Image de couverture de livre

Self-Attention as Transport: Limits of Symmetric Spectral Diagnostics

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Dahlem, Dominik, Maniloff, Diego, Misiura, Mac
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Computation and Language 68T07, 68T50, 15A18, 05C50
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Measuring Alignment-Induced Activation Shifts Correctly: A Template-Controlled Difference-in-Differences Protocol
par: Nakamura, Yuki
Publié: (2026)

OptPO: Optimal Rollout Allocation for Test-time Policy Optimization
par: Wang, Youkang, et autres
Publié: (2025)

Uncertainty Estimation and Quantification for LLMs: A Simple Supervised Approach
par: Liu, Linyu, et autres
Publié: (2024)

The Origin of Self-Attention: Pairwise Affinity Matrices in Feature Selection and the Emergence of Self-Attention
par: Roffo, Giorgio
Publié: (2025)

A Language Model-Driven Semi-Supervised Ensemble Framework for Illicit Market Detection Across Deep/Dark Web and Social Platforms
par: Yazdanjue, Navid, et autres
Publié: (2025)

Clustering in pure-attention hardmax transformers and its role in sentiment analysis
par: Alcalde, Albert, et autres
Publié: (2024)

Mechanistic Analysis of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning
par: Imanov, Olaf Yunus Laitinen
Publié: (2026)

Latent Object Permanence: Topological Phase Transitions, Free-Energy Principles, and Renormalization Group Flows in Deep Transformer Manifolds
par: Alpay, Faruk, et autres
Publié: (2026)

Inference acceleration for large language models using "stairs" assisted greedy generation
par: Grigaliūnas, Domas, et autres
Publié: (2024)

Strategic Doctrine Language Models (sdLM): A Learning-System Framework for Doctrinal Consistency and Geopolitical Forecasting
par: Imanov, Olaf Yunus Laitinen, et autres
Publié: (2026)

Pay Attention to What You Need
par: Gao, Yifei, et autres
Publié: (2023)

Hidden Coalitions in Multi-Agent AI: A Spectral Diagnostic from Internal Representations
par: Berg, Cameron, et autres
Publié: (2026)

Unraveling Media Perspectives: A Comprehensive Methodology Combining Large Language Models, Topic Modeling, Sentiment Analysis, and Ontology Learning to Analyse Media Bias
par: Jähde, Orlando, et autres
Publié: (2025)

Cache-to-Cache: Direct Semantic Communication Between Large Language Models
par: Fu, Tianyu, et autres
Publié: (2025)

HEFT: A Coarse-to-Fine Hierarchy for Enhancing the Efficiency and Accuracy of Language Model Reasoning
par: Hill, Brennen
Publié: (2025)

Evaluating Embedding Generalization: How LLMs, LoRA, and SLERP Shape Representational Geometry
par: Kabane, Siyaxolisa
Publié: (2025)

mHC-SSM: Manifold-Constrained Hyper-Connections for State Space Language Models with Stream-Specialized Adapters
par: Mutlu, Abdulvahap, et autres
Publié: (2026)

Extracting Sentence Embeddings from Pretrained Transformer Models
par: Stankevičius, Lukas, et autres
Publié: (2024)

Sentiment Analysis of Lithuanian Online Reviews Using Large Language Models
par: Vileikytė, Brigita, et autres
Publié: (2024)

ReFactor GNNs: Revisiting Factorisation-based Models from a Message-Passing Perspective
par: Chen, Yihong, et autres
Publié: (2022)

Parameter-Efficient Transformer Embeddings
par: Ndubuaku, Henry, et autres
Publié: (2025)

DYNAMAX: Dynamic computing for Transformers and Mamba based architectures
par: Nogales, Miguel, et autres
Publié: (2025)

OPENXRD: A Comprehensive Benchmark Framework for LLM/MLLM XRD Question Answering
par: Vosoughi, Ali, et autres
Publié: (2025)

Bridging the Language Gap: Enhancing Multilingual Prompt-Based Code Generation in LLMs via Zero-Shot Cross-Lingual Transfer
par: Li, Mingda, et autres
Publié: (2024)

SAGE: Sign-Adaptive Gradient for Memory-Efficient LLM Optimization
par: Lee, Wooin, et autres
Publié: (2026)

Retrieval-augmented code completion for local projects using large language models
par: Hostnik, Marko, et autres
Publié: (2024)

Exact Sequence Interpolation with Transformers
par: Alcalde, Albert, et autres
Publié: (2025)

On the existence of minimizers in shallow residual ReLU neural network optimization landscapes
par: Dereich, Steffen, et autres
Publié: (2023)

On the existence of optimal shallow feedforward networks with ReLU activation
par: Dereich, Steffen, et autres
Publié: (2023)

Improving Recursive Transformers with Mixture of LoRAs
par: Nouriborji, Mohammadmahdi, et autres
Publié: (2025)

Surfing the modeling of PoS taggers in low-resource scenarios
par: Ferro, Manuel Vilares, et autres
Publié: (2024)

Enhancing Ultra-Low-Bit Quantization of Large Language Models Through Saliency-Aware Partial Retraining
par: Cao, Deyu, et autres
Publié: (2025)

Forging GEMs: Advancing Greek NLP through Quality-Based Corpus Curation
par: Apostolopoulou, Alexandra, et autres
Publié: (2025)

PolyTruth: Multilingual Disinformation Detection using Transformer-Based Language Models
par: Gouliev, Zaur, et autres
Publié: (2025)

Empirical analysis of binding precedent efficiency in Brazilian Supreme Court via case classification
par: Tinarrage, Raphaël, et autres
Publié: (2024)

Beyond Long Context: When Semantics Matter More than Tokens
par: Chawdhury, Tarun Kumar, et autres
Publié: (2025)

Smoothed Embeddings for Robust Language Models
par: Hase, Ryo, et autres
Publié: (2025)

LLM-Assisted Crisis Management: Building Advanced LLM Platforms for Effective Emergency Response and Public Collaboration
par: Otal, Hakan T., et autres
Publié: (2024)

Transactional Attention: Semantic Sponsorship for KV-Cache Retention
par: Basu, Abhinaba
Publié: (2026)

Understanding Reinforcement Learning for Model Training, and future directions with GRAPE
par: Patel, Rohit
Publié: (2025)