifically RAG systems -- the latency of the underlying LLM becomes a crucial bottleneck, since the long contexts of retrieved passages lead large prompts and therefore, compute…

Information Retrieval · Computer Science 2026-04-06 Cornelius Kummer , Lena Jurkschat , Michael Färber , Sahar Vahdati

Large Language Models (LLMs) herald a transformative era in artificial intelligence (AI). However, the expansive scale of data and parameters of LLMs requires high-demand computational and memory resources, restricting their accessibility…

Machine Learning · Computer Science 2024-11-26 Shengwen Ding , Chenhui Hu

Efficient LLM inference scheduling is crucial for user experience. However, LLM inferences exhibit remarkable demand uncertainty (with unknown output length beforehand) and hybridity (being both compute and memory intensive). Existing LLM…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-03-16 Zhenghao Gan , Yichen Bao , Yifei Liu , Chen Chen , Quan Chen , Minyi Guo

We present a practical distillation approach to fine-tune LLMs for invoking tools in real-time applications. We focus on visual editing tasks; specifically, we modify images and videos by interpreting user stylistic requests, specified in…

Computation and Language · Computer Science 2024-10-11 Oren Sultan , Alex Khasin , Guy Shiran , Asnat Greenstein-Messica , Dafna Shahaf

Sparsity has long been a central theme in LLM efficiency, but its role in context processing remains unresolved. As LLM workloads shift toward longer contexts and agentic interactions, the compute and memory bottlenecks of attention become…

Recent advancements in Large Language Model (LLM) agents have enabled complex multi-turn agentic tasks requiring extensive tool calling, where conversations can span dozens of API calls with increasingly large context windows. However,…

Computation and Language · Computer Science 2026-02-03 Elias Lumer , Faheem Nizar , Akshaya Jangiti , Kevin Frank , Anmol Gulati , Mandar Phadate , Vamse Kumar Subbiah

Efficiently deploying large language models (LLMs) in real-world scenarios remains a critical challenge, primarily due to hardware heterogeneity, inference framework limitations, and workload complexities.Efficiently deploying large…

Artificial Intelligence · Computer Science 2025-01-28 Yanyu Chen , Ganhong Huang

As large language models (LLMs) show impressive performance on complex tasks, they still struggle with longer contextual understanding and high computational costs. To balance efficiency and quality, we introduce LLMSteer, a…

Machine Learning · Computer Science 2024-11-22 Zhuohan Gu , Jiayi Yao , Kuntai Du , Junchen Jiang

Recently, large language models (LLMs) have achieved huge success in the natural language processing (NLP) field, driving a growing demand to extend their deployment from the cloud to edge devices. However, deploying LLMs on…

Hardware Architecture · Computer Science 2025-05-08 Yanbiao Liang , Huihong Shi , Haikuo Shao , Zhongfeng Wang

Large language model (LLM) agents show promise on realistic tool-use tasks, but deploying capable agents on modest hardware remains challenging. We study whether inference-time scaffolding alone, without any additional training compute, can…

Artificial Intelligence · Computer Science 2026-04-16 S. Aaron McClendon , Jorge Gallego-Feliciano , Stavros Zervoudakis , Antonios Saravanos

Test-time compute scaling, the practice of spending extra computation during inference via repeated sampling, search, or extended reasoning, has become a powerful lever for improving large language model performance. Yet deploying these…

Machine Learning · Computer Science 2026-04-17 Zhiyuan Zhai , Bingcong Li , Bingnan Xiao , Ming Li , Xin Wang

Large language models~(LLMs) are known for their high demand on computing resources and memory due to their substantial model size, which leads to inefficient inference on moderate GPU systems. Techniques like quantization or pruning can…

Computational Engineering, Finance, and Science · Computer Science 2024-11-26 Wenxiang Lin , Xinglin Pan , Shaohuai Shi , Xuan Wang , Xiaowen Chu

Test-time scaling (TTS) has become an effective approach for improving large language model performance by allocating additional computation during inference. However, existing TTS strategies are largely hand-crafted: researchers manually…

Computation and Language · Computer Science 2026-05-13 Tong Zheng , Haolin Liu , Chengsong Huang , Huiwen Bao , Sheng Zhang , Rui Liu , Runpeng Dai , Ruibo Chen , Chenxi Liu , Tianyi Xiong , Xidong Wu , Hongming Zhang , Heng Huang

There have been numerous attempts to distill quadratic attention-based large language models (LLMs) into sub-quadratic linearized architectures. However, despite extensive research, such distilled models often fail to match the performance…

In this paper, we propose Patience-based Early Exit, a straightforward yet effective inference method that can be used as a plug-and-play technique to simultaneously improve the efficiency and robustness of a pretrained language model…

Computation and Language · Computer Science 2020-10-23 Wangchunshu Zhou , Canwen Xu , Tao Ge , Julian McAuley , Ke Xu , Furu Wei

Large Language Models (LLMs) have a natural role in answering complex queries about data streams, but the high computational cost of LLM inference makes them infeasible in many such tasks. We propose online cascade learning, the first…

Machine Learning · Computer Science 2024-06-19 Lunyiu Nie , Zhimin Ding , Erdong Hu , Christopher Jermaine , Swarat Chaudhuri

LLM alignment ensures that large language models behave safely and effectively by aligning their outputs with human values, goals, and intentions. Aligning LLMs employ huge amounts of data, computation, and time. Moreover, curating data…

Machine Learning · Computer Science 2025-02-19 Amrit Khera , Rajat Ghosh , Debojyoti Dutta

Recent years have seen significant advancements in foundation models through generative pre-training, yet algorithmic innovation in this space has largely stagnated around autoregressive models for discrete signals and diffusion models for…

Machine Learning · Computer Science 2025-03-12 Jiaming Song , Linqi Zhou

This paper focuses on modern efficient training and inference technologies on foundation models and illustrates them from two perspectives: model and system design. Model and System Design optimize LLM training and inference from different…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-04-15 Dong Liu , Yanxuan Yu , Yite Wang , Jing Wu , Zhongwei Wan , Sina Alinejad , Benjamin Lengerich , Ying Nian Wu