Imagen de Portada

MirrorLA: Reflecting Feature Map for Vision Linear Attention

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Meng, Weikang, Huo, Liangyu, Luo, Yadan, Wang, Yaowei, Li, Yingjian, Zhang, Zheng
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Norm$\times$Direction: Restoring the Missing Query Norm in Vision Linear Attention
por: Meng, Weikang, et al.
Publicado: (2025)

STILL: Selecting Tokens for Intra-Layer Hybrid Attention to Linearize LLMs
por: Meng, Weikang, et al.
Publicado: (2026)

PolaFormer: Polarity-aware Linear Attention for Vision Transformers
por: Meng, Weikang, et al.
Publicado: (2025)

PLS in the Mirror of Self-Attention
por: Jiangsheng, et al.
Publicado: (2026)

MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map
por: Chou, Yuhong, et al.
Publicado: (2024)

A Finite Sample Analysis of Distributional TD Learning with Linear Function Approximation
por: Peng, Yang, et al.
Publicado: (2025)

Statistical Test for Attention Map in Vision Transformer
por: Shiraishi, Tomohiro, et al.
Publicado: (2024)

Degrees of Freedom for Linear Attention: Distilling Softmax Attention with Optimal Feature Efficiency
por: Nishikawa, Naoki, et al.
Publicado: (2025)

Multi-refined Feature Enhanced Sentiment Analysis Using Contextual Instruction
por: Atandoh, Peter, et al.
Publicado: (2025)

Provable Ordering and Continuity in Vision-Language Pretraining for Generalizable Embodied Agents
por: Zhang, Zhizhen, et al.
Publicado: (2025)

Scaling Linear Attention with Sparse State Expansion
por: Pan, Yuqi, et al.
Publicado: (2025)

ConjNorm: Tractable Density Estimation for Out-of-Distribution Detection
por: Peng, Bo, et al.
Publicado: (2024)

Nonstationary Generalized Linear Bandits with Discounted Online Mirror Descent
por: Lee, Joongkyu, et al.
Publicado: (2026)

EfficientECG: Cross-Attention with Feature Fusion for Efficient Electrocardiogram Classification
por: Deng, Hanhui, et al.
Publicado: (2025)

A Library of Mirrors: Deep Neural Nets in Low Dimensions are Convex Lasso Models with Reflection Features
por: Zeger, Emi, et al.
Publicado: (2024)

Dense Feature Learning via Linear Structure Preservation in Medical Data
por: Zhang, Yuanyun, et al.
Publicado: (2026)

PCaM: A Progressive Focus Attention-Based Information Fusion Method for Improving Vision Transformer Domain Adaptation
por: Zang, Zelin, et al.
Publicado: (2025)

Local Linear Attention: An Optimal Interpolation of Linear and Softmax Attention For Test-Time Regression
por: Zuo, Yifei, et al.
Publicado: (2025)

Beyond Euclidean Proximity: Repairing Latent World Models with Horizon-Matched Trajectory Reachability Metrics
por: Li, Liangyu, et al.
Publicado: (2026)

Kimi Linear: An Expressive, Efficient Attention Architecture
por: Kimi Team, et al.
Publicado: (2025)

Emotion Collider: Dual Hyperbolic Mirror Manifolds for Sentiment Recovery via Anti Emotion Reflection
por: Fu, Rong, et al.
Publicado: (2026)

Log-Linear Attention
por: Guo, Han, et al.
Publicado: (2025)

Statistical Efficiency of Distributional Temporal Difference Learning and Freedman's Inequality in Hilbert Spaces
por: Peng, Yang, et al.
Publicado: (2024)

Federated Reinforcement Learning with Constraint Heterogeneity
por: Jin, Hao, et al.
Publicado: (2024)

Linearized Diffusion Map
por: Candanedo, Julio
Publicado: (2025)

On-the-Fly Adaptive Distillation of Transformer to Dual-State Linear Attention
por: Ro, Yeonju, et al.
Publicado: (2025)

Class-Discriminative Attention Maps for Vision Transformers
por: Brocki, Lennart, et al.
Publicado: (2023)

Hallucination Detection in LLMs Using Spectral Features of Attention Maps
por: Binkowski, Jakub, et al.
Publicado: (2025)

RoPE Attention Can Be Trained in Almost Linear Time
por: Cao, Yang, et al.
Publicado: (2024)

Higher-order Linear Attention
por: Zhang, Yifan, et al.
Publicado: (2025)

Short-Long Convolutions Help Hardware-Efficient Linear Attention to Focus on Long Sequences
por: Liu, Zicheng, et al.
Publicado: (2024)

Adaptive Memory Decay for Log-Linear Attention
por: Amin, Yaxita, et al.
Publicado: (2026)

Training Dynamics of In-Context Learning in Linear Attention
por: Zhang, Yedi, et al.
Publicado: (2025)

MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object Detection
por: Chen, Zhuoxiao, et al.
Publicado: (2024)

Implicit Bias of Mirror Flow in Homogeneous Neural Networks: Sparse and Dense Feature Learning
por: Jacobs, Tom, et al.
Publicado: (2026)

Contextual Linear Bandits with Delay as Payoff
por: Zhang, Mengxiao, et al.
Publicado: (2025)

Macformer: Transformer with Random Maclaurin Feature Attention
por: Guo, Yuhan, et al.
Publicado: (2024)

One-Step Flow Policy Mirror Descent
por: Chen, Tianyi, et al.
Publicado: (2025)

CodeMerge: Codebook-Guided Model Merging for Robust Test-Time Adaptation in Autonomous Driving
por: Yang, Huitong, et al.
Publicado: (2025)

DistZO2: High-Throughput and Memory-Efficient Zeroth-Order Fine-tuning LLMs with Distributed Parallel Computing
por: Wang, Liangyu, et al.
Publicado: (2025)