English
Related papers

Related papers: AgentIR: A Workload-Adaptive Cascade Retrieval Sub…

200 papers

Streaming ASR with strict latency constraints is required in many speech recognition applications. In order to achieve the required latency, streaming ASR models sacrifice accuracy compared to non-streaming ASR models due to lack of future…

Computation and Language · Computer Science 2022-03-30 Jay Mahadeokar , Yangyang Shi , Ke Li , Duc Le , Jiedan Zhu , Vikas Chandra , Ozlem Kalinli , Michael L Seltzer

Retrieval-Augmented Generation (RAG) helps LLMs stay accurate, but feeding long documents into a prompt makes the model slow and expensive. This has motivated context compression, ranging from token pruning and summarization to…

Computation and Language · Computer Science 2026-01-09 Jianbo Li , Yi Jiang , Sendong Zhao , Bairui Hu , Haochun Wang , Bing Qin

The proliferation of large language models (LLMs) is accelerating the integration of multimodal assistants into edge devices, where inference is executed under stringent latency and energy constraints, often exacerbated by intermittent…

Hardware Architecture · Computer Science 2026-01-29 Yanru Chen , Runyang Tian , Yue Pan , Zheyu Li , Weihong Xu , Tajana Rosing

Current LLM agents lack principled mechanisms for managing persistent memory across long interaction horizons. We present a biologically-grounded memory architecture comprising six cognitive mechanisms: (1) sleep-phase consolidation, (2)…

Artificial Intelligence · Computer Science 2026-05-12 Doga Kerestecioglu , Alexei Robsky , Clemens Vasters , Anshul Sharma , Yitzhak Kesselman

In this technical report, we present the Ring-linear model series, specifically including Ring-mini-linear-2.0 and Ring-flash-linear-2.0. Ring-mini-linear-2.0 comprises 16B parameters and 957M activations, while Ring-flash-linear-2.0…

The wide adoption of deep neural networks has been accompanied by ever-increasing energy and performance demands due to the expensive nature of training them. Numerous special-purpose architectures have been proposed to accelerate training:…

Distributed, Parallel, and Cluster Computing · Computer Science 2019-12-30 Aayush Ankit , Izzat El Hajj , Sai Rahul Chalamalasetti , Sapan Agarwal , Matthew Marinella , Martin Foltin , John Paul Strachan , Dejan Milojicic , Wen-mei Hwu , Kaushik Roy

An agent that operates sequentially must incorporate new experience without forgetting old experience, under a fixed memory budget. We propose a framework in which memory is not a parameter vector but a stochastic process: a Bridge…

Machine Learning · Computer Science 2026-04-02 Michael Chertkov

Large Language Model (LLM) workloads have distinct prefill and decode phases with different compute and memory requirements which should ideally be accounted for when scheduling input queries across different LLM instances in a cluster.…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-01-08 Kunal Jain , Anjaly Parayil , Ankur Mallick , Esha Choukse , Xiaoting Qin , Jue Zhang , Íñigo Goiri , Rujia Wang , Chetan Bansal , Victor Rühle , Anoop Kulkarni , Steve Kofsky , Saravan Rajmohan

Long-term memory is critical for dialogue systems that support continuous, sustainable, and personalized interactions. However, existing methods rely on continuous summarization or OpenIE-based graph construction paired with fixed…

Computation and Language · Computer Science 2026-04-09 Yijie Zhong , Yunfan Gao , Haofen Wang

Recent work on domain-specific reasoning with large language models (LLMs) often relies on training-intensive approaches that require parameter updates. While activation steering has emerged as a parameter efficient alternative, existing…

Artificial Intelligence · Computer Science 2026-01-21 Wencheng Ye , Xiaoyang Yuan , Yi Bin , Pengpeng Zeng , Hengyu Jin , Liang Peng , Heng Tao Shen

Large language models(LLMs) are now used to power complex multi-turn agentic workflows. Existing systems run agentic inference by loosely assembling isolated components: an LLM inference engine (e.g., vLLM) and a tool orchestrator (e.g.,…

Operating Systems · Computer Science 2026-03-12 Hao Kang , Ziyang Li , Xinyu Yang , Weili Xu , Yinfang Chen , Junxiong Wang , Beidi Chen , Tushar Krishna , Chenfeng Xu , Simran Arora

Large reasoning models (LRMs) achieve strong accuracy through test-time scaling, generating longer chains of thought or sampling multiple solutions, but at steep costs in tokens and latency. We argue that memory is a core ingredient for…

Multiagent Systems · Computer Science 2026-03-04 Daivik Patel , Shrenik Patel

Streaming speech recognition architectures are employed for low-latency, real-time applications. Such architectures are often characterized by their causality. Causal architectures emit tokens at each frame, relying only on current and past…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-11 Grant P. Strimel , Yi Xie , Brian King , Martin Radfar , Ariya Rastrow , Athanasios Mouchtaris

Pretrained transformer models have demonstrated remarkable performance across various natural language processing tasks. These models leverage the attention mechanism to capture long- and short-range dependencies in the sequence. However,…

Computation and Language · Computer Science 2023-10-20 Qingru Zhang , Dhananjay Ram , Cole Hawkins , Sheng Zha , Tuo Zhao

Recurrent neural networks (RNNs) are becoming the de facto solution for speech recognition. RNNs exploit long-term temporal relationships in data by applying repeated, learned transformations. Unlike fully-connected (FC) layers with single…

Signal Processing · Electrical Eng. & Systems 2019-08-27 Udit Gupta , Brandon Reagen , Lillian Pentecost , Marco Donato , Thierry Tambe , Alexander M. Rush , Gu-Yeon Wei , David Brooks

Large Reasoning Models (LRMs) like o3 and DeepSeek-R1 have achieved remarkable progress in reasoning tasks with long cot. However, they remain computationally inefficient and struggle with accuracy when solving problems requiring complex…

Artificial Intelligence · Computer Science 2026-03-03 Haipeng Luo , Huawen Feng , Qingfeng Sun , Can Xu , Kai Zheng , Yufei Wang , Tao Yang , Han Hu , Yansong Tang

Cascaded LLM systems coordinate models of varying sizes with human experts to balance accuracy, cost, and abstention under uncertainty. However, single-model tiers at each stage often struggle with ambiguous queries, triggering premature…

Computation and Language · Computer Science 2026-04-15 Raeyoung Chang , Dongwook Kwon , Jisoo Lee , Nikhil Verma

Large language model (LLM) agents are fundamentally bottlenecked by finite context windows on long-horizon tasks. As trajectories grow, retaining tool outputs and intermediate reasoning in-context quickly becomes infeasible: the working…

Computation and Language · Computer Science 2026-03-05 Zhenting Wang , Huancheng Chen , Jiayun Wang , Wei Wei

This technical report details a novel approach to combining reasoning and retrieval augmented generation (RAG) within a single, lean language model architecture. While existing RAG systems typically rely on large-scale models and external…

Conventional transformer inference engines are request-driven, paying an O(n) prefill cost on every query. In streaming workloads, where data arrives continuously and queries probe an ever-growing context, this cost is prohibitive. We…

Machine Learning · Computer Science 2026-05-14 Victor Norgren