Image de couverture de livre

Interpretable-by-Design Transformers via Architectural Stream Independence

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Kerce, Clayton, Fox, Alexis
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

The Dual-Stream Transformer: Channelized Architecture for Interpretable Language Modeling
par: Kerce, J. Clayton, et autres
Publié: (2026)

Engineering Verifiable Modularity in Transformers via Per-Layer Supervision
par: Kerce, J. Clayton
Publié: (2026)

Stream separation improves Bregman conditioning in transformers
par: Kerce, James Clayton
Publié: (2026)

GLIDR: Graph-Like Inductive Logic Programming with Differentiable Reasoning
par: Johnson, Blair, et autres
Publié: (2025)

KLAS: Using Similarity to Stitch Neural Networks for Improved Accuracy-Efficiency Tradeoffs
par: Sanyal, Debopam, et autres
Publié: (2026)

Residual Stream Duality in Modern Transformer Architectures
par: Zhang, Yifan
Publié: (2026)

LUMINA: Laplacian-Unifying Mechanism for Interpretable Neurodevelopmental Analysis via Quad-Stream GCN
par: Cha, Minkyung, et autres
Publié: (2026)

Don't Retrain, Align: Adapting Autoregressive LMs to Diffusion LMs via Representation Alignment
par: Peng, Fred Zhangzhi, et autres
Publié: (2026)

WinTSR: A Windowed Temporal Saliency Rescaling Method for Interpreting Time Series Deep Learning Models
par: Islam, Md. Khairul, et autres
Publié: (2024)

SE-VGAE: Unsupervised Disentangled Representation Learning for Interpretable Architectural Layout Design Graph Generation
par: Chen, Jielin, et autres
Publié: (2024)

Understanding Transformer Reasoning Capabilities via Graph Algorithms
par: Sanford, Clayton, et autres
Publié: (2024)

Towards Mechanistic Interpretability of Graph Transformers via Attention Graphs
par: El, Batu, et autres
Publié: (2025)

Transformer Normalisation Layers and the Independence of Semantic Subspaces
par: Menary, Stephen, et autres
Publié: (2024)

Generative Modeling of Networked Time-Series via Transformer Architectures
par: Elnady, Yusuf
Publié: (2025)

On Limitations of the Transformer Architecture
par: Peng, Binghui, et autres
Publié: (2024)

Exploring Diffusion Transformer Designs via Grafting
par: Chandrasegaran, Keshigeyan, et autres
Publié: (2025)

Architecture Determines Observability of Transformers
par: Carmichael, Thomas
Publié: (2026)

Temporal Inductive Logic Reasoning over Hypergraphs
par: Yang, Yuan, et autres
Publié: (2022)

CardioPatternFormer: Pattern-Guided Attention for Interpretable ECG Classification with Transformer Architecture
par: Uğraş, Berat Kutay, et autres
Publié: (2025)

Prototype Transformer: Towards Language Model Architectures Interpretable by Design
par: Yordanov, Yordan, et autres
Publié: (2026)

Finding Clustering Algorithms in the Transformer Architecture
par: Clarkson, Kenneth L., et autres
Publié: (2025)

CoFrNets: Interpretable Neural Architecture Inspired by Continued Fractions
par: Puri, Isha, et autres
Publié: (2025)

Feature Engineering for Agents: An Adaptive Cognitive Architecture for Interpretable ML Monitoring
par: Bravo-Rocca, Gusseppe, et autres
Publié: (2025)

CARL: Causality-guided Architecture Representation Learning for an Interpretable Performance Predictor
par: Ji, Han, et autres
Publié: (2025)

Content-Style Identification via Differential Independence
par: Timilsina, Subash, et autres
Publié: (2026)

Dynamics of the Transformer Residual Stream: Coupling Spectral Geometry to Network Topology
par: Fernando, Jesseba, et autres
Publié: (2026)

A Dual-Stream Physics-Augmented Unsupervised Architecture for Runtime Embedded Vehicle Health Monitoring
par: Spotorno, Enzo Nicolas, et autres
Publié: (2026)

nnterp: A Standardized Interface for Mechanistic Interpretability of Transformers
par: Dumas, Clément
Publié: (2025)

Interpreting Affine Recurrence Learning in GPT-style Transformers
par: Bhargav, Samarth, et autres
Publié: (2024)

Mechanistic Interpretability for Transformer-based Time Series Classification
par: Kalnāre, Matīss, et autres
Publié: (2025)

OT-Transformer: A Continuous-time Transformer Architecture with Optimal Transport Regularization
par: Kan, Kelvin, et autres
Publié: (2025)

Momentum Streams for Optimizer-Inspired Transformers
par: Gai, Jingchu, et autres
Publié: (2026)

Interpreting Time Series Transformer Models and Sensitivity Analysis of Population Age Groups to COVID-19 Infections
par: Islam, Md Khairul, et autres
Publié: (2024)

The Residual Stream Is All You Need: On the Redundancy of the KV Cache in Transformer Inference
par: Qasim, Kaleem Ullah, et autres
Publié: (2026)

Bridging MARL to SARL: An Order-Independent Multi-Agent Transformer via Latent Consensus
par: Zhao, Zijian, et autres
Publié: (2026)

A Survey of Graph Transformers: Architectures, Theories and Applications
par: Yuan, Chaohao, et autres
Publié: (2025)

Safe Transformer: An Explicit Safety Bit For Interpretable And Controllable Alignment
par: Feng, Jingyuan, et autres
Publié: (2026)

Efficient and Interpretable Neural Networks Using Complex Lehmer Transform
par: Ataei, Masoud, et autres
Publié: (2025)

Interpretability by Design for Efficient Multi-Objective Reinforcement Learning
par: Xia, Qiyue, et autres
Publié: (2025)

Neural Approaches to SAT Solving: Design Choices and Interpretability
par: Mojžíšek, David, et autres
Publié: (2025)