Image de couverture de livre

E2Former-V2: On-the-Fly Equivariant Attention with Linear Activation Memory

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Huang, Lin, Huang, Chengxiang, Wang, Ziang, Du, Yiyue, Wang, Chu, Lu, Haocheng, Li, Yunyang, Liu, Xiaoli, Jiang, Arthur, Zhang, Jia
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

E2Former: An Efficient and Equivariant Transformer with Linear-Scaling Tensor Products
par: Li, Yunyang, et autres
Publié: (2025)

Elign: Equivariant Diffusion Model Alignment from Foundational Machine Learning Force Fields
par: Li, Yunyang, et autres
Publié: (2026)

LaplacianFormer:Rethinking Linear Attention with Laplacian Kernel
par: Feng, Zhe, et autres
Publié: (2026)

PolaFormer: Polarity-aware Linear Attention for Vision Transformers
par: Meng, Weikang, et autres
Publié: (2025)

On-the-Fly Adaptive Distillation of Transformer to Dual-State Linear Attention
par: Ro, Yeonju, et autres
Publié: (2025)

Linear Memory SE(2) Invariant Attention
par: Pronovost, Ethan, et autres
Publié: (2025)

MDN: Parallelizing Stepwise Momentum for Delta Linear Attention
par: Huang, Yulong, et autres
Publié: (2026)

Inter2Former: Dynamic Hybrid Attention for Efficient High-Precision Interactive
par: Huang, You, et autres
Publié: (2025)

GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Prediction
par: Huang, Yuanhui, et autres
Publié: (2024)

MemFly: On-the-Fly Memory Optimization via Information Bottleneck
par: Zhang, Zhenyuan, et autres
Publié: (2026)

Flow Equivariant World Models: Memory for Partially Observed Dynamic Environments
par: Lillemark, Hansen Jin, et autres
Publié: (2026)

ScatterFormer: Efficient Voxel Transformer with Scattered Linear Attention
par: He, Chenhang, et autres
Publié: (2024)

FloE: On-the-Fly MoE Inference on Memory-constrained GPU
par: Zhou, Yuxin, et autres
Publié: (2025)

LinearARD: Linear-Memory Attention Distillation for RoPE Restoration
par: Yang, Ning, et autres
Publié: (2026)

MixFormerV2: Efficient Fully Transformer Tracking
par: Cui, Yutao, et autres
Publié: (2023)

AesFormer: Transform Everyday Photos into Beautiful Memories
par: Du, Tianxiang, et autres
Publié: (2026)

Search for New Particles with Flying Quantum Sensors in Space
par: Huang, Xingming, et autres
Publié: (2024)

SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference
par: Zhang, Jintao, et autres
Publié: (2025)

Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference
par: You, Haoran, et autres
Publié: (2022)

MonoFormer: One Transformer for Both Diffusion and Autoregression
par: Zhao, Chuyang, et autres
Publié: (2024)

COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training
par: Xi, Haocheng, et autres
Publié: (2024)

Scalable Machine Learning Force Fields for Macromolecular Systems Through Long-Range Aware Message Passing
par: Wang, Chu, et autres
Publié: (2026)

UBio-MolFM: A Universal Molecular Foundation Model for Bio-Systems
par: Huang, Lin, et autres
Publié: (2026)

FreqMixFormerV2: Lightweight Frequency-aware Mixed Transformer for Human Skeleton Action Recognition
par: Wu, Wenhan, et autres
Publié: (2024)

Cation–Anion Synergistic Activation of Ni(OH) 2 for Efficient Electrooxidation of 5‐Hydroxymethylfurfural
par: Kangnan Yuan, et autres
Publié: (2026)

Few-shot Implicit Function Generation via Equivariance
par: Huang, Suizhi, et autres
Publié: (2025)

RSRWKV: A Linear-Complexity 2D Attention Mechanism for Efficient Remote Sensing Vision Task
par: Li, Chunshan, et autres
Publié: (2025)

23‐2: Invited Paper: A Multimodal Network for Visual Discomfort Prediction
par: Yunyang Shi, et autres
Publié: (2025)

ResFormer: All-Time Reservoir Memory for Long Sequence Classification
par: Liu, Hongbo, et autres
Publié: (2025)

Orient Anything V2: Unifying Orientation and Rotation Understanding
par: Wang, Zehan, et autres
Publié: (2026)

VecFormer: Towards Efficient and Generalizable Graph Transformer with Graph Token Attention
par: Zhou, Jingbo, et autres
Publié: (2026)

Power-based Partial Attention: Bridging Linear-Complexity and Full Attention
par: Huang, Yufeng
Publié: (2026)

Seeing Through Reflections: Advancing 3D Scene Reconstruction in Mirror-Containing Environments with Gaussian Splatting
par: Guo, Zijing, et autres
Publié: (2025)

CloudFormer: An Attention-based Performance Prediction for Public Clouds with Unknown Workload
par: Shahbazinia, Amirhossein, et autres
Publié: (2025)

SLA2: Sparse-Linear Attention with Learnable Routing and QAT
par: Zhang, Jintao, et autres
Publié: (2026)

E(2)-Equivariant Graph Planning for Navigation
par: Zhao, Linfeng, et autres
Publié: (2023)

SpatialFormer: Semantic and Target Aware Attentions for Few-Shot Learning
par: Lai, Jinxiang, et autres
Publié: (2023)

Attention2Probability: Attention-Driven Terminology Probability Estimation for Robust Speech-to-Text System
par: Du, Yanfan, et autres
Publié: (2025)

Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions
par: Kang, Diancheng, et autres
Publié: (2026)

RecurFormer: Not All Transformer Heads Need Self-Attention
par: Yan, Ruiqing, et autres
Publié: (2024)