Imagen de Portada

The Need for Speed: Pruning Transformers with One Recipe

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Khaki, Samir, Plataniotis, Konstantinos N.
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

ProbMCL: Simple Probabilistic Contrastive Learning for Multi-label Visual Classification
por: Sajedi, Ahmad, et al.
Publicado: (2024)

Data-to-Model Distillation: Data-Efficient Learning Framework
por: Sajedi, Ahmad, et al.
Publicado: (2024)

DataDAM: Efficient Dataset Distillation with Attention Matching
por: Sajedi, Ahmad, et al.
Publicado: (2023)

SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity
por: Khaki, Samir, et al.
Publicado: (2025)

Active Inference and Reinforcement Learning: A unified inference on continuous state and action spaces under partial observability
por: Malekzadeh, Parvin, et al.
Publicado: (2022)

A unified uncertainty-aware exploration: Combining epistemic and aleatory uncertainty
por: Malekzadeh, Parvin, et al.
Publicado: (2024)

Prioritize Alignment in Dataset Distillation
por: Li, Zekai, et al.
Publicado: (2024)

Uncertainty-aware transfer across tasks using hybrid model-based successor feature reinforcement learning
por: Malekzadeh, Parvin, et al.
Publicado: (2023)

A Robust Quantile Huber Loss With Interpretable Parameter Adjustment In Distributional Reinforcement Learning
por: Malekzadeh, Parvin, et al.
Publicado: (2024)

NYCTALE: Neuro-Evidence Transformer for Adaptive and Personalized Lung Nodule Invasiveness Prediction
por: Khademi, Sadaf, et al.
Publicado: (2024)

GSTAM: Efficient Graph Distillation with Structural Attention-Matching
por: Rasti-Meymandi, Arash, et al.
Publicado: (2024)

The Missing Point in Vision Transformers for Universal Image Segmentation
por: Shahabodini, Sajjad, et al.
Publicado: (2025)

DECODE: Dual-Enhanced Conditioned Diffusion for EEG Forecasting
por: Shabanpour, Mehran, et al.
Publicado: (2026)

Sparse Model Soups: A Recipe for Improved Pruning via Model Averaging
por: Zimmer, Max, et al.
Publicado: (2023)

EX-DRL: Hedging Against Heavy Losses with EXtreme Distributional Reinforcement Learning
por: Malekzadeh, Parvin, et al.
Publicado: (2024)

Normalized Conditional Mutual Information Surrogate Loss for Deep Neural Classifiers
por: Ye, Linfeng, et al.
Publicado: (2026)

Self-Prompting Polyp Segmentation in Colonoscopy using Hybrid Yolo-SAM 2 Model
por: Mansoori, Mobina, et al.
Publicado: (2024)

Polyp SAM 2: Advancing Zero shot Polyp Segmentation in Colorectal Cancer Detection
por: Mansoori, Mobina, et al.
Publicado: (2024)

HistoSegCap: Capsules for Weakly-Supervised Semantic Segmentation of Histological Tissue Type in Whole Slide Images
por: Mansoori, Mobina, et al.
Publicado: (2024)

Resource-Constrained Affect Modelling via Variance Regularisation Pruning
por: Pinitas, Kosmas, et al.
Publicado: (2026)

FedD2S: Personalized Data-Free Federated Knowledge Distillation
por: Atapour, Kawa, et al.
Publicado: (2024)

Leveraging Foundation Models for Efficient Federated Learning in Resource-restricted Edge Networks
por: Atapour, S. Kawa, et al.
Publicado: (2024)

CORP: Closed-Form One-shot Representation-Preserving Structured Pruning for Transformers
por: Zhang, Boxiang, et al.
Publicado: (2026)

Value of Information-Enhanced Exploration in Bootstrapped DQN
por: Plataniotis, Stergios, et al.
Publicado: (2025)

TimeRecipe: A Time-Series Forecasting Recipe via Benchmarking Module Level Effectiveness
por: Zhao, Zhiyuan, et al.
Publicado: (2025)

Adapting to Distribution Shift by Visual Domain Prompt Generation
por: Chi, Zhixiang, et al.
Publicado: (2024)

Learning to Adapt Frozen CLIP for Few-Shot Test-Time Domain Adaptation
por: Chi, Zhixiang, et al.
Publicado: (2025)

SEVEN: Pruning Transformer Model by Reserving Sentinels
por: Xiao, Jinying, et al.
Publicado: (2024)

Advancements in Medical Image Classification through Fine-Tuning Natural Domain Foundation Models
por: Mansoori, Mobina, et al.
Publicado: (2025)

Beyond One-Way Pruning: Bidirectional Pruning-Regrowth for Extreme Accuracy-Sparsity Tradeoff
por: Liu, Junchen, et al.
Publicado: (2025)

ATOM: Attention Mixer for Efficient Dataset Distillation
por: Khaki, Samir, et al.
Publicado: (2024)

Muon in Vision Transformers: Optimizer-Recipe Interactions and Gradient Spectra
por: Southworth, Ben S., et al.
Publicado: (2026)

A Recipe for Improved Certifiable Robustness
por: Hu, Kai, et al.
Publicado: (2023)

Adaptive Pruning of Pretrained Transformer via Differential Inclusions
por: Ding, Yizhuo, et al.
Publicado: (2025)

OpenThoughts: Data Recipes for Reasoning Models
por: Guha, Etash, et al.
Publicado: (2025)

SAS: Semantic-aware Sampling for Generative Dataset Distillation
por: Li, Mingzhuo, et al.
Publicado: (2026)

Distribution Alignment for Fully Test-Time Adaptation with Dynamic Online Data Streams
por: Wang, Ziqiang, et al.
Publicado: (2024)

Plug-in Feedback Self-adaptive Attention in CLIP for Training-free Open-Vocabulary Segmentation
por: Chi, Zhixiang, et al.
Publicado: (2025)

Pruning One More Token is Enough: Leveraging Latency-Workload Non-Linearities for Vision Transformers on the Edge
por: Eliopoulos, Nick John, et al.
Publicado: (2024)

Information-Guided Diffusion Sampling for Dataset Distillation
por: Ye, Linfeng, et al.
Publicado: (2025)