English
Related papers

Related papers: ASAP-NMS: Accelerating Non-Maximum Suppression Usi…

200 papers

Modern Neural Network (NN) architectures heavily rely on vast numbers of multiply-accumulate arithmetic operations, constituting the predominant computational cost. Therefore, this paper proposes a high-throughput, scalable and energy…

Hardware Architecture · Computer Science 2024-07-09 Xuqi Zhu , Huaizhi Zhang , JunKyu Lee , Jiacheng Zhu , Chandrajit Pal , Sangeet Saha , Klaus D. McDonald-Maier , Xiaojun Zhai

We design and develop a work-efficient multithreaded algorithm for sparse matrix-sparse vector multiplication (SpMSpV) where the matrix, the input vector, and the output vector are all sparse. SpMSpV is an important primitive in the…

Distributed, Parallel, and Cluster Computing · Computer Science 2016-10-26 Ariful Azad , Aydin Buluc

Markov Chain Monte Carlo (MCMC) methods, such as the Metropolis-Hastings (MH) algorithm, are widely used for Bayesian inference. One of the most important issues for any MCMC method is the convergence of the Markov chain, which depends…

Computation · Statistics 2015-11-20 Luca Martino , Jesse Read , David Luengo

Pairwise comparison data arise in many domains with subjective assessment experiments, for example in image and video quality assessment. In these experiments observers are asked to express a preference between two conditions. However, many…

Machine Learning · Computer Science 2020-04-14 Aliaksei Mikhailiuk , Clifford Wilmot , Maria Perez-Ortiz , Dingcheng Yue , Rafal Mantiuk

Statistical n-gram language models are widely used for context-biasing tasks in Automatic Speech Recognition (ASR). However, existing implementations lack computational efficiency due to poor parallelization, making context-biasing less…

Audio and Speech Processing · Electrical Eng. & Systems 2025-05-30 Vladimir Bataev , Andrei Andrusenko , Lilit Grigoryan , Aleksandr Laptev , Vitaly Lavrukhin , Boris Ginsburg

Anderson Acceleration (AA) has been widely used to solve nonlinear fixed-point problems due to its rapid convergence. This work focuses on a variant of AA in which multiple Picard iterations are performed between each AA step, referred to…

Numerical Analysis · Mathematics 2025-07-15 Xue Feng , M. Paul Laiu , Thomas Strohmer

Processing in-memory (PIM) is promising to accelerate neural networks (NNs) because it minimizes data movement and provides large computational parallelism. Similar to machine learning accelerators, application mapping, which determines the…

Hardware Architecture · Computer Science 2024-07-02 Xuan Wang , Minxuan Zhou , Tajana Rosing

General-purpose Sparse Matrix-Matrix Multiplication (SpMM) is a fundamental kernel in scientific computing and deep learning. The emergence of new matrix computation units such as Tensor Cores (TCs) brings more opportunities for SpMM…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-01-17 Haisha Zhao , San Li , Jiaheng Wang , Chunbao Zhou , Jue Wang , Zhikuang Xin , Shunde Li , Zhiqiang Liang , Zhijie Pan , Fang Liu , Yan Zeng , Yangang Wang , Xuebin Chi

Transducer models have emerged as a promising choice for end-to-end ASR systems, offering a balanced trade-off between recognition accuracy, streaming capabilities, and inference speed in greedy decoding. However, beam search significantly…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-03 Lilit Grigoryan , Vladimir Bataev , Andrei Andrusenko , Hainan Xu , Vitaly Lavrukhin , Boris Ginsburg

A recurring pattern in "reasoning without training" is that base LLMs already assign non-trivial probability mass to correct multi-step solutions; the bottleneck is locating these modes efficiently at inference time. Power sampling provides…

Artificial Intelligence · Computer Science 2026-05-13 Tu Nguyen , Matthieu Zimmer , Rasul Tutunov , Xiaotong Ji , Haitham Bou Ammar

Simulated Annealing using Metropolis steps at decreasing temperatures is widely used to solve complex combinatorial optimization problems. In order to improve its efficiency, we can use the Rejection-Free version of the Metropolis…

Optimization and Control · Mathematics 2022-10-10 Sigeng Chen , Jeffrey S. Rosenthal , Aki Dote , Hirotaka Tamura , Ali Sheikholeslami

The non-local module works as a particularly useful technique for semantic segmentation while criticized for its prohibitive computation and GPU memory occupation. In this paper, we present Asymmetric Non-local Neural Network to semantic…

Computer Vision and Pattern Recognition · Computer Science 2019-08-30 Zhen Zhu , Mengde Xu , Song Bai , Tengteng Huang , Xiang Bai

Generative Recommendation (GR) has recently transitioned from atomic item-indexing to Semantic ID (SID)-based frameworks to capture intrinsic item relationships and enhance generalization. However, the adoption of high-granularity SIDs…

Information Retrieval · Computer Science 2026-04-08 Tianyu Zhan , Kairui Fu , Chengfei Lv , Zheqi Lv , Shengyu Zhang

We consider the problem of recovering clustered sparse signals with no prior knowledge of the sparsity pattern. Beyond simple sparsity, signals of interest often exhibits an underlying sparsity pattern which, if leveraged, can improve the…

Information Theory · Computer Science 2016-01-05 Xiangming Meng , Sheng Wu , Linling Kuang , Defeng , Huang , Jianhua Lu

This article addresses the problem of multiple preamble detection in random access systems based on orthogonal time frequency space (OTFS) signaling. This challenge is formulated as a structured sparse recovery problem in the complex…

Signal Processing · Electrical Eng. & Systems 2025-09-05 Alessandro Mirri , Vishnu Teja Kunde , Enrico Paolini , Jean-Francois Chamberland

Despite the numerous uses of semidefinite programming (SDP) and its universal solvability via interior point methods (IPMs), it is rarely applied to practical large-scale problems. This mainly owes to the computational cost of IPMs that…

Optimization and Control · Mathematics 2024-03-19 Yifan Ran , Stefan Vlaski , Wei Dai

Deep neural networks have gained great success due to the increasing amounts of data, and diverse effective neural network designs. However, it also brings a heavy computing burden as the amount of training data is proportional to the…

Machine Learning · Computer Science 2023-10-19 Peng Yao , Chao Liao , Jiyuan Jia , Jianchao Tan , Bin Chen , Chengru Song , Di Zhang

Large language models have high compute, latency, and memory requirements. While specialized accelerators such as GPUs and TPUs typically run these workloads, CPUs are more widely available and consume less energy. Accelerating LLMs with…

This work develops a fast, memory-efficient, and general algorithm for accelerated/undersampled dynamic MRI by assuming an approximate LR model on the matrix formed by the vectorized images of the sequence. By general, we mean that our…

Image and Video Processing · Electrical Eng. & Systems 2025-02-28 Silpa Babu , Sajan Goud Lingala , Namrata Vaswani

Filtered-X LMS (FxLMS) is commonly used for active noise control (ANC), wherein the soundfield is minimized at a desired location. Given prior knowledge of the spatial region of the noise or control sources, we could improve FxLMS by…

Machine Learning · Computer Science 2026-02-25 Kanad Sarkar , Austin Lu , Manan Mittal , Yongjie Zhuang , Ryan Corey , Andrew Singer