Cover Image

GradAttn: Replacing Fixed Residual Connections with Task-Modulated Attention Pathways

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ghoshal, Soudeep, Buckchash, Himanshu
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

D-Attn: Decomposed Attention for Large Vision-and-Language Models
by: Kuo, Chia-Wen, et al.
Published: (2025)

DiTFastAttn: Attention Compression for Diffusion Transformer Models
by: Yuan, Zhihang, et al.
Published: (2024)

Fusing Memory and Attention: A study on LSTM, Transformer and Hybrid Architectures for Symbolic Music Generation
by: Ghoshal, Soudeep, et al.
Published: (2026)

AttnMod: Attention-Based New Art Styles
by: Su, Shih-Chieh
Published: (2024)

TS-Attn: Temporal-wise Separable Attention for Multi-Event Video Generation
by: Zhang, Hongyu, et al.
Published: (2026)

AttnRouter: Per-Category Attention Routing for Training-Free Image Editing on MMDiT
by: Li, Guandong, et al.
Published: (2026)

Comp-Attn: Present-and-Align Attention for Compositional Video Generation
by: Zhang, Hongyu, et al.
Published: (2025)

NDT: Non-Differential Transformer and Its Application to Sentiment Analysis
by: Ghoshal, Soudeep, et al.
Published: (2026)

Rectified SpaAttn: Revisiting Attention Sparsity for Efficient Video Generation
by: Liu, Xuewen, et al.
Published: (2025)

Attn-Adapter: Attention Is All You Need for Online Few-shot Learner of Vision-Language Model
by: Bui, Phuoc-Nguyen, et al.
Published: (2025)

ReViT: Enhancing Vision Transformers Feature Diversity with Attention Residual Connections
by: Diko, Anxhelo, et al.
Published: (2024)

ColFigPhotoAttnNet: Reliable Finger Photo Presentation Attack Detection Leveraging Window-Attention on Color Spaces
by: Vurity, Anudeep, et al.
Published: (2025)

DiffAttn: Diffusion-Based Drivers' Visual Attention Prediction with LLM-Enhanced Semantic Reasoning
by: Liu, Weimin, et al.
Published: (2026)

AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers
by: Achtibat, Reduan, et al.
Published: (2024)

DiTFastAttnV2: Head-wise Attention Compression for Multi-Modality Diffusion Transformers
by: Zhang, Hanling, et al.
Published: (2025)

$Δ$-AttnMask: Attention-Guided Masked Hidden States for Efficient Data Selection and Augmentation
by: Hu, Jucheng, et al.
Published: (2025)

AttnDreamBooth: Towards Text-Aligned Personalized Text-to-Image Generation
by: Pang, Lianyu, et al.
Published: (2024)

Residual Connections Harm Generative Representation Learning
by: Zhang, Xiao, et al.
Published: (2024)

FlowPortal: Residual-Corrected Flow for Training-Free Video Relighting and Background Replacement
by: Gao, Wenshuo, et al.
Published: (2025)

Generalizing GradCAM for Embedding Networks
by: Bachhawat, Mudit
Published: (2024)

Enhancing ASL Recognition with GCNs and Successive Residual Connections
by: Sarkar, Ushnish, et al.
Published: (2024)

Enhancing Tea Leaf Disease Recognition with Attention Mechanisms and Grad-CAM Visualization
by: Shikdar, Omar Faruq, et al.
Published: (2025)

Replacement Learning: Training Vision Tasks with Fewer Learnable Parameters
by: Zhang, Yuming, et al.
Published: (2024)

DIFEM: Key-points Interaction based Feature Extraction Module for Violence Recognition in Videos
by: Mittal, Himanshu, et al.
Published: (2024)

FG-Attn: Leveraging Fine-Grained Sparsity In Diffusion Transformers
by: Durvasula, Sankeerth, et al.
Published: (2025)

Soybean Disease Detection via Interpretable Hybrid CNN-GNN: Integrating MobileNetV2 and GraphSAGE with Cross-Modal Attention
by: Jahin, Md Abrar, et al.
Published: (2025)

Delta Attention Residuals
by: Luo, Cheng, et al.
Published: (2026)

An Attention Infused Deep Learning System with Grad-CAM Visualization for Early Screening of Glaucoma
by: Swaminathan, Ramanathan
Published: (2025)

Interpretable Dynamic Graph Neural Networks for Small Occluded Object Detection and Tracking
by: Soudeep, Shahriar, et al.
Published: (2024)

PADRe: A Unifying Polynomial Attention Drop-in Replacement for Efficient Vision Transformer
by: Letourneau, Pierre-David, et al.
Published: (2024)

MaskAttn-SDXL: Controllable Region-Level Text-To-Image Generation
by: Chang, Yu, et al.
Published: (2025)

ResLink: A Novel Deep Learning Architecture for Brain Tumor Classification with Area Attention and Residual Connections
by: Arya, Sumedha, et al.
Published: (2025)

Grad-ECLIP: Gradient-based Visual and Textual Explanations for CLIP
by: Zhao, Chenyang, et al.
Published: (2025)

MaskAttn-UNet: A Mask Attention-Driven Framework for Universal Low-Resolution Image Segmentation
by: Cheng, Anzhe, et al.
Published: (2025)

Attention Residual Fusion Network with Contrast for Source-free Domain Adaptation
by: Shao, Renrong, et al.
Published: (2025)

uniGradICON: A Foundation Model for Medical Image Registration
by: Tian, Lin, et al.
Published: (2024)

Deterministic Continuous Replacement: Fast and Stable Module Replacement in Pretrained Transformers
by: Bradbury, Rowan, et al.
Published: (2025)

RG-Attn: Radian Glue Attention for Multi-modality Multi-agent Cooperative Perception
by: Li, Lantao, et al.
Published: (2025)

ResCLIP: Residual Attention for Training-free Dense Vision-language Inference
by: Yang, Yuhang, et al.
Published: (2024)

BiM-GeoAttn-Net: Linear-Time Depth Modeling with Geometry-Aware Attention for 3D Aortic Dissection CTA Segmentation
by: Zhang, Yuan, et al.
Published: (2026)