English
Related papers

Related papers: A two-step sequential approach for hyperparameter …

200 papers

Large language models (LLMs) often struggle to accurately read and comprehend extremely long texts. Current methods for improvement typically rely on splitting long contexts into fixed-length chunks. However, fixed truncation risks…

Computation and Language · Computer Science 2025-06-04 Boheng Sheng , Jiacheng Yao , Meicong Zhang , Guoxiu He

Long document summarization poses a significant challenge in natural language processing due to input lengths that exceed the capacity of most state-of-the-art pre-trained language models. This study proposes a hierarchical framework that…

Computation and Language · Computer Science 2024-10-10 Yuan-Jhe Yin , Bo-Yu Chen , Berlin Chen

As deep learning techniques advance more than ever, hyper-parameter optimization is the new major workload in deep learning clusters. Although hyper-parameter optimization is crucial in training deep learning models for high model…

Machine Learning · Computer Science 2019-11-26 Ahnjae Shin , Dong-Jin Shin , Sungwoo Cho , Do Yoon Kim , Eunji Jeong , Gyeong-In Yu , Byung-Gon Chun

Speculative decoding accelerates large language model inference by using smaller draft models to generate candidate tokens for parallel verification. However, current approaches are limited by sequential stage dependencies that prevent full…

Artificial Intelligence · Computer Science 2025-05-06 Bradley McDanel , Sai Qian Zhang , Yunhai Hu , Zining Liu

Massive data analysis becomes increasingly prevalent, subsampling methods like BLB (Bag of Little Bootstraps) serves as powerful tools for assessing the quality of estimators for massive data. However, the performance of the subsampling…

Methodology · Statistics 2022-01-14 Yingying Ma , Hansheng Wang

We propose a feature-extraction procedure based on the statistical characterization of waveforms, applied as a fast pre-processing stage in a pattern recognition task using simple artificial neural network models. This procedure involves…

Signal Processing · Electrical Eng. & Systems 2025-12-30 G. H. Bustos , H. H. Segnorile

Continual learning aims to refine model parameters for new tasks while retaining knowledge from previous tasks. Recently, prompt-based learning has emerged to leverage pre-trained models to be prompted to learn subsequent tasks without the…

Computer Vision and Pattern Recognition · Computer Science 2024-03-19 Jisu Han , Jaemin Na , Wonjun Hwang

Feature subset selection, as a special case of the general subset selection problem, has been the topic of a considerable number of studies due to the growing importance of data-mining applications. In the feature subset selection problem…

Machine Learning · Computer Science 2014-11-13 Tofigh Naghibi , Sarah Hoffmann , Beat Pfister

Diffusion probabilistic models (DPMs) have achieved impressive success in visual generation. While, they suffer from slow inference speed due to iterative sampling. Employing fewer sampling steps is an intuitive solution, but this will also…

Computer Vision and Pattern Recognition · Computer Science 2025-06-17 Hu Yu , Hao Luo , Fan Wang , Feng Zhao

Existing pyramid-based upsamplers (e.g. SemanticFPN), although efficient, usually produce less accurate results compared to dilation-based models when using the same backbone. This is partially caused by the contaminated high-level features…

Computer Vision and Pattern Recognition · Computer Science 2023-11-30 Ye Huang , Di Kang , Shenghua Gao , Wen Li , Lixin Duan

Large Language Models (LLMs) have demonstrated remarkable capabilities in handling long context inputs, but this comes at the cost of increased computational resources and latency. Our research introduces a novel approach for the long…

Computation and Language · Computer Science 2024-09-27 Zhenmei Shi , Yifei Ming , Xuan-Phi Nguyen , Yingyu Liang , Shafiq Joty

This work is concerned with approximating the smallest eigenvalue of a parameter-dependent Hermitian matrix $A(\mu)$ for many parameter values $\mu \in \mathbb{R}^P$. The design of reliable and efficient algorithms for addressing this task…

Numerical Analysis · Mathematics 2015-04-24 Petar Sirković , Daniel Kressner

Multimodal Large Language Models (MLLMs) have demonstrated significant capabilities in image understanding, but long-video are constrained by context windows and computational cost. Uniform frame sampling often leads to substantial…

Machine Learning · Computer Science 2025-10-17 Yifeng Yao , Yike Yun , Jing Wang , Huishuai Zhang , Dongyan Zhao , Ke Tian , Zhihao Wang , Minghui Qiu , Tao Wang

Contextual Partitioning introduces an innovative approach to enhancing the architectural design of large-scale computational models through the dynamic segmentation of parameters into context-aware regions. This methodology emphasizes the…

Computation and Language · Computer Science 2025-08-11 Offa Kingsleigh , Alfred Abercrombie , David Woolstencroft , Beorhtric Meadowcroft , Marcus Irvin

In this study, we present an innovative technique for speaker adaptation in order to improve the accuracy of segmentation with application to unit-selection Text-To-Speech (TTS) systems. Unlike conventional techniques for speaker…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-01 Claudio Zito , Fabio Tesser , Mauro Nicolao , Piero Cosi

An important approach for efficient inference in probabilistic graphical models exploits symmetries among objects in the domain. Symmetric variables (states) are collapsed into meta-variables (meta-states) and inference algorithms are run…

Artificial Intelligence · Computer Science 2016-07-01 Ankit Anand , Aditya Grover , Mausam , Parag Singla

This work focuses on a parameter-free joint piecewise smooth image denoising and contour detection. Formulated as the minimization of a discrete Mumford-Shah functional and estimated via a theoretically grounded alternating minimization…

Image and Video Processing · Electrical Eng. & Systems 2023-02-01 Charles-Gérard Lucas , Barbara Pascal , Nelly Pustelnik , Patrice Abry

Current object detectors typically have a feature pyramid (FP) module for multi-level feature fusion (MFF) which aims to mitigate the gap between features from different levels and form a comprehensive object representation to achieve…

Computer Vision and Pattern Recognition · Computer Science 2023-08-29 Zhe Chen , Jing Zhang , Yufei Xu , Dacheng Tao

Promptable foundation models such as the Segment Anything Model (SAM) produce high-quality masks but remain semantically blind, relying on external prompts to specify categories. Existing vision-language approaches address this limitation…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Shayan Jalilian , Abdul Bais

We consider the problem of using sentence compression techniques to facilitate query-focused multi-document summarization. We present a sentence-compression-based framework for the task, and design a series of learning-based compression…

Computation and Language · Computer Science 2016-06-27 Lu Wang , Hema Raghavan , Vittorio Castelli , Radu Florian , Claire Cardie