Image de couverture de livre

The Phasor Transformer: Resolving Attention Bottlenecks on the Unit Circle

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Sigdel, Dibakar
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

PhasorFlow: A Python Library for Unit Circle Based Computing
par: Sigdel, Dibakar, et autres
Publié: (2026)

Variational Phasor Circuits for Phase-Native Brain-Computer Interface Classification
par: Sigdel, Dibakar
Publié: (2026)

Attention Saturation and Gradient Suppression at Inflection Layers: Diagnosing and Mitigating Bottlenecks in Transformer Adaptation
par: Zixian, Wang
Publié: (2025)

Flash STU: Fast Spectral Transform Units
par: Liu, Y. Isabel, et autres
Publié: (2024)

Resolve Highway Conflict in Multi-Autonomous Vehicle Controls with Local State Attention
par: Ta, Xuan Duy, et autres
Publié: (2025)

The Bayesian Geometry of Transformer Attention
par: Agarwal, Naman, et autres
Publié: (2025)

Bottlenecked Transformers: Periodic KV Cache Consolidation for Generalised Reasoning
par: Oomerjee, Adnan, et autres
Publié: (2025)

Mixture of Concept Bottleneck Experts
par: De Santis, Francesco, et autres
Publié: (2026)

Dynamic Graph Information Bottleneck
par: Yuan, Haonan, et autres
Publié: (2024)

Counterfactual Concept Bottleneck Models
par: Dominici, Gabriele, et autres
Publié: (2024)

Object Centric Concept Bottlenecks
par: Steinmann, David, et autres
Publié: (2025)

Learning to Intervene on Concept Bottlenecks
par: Steinmann, David, et autres
Publié: (2023)

Geometric Attention: A Regime-Explicit Operator Semantics for Transformer Attention
par: Freytes, Luis Rosario
Publié: (2026)

XicorAttention: Time Series Transformer Using Attention with Nonlinear Correlation
par: Kimura, Daichi, et autres
Publié: (2025)

Bottleneck Tokens for Unified Multimodal Retrieval
par: Sun, Siyu, et autres
Publié: (2026)

Causally Reliable Concept Bottleneck Models
par: De Felice, Giovanni, et autres
Publié: (2025)

Incremental Residual Concept Bottleneck Models
par: Shang, Chenming, et autres
Publié: (2024)

Towards Reasonable Concept Bottleneck Models
par: Kalampalikis, Nektarios, et autres
Publié: (2025)

Attention Schema-based Attention Control (ASAC): A Cognitive-Inspired Approach for Attention Management in Transformers
par: Saxena, Krati, et autres
Publié: (2025)

Exact Attention Sensitivity and the Geometry of Transformer Stability
par: Emadi, Seyed Morteza
Publié: (2026)

Unveiling and Controlling Anomalous Attention Distribution in Transformers
par: Yan, Ruiqing, et autres
Publié: (2024)

Graph Convolutions Enrich the Self-Attention in Transformers!
par: Choi, Jeongwhan, et autres
Publié: (2023)

Higher-Order Transformers With Kronecker-Structured Attention
par: Omranpour, Soroush, et autres
Publié: (2024)

Expanding Expressivity in Transformer Models with MöbiusAttention
par: Halacheva, Anna-Maria, et autres
Publié: (2024)

Causally-Aware Information Bottleneck for Domain Adaptation
par: Javidian, Mohammad Ali
Publié: (2026)

Discovering the Representation Bottleneck of Graph Neural Networks
par: Wu, Fang, et autres
Publié: (2022)

Bayesian Concept Bottleneck Models with LLM Priors
par: Feng, Jean, et autres
Publié: (2024)

Interpretable Prototype-based Graph Information Bottleneck
par: Seo, Sangwoo, et autres
Publié: (2023)

Do Concept Bottleneck Models Respect Localities?
par: Raman, Naveen, et autres
Publié: (2024)

Glocal Information Bottleneck for Time Series Imputation
par: Yang, Jie, et autres
Publié: (2025)

MUDDFormer: Breaking Residual Bottlenecks in Transformers via Multiway Dynamic Dense Connections
par: Xiao, Da, et autres
Publié: (2025)

Transolver is a Linear Transformer: Revisiting Physics-Attention through the Lens of Linear Attention
par: Hu, Wenjie, et autres
Publié: (2025)

The Alignment Bottleneck
par: Cao, Wenjun
Publié: (2025)

NoiseFormer -- Noise Diffused Symmetric Attention Transformer
par: Kumar, Phani, et autres
Publié: (2026)

Dispatch-Aware Ragged Attention for Pruned Vision Transformers
par: Abdellatif, Seifeldin, et autres
Publié: (2026)

ZeroS: Zero-Sum Linear Attention for Efficient Transformers
par: Lu, Jiecheng, et autres
Publié: (2026)

Echo State Transformer: Attention Over Finite Memories
par: Bendi-Ouis, Yannis, et autres
Publié: (2025)

Strassen Attention, Split VC Dimension and Compositionality in Transformers
par: Kozachinskiy, Alexander, et autres
Publié: (2025)

HATSolver: Learning Groebner Bases with Hierarchical Attention Transformers
par: Malhou, Mohamed, et autres
Publié: (2025)

Learning Concept Bottleneck Models from Mechanistic Explanations
par: De Santis, Antonio, et autres
Publié: (2026)