Cover Image

An empirical study of task and feature correlations in the reuse of pre-trained models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Mohamud, Jama Hussein, Brink, Willie
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Self-Routing: Parameter-Free Expert Routing from Hidden States
by: Mohamud, Jama Hussein, et al.
Published: (2026)

Why pre-training is beneficial for downstream classification tasks?
by: Jiang, Xin, et al.
Published: (2024)

Multi-task GINN-LP for Multi-target Symbolic Regression
by: Rajabu, Hussein, et al.
Published: (2025)

Leveraging LLMs as Meta-Judges: A Multi-Agent Framework for Evaluating LLM Judgments
by: Li, Yuran, et al.
Published: (2025)

Prompt replay: speeding up grpo with on-policy reuse of high-signal prompts
by: Baroian, Andrei, et al.
Published: (2026)

Aviary: training language agents on challenging scientific tasks
by: Narayanan, Siddharth, et al.
Published: (2024)

Provable unlearning in topic modeling and downstream tasks
by: Wei, Stanley, et al.
Published: (2024)

A comparative study on feature selection for a risk prediction model for colorectal cancer
by: Cueto-López, N., et al.
Published: (2024)

pUniFind: a unified large pre-trained deep learning model pushing the limit of mass spectra interpretation
by: Zhao, Jiale, et al.
Published: (2025)

User-centric evaluation of explainability of AI with and for humans: a comprehensive empirical study
by: Bobek, Szymon, et al.
Published: (2024)

Continual Quantization-Aware Pre-Training: When to transition from 16-bit to 1.58-bit pre-training for BitNet language models?
by: Nielsen, Jacob, et al.
Published: (2025)

Target noise: A pre-training based neural network initialization for efficient high resolution learning
by: Wang, Shaowen, et al.
Published: (2026)

Are foundation models useful feature extractors for electroencephalography analysis?
by: Turgut, Özgün, et al.
Published: (2025)

EXACT: Towards a platform for empirically benchmarking Machine Learning model explanation methods
by: Clark, Benedict, et al.
Published: (2024)

Early-stopping for Transformer model training
by: He, Jing, et al.
Published: (2025)

Adaptively profiling models with task elicitation
by: Brown, Davis, et al.
Published: (2025)

Uncertainty Quantification for Forward and Inverse Problems of PDEs via Latent Global Evolution
by: Wu, Tailin, et al.
Published: (2024)

Stanford Sleep Bench: Evaluating Polysomnography Pre-training Methods for Sleep Foundation Models
by: Kjaer, Magnus Ruud, et al.
Published: (2025)

Benchmarking pre-trained text embedding models in aligning built asset information
by: Shahinmoghadam, Mehrzad, et al.
Published: (2024)

Knowledge graphs for empirical concept retrieval
by: Tětková, Lenka, et al.
Published: (2024)

Inductive biases of multi-task learning and finetuning: multiple regimes of feature reuse
by: Lippl, Samuel, et al.
Published: (2023)

MTLComb: multi-task learning combining regression and classification tasks for joint feature selection
by: Cao, Han, et al.
Published: (2024)

Deep learning and abstractive summarisation for radiological reports: an empirical study for adapting the PEGASUS models' family with scarce data
by: Benzoni, Claudio, et al.
Published: (2025)

Tokenize features, enhancing tables: the FT-TABPFN model for tabular classification
by: Liu, Quangao, et al.
Published: (2024)

Preventing overfitting in deep learning using differential privacy
by: Khatri, Alizishaan Anwar Hussein
Published: (2026)

EXGnet: a single-lead explainable-AI guided multiresolution network with train-only quantitative features for trustworthy ECG arrhythmia classification
by: Showrav, Tushar Talukder, et al.
Published: (2025)

ExplainerPFN: Towards tabular foundation models for model-free zero-shot feature importance estimations
by: Fonseca, Joao, et al.
Published: (2026)

Small transformer architectures for task switching
by: Gros, Claudius
Published: (2025)

Efficiency optimization of large-scale language models based on deep learning in natural language processing tasks
by: Mei, Taiyuan, et al.
Published: (2024)

Aleph-Alpha-GermanWeb: Improving German-language LLM pre-training with model-based data curation and synthetic data generation
by: Burns, Thomas F, et al.
Published: (2025)

Auxiliary task discovery through generate-and-test
by: Rafiee, Banafsheh, et al.
Published: (2022)

Does Deep Active Learning Work in the Wild?
by: Ren, Simiao, et al.
Published: (2023)

DeLLMa: Decision Making Under Uncertainty with Large Language Models
by: Liu, Ollie, et al.
Published: (2024)

IMPACTX: improving model performance by appropriately constraining the training with teacher explanations
by: Apicella, Andrea, et al.
Published: (2025)

Building surrogate models using trajectories of agents trained by Reinforcement Learning
by: Cestero, Julen, et al.
Published: (2025)

RDI: An adversarial robustness evaluation metric for deep neural networks based on model statistical features
by: Song, Jialei, et al.
Published: (2025)

ProdRev: A DNN framework for empowering customers using generative pre-trained transformers
by: Gupta, Aakash, et al.
Published: (2025)

TrackGPT -- A generative pre-trained transformer for cross-domain entity trajectory forecasting
by: Stroh, Nicholas
Published: (2024)

Curriculum reinforcement learning with measurable task representation learning
by: Wen, Yongyan, et al.
Published: (2026)

Offline Multi-task Transfer RL with Representational Penalization
by: Bose, Avinandan, et al.
Published: (2024)