English
Related papers

Related papers: Efficient Stitchable Task Adaptation

200 papers

Recently, there have been increasing demands to construct compact deep architectures to remove unnecessary redundancy and to improve the inference speed. While many recent works focus on reducing the redundancy by eliminating unneeded…

Computer Vision and Pattern Recognition · Computer Science 2018-03-28 Eunwoo Kim , Chanho Ahn , Songhwai Oh

Spatio-Temporal predictive Learning is a self-supervised learning paradigm that enables models to identify spatial and temporal patterns by predicting future frames based on past frames. Traditional methods, which use recurrent neural…

Computer Vision and Pattern Recognition · Computer Science 2024-11-18 Andrea Alfarano , Alberto Alfarano , Linda Friso , Andrea Bacciu , Irene Amerini , Fabrizio Silvestri

The demand for low-power inference and training of deep neural networks (DNNs) on edge devices has intensified the need for algorithms that are both scalable and energy-efficient. While spiking neural networks (SNNs) allow for efficient…

Neural and Evolutionary Computing · Computer Science 2025-11-18 Marco Paul E. Apolinario , Kaushik Roy , Charlotte Frenkel

Fine-grained sparsity promises higher parametric capacity without proportional per-token compute, but often suffers from training instability, load balancing, and communication overhead. We introduce STEM (Scaling Transformers with…

We propose STANE (Shared and Time-specific Adaptive Network Embedding), a new joint embedding framework for dynamic networks that captures both stable global structures and localized temporal variations. To further improve the model's…

Methodology · Statistics 2025-10-21 Hairi Bai , Xinyan Fan , Kuangnan Fang , Yan Zhang

The rapid evolution of large language models (LLMs) has intensified the demand for effective personalization techniques that can adapt model behavior to individual user preferences. Despite the non-parametric methods utilizing the…

Artificial Intelligence · Computer Science 2025-11-03 Kounianhua Du , Jianxing Liu , Kangning Zhang , Wenxiang Jiao , Yuan Lu , Jiarui Jin , Weiwen Liu , Yong Yu , Weinan Zhang

We propose a distributed system based on lowpower embedded FPGAs designed for edge computing applications focused on exploring distributing scheduling optimizations for Deep Learning (DL) workloads to obtain the best performance regarding…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-05-31 Hans Johnson , Tianyang Fang , Alejandro Perez-Vicente , Jafar Saniie

There has been growing interest in parameter-efficient methods to apply pre-trained language models to downstream tasks. Building on the Prompt Tuning approach of Lester et al. (2021), which learns task-specific soft prompts to condition a…

Computation and Language · Computer Science 2022-03-18 Tu Vu , Brian Lester , Noah Constant , Rami Al-Rfou , Daniel Cer

Intermediate-task transfer can benefit a wide range of NLP tasks with properly selected source datasets. However, it is computationally infeasible to experiment with all intermediate transfer combinations, making choosing a useful source…

Computation and Language · Computer Science 2022-10-24 Wangchunshu Zhou , Canwen Xu , Julian McAuley

Spoken Language Models (SLMs) are increasingly central to modern speech-driven applications, but performance degrades under acoustic shift - real-world noise, reverberation, and microphone variation. Prior solutions rely on offline domain…

Neural Architecture Search (NAS) methods have been shown to outperform hand-designed models and help to democratize AI. However, NAS methods often start from scratch with each new task, making them computationally expensive and limiting…

Machine Learning · Computer Science 2025-07-15 Prabhant Singh , Joaquin Vanschoren

Training a deep neural network requires a large amount of single-task data and involves a long time-consuming optimization phase. This is not scalable to complex, realistic environments with new unexpected changes. Humans can perform fast…

Neural and Evolutionary Computing · Computer Science 2020-09-04 Tsendsuren Munkhdalai

While there are many advantages to deploying machine learning models on edge devices, the resource constraints of mobile platforms, the dynamic nature of the environment, and differences between the distribution of training versus…

Machine Learning · Computer Science 2025-03-21 Cynthia Dong , Hong Jia , Young D. Kwon , Georgios Rizos , Cecilia Mascolo

Spiking neural networks (SNNs), that operate via binary spikes distributed over time, have emerged as a promising energy efficient ML paradigm for resource-constrained devices. However, the current state-of-the-art (SOTA) SNNs require…

Computer Vision and Pattern Recognition · Computer Science 2021-12-23 Gourav Datta , Peter A. Beerel

Multivariate Time Series (MTS) forecasting plays a vital role in a wide range of applications. Recently, Spatial-Temporal Graph Neural Networks (STGNNs) have become increasingly popular MTS forecasting methods. STGNNs jointly model the…

Machine Learning · Computer Science 2022-08-17 Zezhi Shao , Zhao Zhang , Fei Wang , Yongjun Xu

With the rise of Visual and Language Pretraining (VLP), an increasing number of downstream tasks are adopting the paradigm of pretraining followed by fine-tuning. Although this paradigm has demonstrated potential in various multimodal…

Computer Vision and Pattern Recognition · Computer Science 2024-05-29 Tengjun Huang

While task-specific finetuning of pretrained networks has led to significant empirical advances in NLP, the large size of networks makes finetuning difficult to deploy in multi-task, memory-constrained settings. We propose diff pruning as a…

Computation and Language · Computer Science 2021-06-10 Demi Guo , Alexander M. Rush , Yoon Kim

We revisit and extend model stitching (Lenc & Vedaldi 2015) as a methodology to study the internal representations of neural networks. Given two trained and frozen models $A$ and $B$, we consider a "stitched model'' formed by connecting the…

Machine Learning · Computer Science 2021-06-16 Yamini Bansal , Preetum Nakkiran , Boaz Barak

Spiking neural networks (SNNs) promise low-power event-driven computation for temporally rich tasks, but commonly used neuron models often trade off gradient-based trainability, dynamical richness, and high activity sparsity. These…

Neural and Evolutionary Computing · Computer Science 2026-05-13 Alex Fulleda-Garcia , Saray Soldado-Magraner , Josep Maria Margarit-Taulé

Deep learning (DL)-based channel state information (CSI) feedback has shown promising potential to improve spectrum efficiency in massive MIMO systems. However, practical DL approaches require a sizeable CSI dataset for each scenario, and…

Information Theory · Computer Science 2023-11-07 Zhenyu Liu , Li Wang , Lianming Xu , Zhi Ding