English
Related papers

Related papers: Data-Oriented Language Implementation of Lattice-B…

200 papers

Transformer based Large Language Models (LLMs) have been widely used in many fields, and the efficiency of LLM inference becomes hot topic in real applications. However, LLMs are usually complicatedly designed in model structure with…

Hardware Architecture · Computer Science 2024-06-25 Hui Wu , Yi Gan , Feng Yuan , Jing Ma , Wei Zhu , Yutao Xu , Hong Zhu , Yuhua Zhu , Xiaoli Liu , Jinghui Gu , Peng Zhao

We study exact sparse linear regression with an $\ell_0-\ell_2$ penalty and develop a branch-and-bound (BnB) algorithm explicitly designed for GPU execution. Starting from a perspective reformulation, we derive an interval relaxation that…

Optimization and Control · Mathematics 2026-02-05 Xiang Meng , Ryan Lucas , Rahul Mazumder

Recently, large language models (LLMs) have shown surprising performance in task-specific workloads as well as general tasks with the given prompts. However, to achieve unprecedented performance, recent LLMs use billions to trillions of…

Machine Learning · Computer Science 2024-06-21 Geonhwa Jeong , Po-An Tsai , Stephen W. Keckler , Tushar Krishna

Geometry problem solving (GPS) is a challenging mathematical reasoning task requiring multi-modal understanding, fusion, and reasoning. Existing neural solvers take GPS as a vision-language task but are short in the representation of…

Computer Vision and Pattern Recognition · Computer Science 2024-02-21 Zhong-Zhi Li , Ming-Liang Zhang , Fei Yin , Cheng-Lin Liu

The original softmax-based attention mechanism (regular attention) in the extremely successful Transformer architecture computes attention between $N$ tokens, each embedded in a $D$-dimensional head, with a time complexity of $O(N^2D)$.…

Machine Learning · Computer Science 2025-10-28 Armin Gerami , Ramani Duraiswami

Data efficiency, despite being an attractive characteristic, is often challenging to measure and optimize for in task-oriented semantic parsing; unlike exact match, it can require both model- and domain-specific setups, which have,…

Computation and Language · Computer Science 2021-07-13 Shrey Desai , Akshat Shrivastava , Justin Rill , Brian Moran , Safiyyah Saleem , Alexander Zotov , Ahmed Aly

Sparse active illumination enables precise time-of-flight depth sensing as it maximizes signal-to-noise ratio for low power budgets. However, depth completion is required to produce dense depth maps for 3D perception. We address this task…

Computer Vision and Pattern Recognition · Computer Science 2022-05-26 Xiaowen Jiang , Valerio Cambareri , Gianluca Agresti , Cynthia Ifeyinwa Ugwu , Adriano Simonetto , Fabien Cardinaux , Pietro Zanuttigh

Graph analytics techniques based on spectral methods process extremely large sparse matrices with millions or even billions of non-zero values. Behind these algorithms lies the Top-K sparse eigenproblem, the computation of the largest…

Hardware Architecture · Computer Science 2022-01-20 Francesco Sgherzi , Alberto Parravicini , Marco Domenico Santambrogio

We present a new design pattern for high-performance parallel scientific software, named coalesced communication. This pattern allows for a structured way to improve the communication performance through coalescence of multiple…

Distributed, Parallel, and Cluster Computing · Computer Science 2012-10-17 Hywel B. Carver , Derek Groen , James Hetherington , Rupert W. Nash , Miguel O. Bernabeu , Peter V. Coveney

The rapid evolution of Large Language Models (LLMs) has significantly impacted the field of natural language processing, but their growing complexity raises concerns about resource usage and transparency. Addressing these challenges, we…

Machine Learning · Computer Science 2026-04-13 Gyuwon Park , DongIl Shin , SolGil Oh , SangGi Ryu , Byung-Hak Kim

We consider the neural sparse representation to solve Boltzmann equation with BGK and quadratic collision model, where a network-based ansatz that can approximate the distribution function with extremely high efficiency is proposed.…

Numerical Analysis · Mathematics 2023-02-21 Zhengyi Li , Yanli Wang , Hongsheng Liu , Zidong Wang , Bin Dong

Modern sparse language models typically achieve sparsity through Mixture-of-Experts (MoE) layers, which dynamically route tokens to dense MLP "experts." However, dynamic hard routing has a number of drawbacks, such as potentially poor…

Machine Learning · Computer Science 2026-02-02 Albert Tseng , Christopher De Sa

Multi-head-self-attention (MHSA) mechanisms achieve state-of-the-art (SOTA) performance across natural language processing and vision tasks. However, their quadratic dependence on sequence lengths has bottlenecked inference speeds. To…

Programming Languages · Computer Science 2024-07-25 Ahan Gupta , Yueming Yuan , Devansh Jain , Yuhao Ge , David Aponte , Yanqi Zhou , Charith Mendis

The torrential influx of floating-point data from domains like IoT and HPC necessitates high-performance lossless compression to mitigate storage costs while preserving absolute data fidelity. Leveraging GPU parallelism for this task…

Databases · Computer Science 2025-11-12 Zheng Li , Weiyan Wang , Ruiyuan Li , Chao Chen , Xianlei Long , Linjiang Zheng , Quanqing Xu , Chuanhui Yang

While dense retrieval models have become the standard for state-of-the-art information retrieval, their deployment is often constrained by high memory requirements and reliance on GPU accelerators for vector similarity search. Learned…

Information Retrieval · Computer Science 2026-01-06 Zhichao Xu , Shengyao Zhuang , Crystina Zhang , Xueguang Ma , Yijun Tian , Maitrey Mehta , Jimmy Lin , Vivek Srikumar

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

The exponentially growing model size drives the continued success of deep learning, but it brings prohibitive computation and memory cost. From the algorithm perspective, model sparsification and quantization have been studied to alleviate…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-05-09 Shigang Li , Kazuki Osawa , Torsten Hoefler

Post-training quantization (PTQ) plays a crucial role in the democratization of large language models (LLMs). However, existing low-bit quantization and sparsification techniques are difficult to balance accuracy and efficiency due to the…

Computation and Language · Computer Science 2025-12-08 Ruixuan Huang , Hao Zeng , Hantao Huang , Jinyuan Shi , Minghui Yu , Ian En-Hsu Yen , Shuai Wang

The rapid development of large language models (LLM) has greatly enhanced everyday applications. While many FPGA-based accelerators, with flexibility for fine-grained data control, exhibit superior speed and energy efficiency compared to…

Hardware Architecture · Computer Science 2026-03-24 Zifan He , Shengyu Ye , Rui Ma , Yang Wang , Jason Cong

The traditional method for computation in either the surface code or in the Raussendorf model is the creation of holes or "defects" within the encoded lattice of qubits that are manipulated via topological braiding to enact logic gates.…

Quantum Physics · Physics 2017-09-20 Daniel Herr , Franco Nori , Simon J. Devitt