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