Imagen de Portada

Activator: GLU Activation Function as the Core Component of a Vision Transformer

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Abdullah, Abdullah Nazhat, Aydin, Tarkan
Formato:	Preprint
Publicado:	2024
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

NiNformer: A Network in Network Transformer with Token Mixing Generated Gating Function
por: Abdullah, Abdullah Nazhat, et al.
Publicado: (2024)

LoLA-SpecViT: Local Attention SwiGLU Vision Transformer with LoRA for Hyperspectral Imaging
por: Zidi, Fadi Abdeladhim, et al.
Publicado: (2025)

ADFQ-ViT: Activation-Distribution-Friendly Post-Training Quantization for Vision Transformers
por: Jiang, Yanfeng, et al.
Publicado: (2024)

ABFR-KAN: Kolmogorov-Arnold Networks for Functional Brain Analysis
por: Ward, Tyler, et al.
Publicado: (2026)

Trainable Highly-expressive Activation Functions
por: Chelly, Irit, et al.
Publicado: (2024)

Layout Anything: One Transformer for Universal Room Layout Estimation
por: Mia, Md Sohag, et al.
Publicado: (2025)

Can Cross-Layer Transcoders Replace Vision Transformer Activations? An Interpretable Perspective on Vision
por: Chatzoudis, Gerasimos, et al.
Publicado: (2026)

Steering Video Diffusion Transformers with Massive Activations
por: Cheng, Xianhang, et al.
Publicado: (2026)

MixA-Q: Revisiting Activation Sparsity for Vision Transformers from a Mixed-Precision Quantization Perspective
por: Wang, Weitian, et al.
Publicado: (2025)

TAP into the Patch Tokens: Leveraging Vision Foundation Model Features for AI-Generated Image Detection
por: Abdullah, Ahmed, et al.
Publicado: (2026)

Prompting Medical Vision-Language Models to Mitigate Diagnosis Bias by Generating Realistic Dermoscopic Images
por: Munia, Nusrat, et al.
Publicado: (2025)

L-SWAG: Layer-Sample Wise Activation with Gradients information for Zero-Shot NAS on Vision Transformers
por: Casarin, Sofia, et al.
Publicado: (2025)

Improving Brain Disorder Diagnosis with Advanced Brain Function Representation and Kolmogorov-Arnold Networks
por: Ward, Tyler, et al.
Publicado: (2025)

Vision-Centric Activation and Coordination for Multimodal Large Language Models
por: Wang, Yunnan, et al.
Publicado: (2025)

Adaptive Parametric Activation: Unifying and Generalising Activation Functions Across Tasks
por: Alexandridis, Konstantinos Panagiotis, et al.
Publicado: (2024)

MDE-VIO: Enhancing Visual-Inertial Odometry Using Learned Depth Priors
por: Alniak, Arda, et al.
Publicado: (2026)

Unleashing Diffusion Transformers for Visual Correspondence by Modulating Massive Activations
por: Gan, Chaofan, et al.
Publicado: (2025)

Massive Activations are the Key to Local Detail Synthesis in Diffusion Transformers
por: Gan, Chaofan, et al.
Publicado: (2025)

EVCC: Enhanced Vision Transformer-ConvNeXt-CoAtNet Fusion for Classification
por: Hasan, Kazi Reyazul, et al.
Publicado: (2025)

Evaluating Model Performance with Hard-Swish Activation Function Adjustments
por: Pydimarry, Sai Abhinav, et al.
Publicado: (2024)

STAF: Sinusoidal Trainable Activation Functions for Implicit Neural Representation
por: Morsali, Alireza, et al.
Publicado: (2025)

Pix4Point: Image Pretrained Standard Transformers for 3D Point Cloud Understanding
por: Qian, Guocheng, et al.
Publicado: (2022)

DiTAS: Quantizing Diffusion Transformers via Enhanced Activation Smoothing
por: Dong, Zhenyuan, et al.
Publicado: (2024)

VISIONLOGIC: From Neuron Activations to Causally Grounded Concept Rules for Vision Models
por: Geng, Chuqin, et al.
Publicado: (2025)

A Probabilistic Segment Anything Model for Ambiguity-Aware Medical Image Segmentation
por: Ward, Tyler, et al.
Publicado: (2025)

DArFace: Deformation Aware Robustness for Low Quality Face Recognition
por: Gulshad, Sadaf, et al.
Publicado: (2025)

Class-N-Diff: Classification-Induced Diffusion Model Can Make Fair Skin Cancer Diagnosis
por: Munia, Nusrat, et al.
Publicado: (2025)

FINER++: Building a Family of Variable-periodic Functions for Activating Implicit Neural Representation
por: Zhu, Hao, et al.
Publicado: (2024)

Ask Me Again Differently: GRAS for Measuring Bias in Vision Language Models on Gender, Race, Age, and Skin Tone
por: Malik, Shaivi, et al.
Publicado: (2025)

VisionTrap: Unanswerable Questions On Visual Data
por: Saadat, Asir, et al.
Publicado: (2025)

Skin Lesion Classification Using a Soft Voting Ensemble of Convolutional Neural Networks
por: Shafi, Abdullah Al, et al.
Publicado: (2025)

SpaAct: Spatially-Activated Transition Learning with Curriculum Adaptation for Vision-Language Navigation
por: Li, Pengna, et al.
Publicado: (2026)

Activation Quantization of Vision Encoders Needs Prefixing Registers
por: Kim, Seunghyeon, et al.
Publicado: (2025)

Memory-Efficient Vision Transformers: An Activation-Aware Mixed-Rank Compression Strategy
por: Azizi, Seyedarmin, et al.
Publicado: (2024)

GraphFusion3D: Dynamic Graph Attention Convolution with Adaptive Cross-Modal Transformer for 3D Object Detection
por: Mia, Md Sohag, et al.
Publicado: (2025)

YoloTag: Vision-based Robust UAV Navigation with Fiducial Markers
por: Raxit, Sourav, et al.
Publicado: (2024)

ConMamba: Contrastive Vision Mamba for Plant Disease Detection
por: Mamun, Abdullah Al, et al.
Publicado: (2025)

GenFormer -- Generated Images are All You Need to Improve Robustness of Transformers on Small Datasets
por: Oehri, Sven, et al.
Publicado: (2024)

PSMamba: Progressive Self-supervised Vision Mamba for Plant Disease Recognition
por: Mamun, Abdullah Al, et al.
Publicado: (2025)

Activating Distributed Visual Region within LLMs for Efficient and Effective Vision-Language Training and Inference
por: Wang, Siyuan, et al.
Publicado: (2024)