Cover Image

Parity, Sensitivity, and Transformers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kozachinskiy, Alexander, Steifer, Tomasz, Wałȩga, Przemysław
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Simple online learning with consistent oracle
by: Kozachinskiy, Alexander, et al.
Published: (2023)

A completely uniform transformer for parity
by: Kozachinskiy, Alexander, et al.
Published: (2025)

Ehrenfeucht-Haussler Rank and Chain of Thought
by: Barceló, Pablo, et al.
Published: (2025)

Optimal bounds for dissatisfaction in perpetual voting
by: Kozachinskiy, Alexander, et al.
Published: (2024)

Strassen Attention, Split VC Dimension and Compositionality in Transformers
by: Kozachinskiy, Alexander, et al.
Published: (2025)

Lower bounds on transformers with infinite precision
by: Kozachinskiy, Alexander
Published: (2024)

Effective Littlestone Dimension
by: Rose, Valentino Delle, et al.
Published: (2024)

The Logical Expressiveness of Temporal GNNs via Two-Dimensional Product Logics
by: Sälzer, Marco, et al.
Published: (2025)

Provably Shorter Scratchpads in Hybrid DeltaNet-Attention Decoders
by: Steifer, Tomasz
Published: (2026)

Explaining k-Nearest Neighbors: Abductive and Counterfactual Explanations
by: Barceló, Pablo, et al.
Published: (2025)

Message Passing on the Edge: Towards Scalable and Expressive GNNs
by: Barceló, Pablo, et al.
Published: (2025)

Continuity and Isolation Lead to Doubts or Dilemmas in Large Language Models
by: Pasten, Hector, et al.
Published: (2025)

Expressive Power of Temporal Message Passing
by: Wałęga, Przemysław Andrzej, et al.
Published: (2024)

Aggregate-Combine-Readout GNNs Are More Expressive Than Logic C2
by: Hauke, Stan P, et al.
Published: (2025)

Self-Improving AI Agents through Self-Play
by: Chojecki, Przemyslaw
Published: (2025)

Mathematics and Coding are Universal AI Benchmarks
by: Chojecki, Przemyslaw
Published: (2025)

Language Generation: Complexity Barriers and Implications for Learning
by: Arenas, Marcelo, et al.
Published: (2025)

Computable universal online learning
by: Kalociński, Dariusz, et al.
Published: (2025)

Differential Adjusted Parity for Learning Fair Representations
by: Sahyouni, Bucher, et al.
Published: (2025)

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

Model Science: getting serious about verification, explanation and control of AI systems
by: Biecek, Przemyslaw, et al.
Published: (2025)

Beyond Backpropagation: Exploring Innovative Algorithms for Energy-Efficient Deep Neural Network Training
by: Spyra, Przemysław
Published: (2025)

Psychometric Tests for AI Agents and Their Moduli Space
by: Chojecki, Przemyslaw
Published: (2025)

The Geometry of Benchmarks: A New Path Toward AGI
by: Chojecki, Przemyslaw
Published: (2025)

Measuring LLM Sensitivity in Transformer-based Tabular Data Synthesis
by: R, Maria F. Davila, et al.
Published: (2025)

The Correspondence Between Bounded Graph Neural Networks and Fragments of First-Order Logic
by: Grau, Bernardo Cuenca, et al.
Published: (2025)

Attributions All the Way Down? The Metagame of Interpretability
by: Baniecki, Hubert, et al.
Published: (2026)

Exploring Local Explanations of Nonlinear Models Using Animated Linear Projections
by: Spyrison, Nicholas, et al.
Published: (2022)

Cumulative Utility Parity for Fair Federated Learning under Intermittent Client Participation
by: Behfar, Stefan, et al.
Published: (2026)

Decoupling Positional and Symbolic Attention Behavior in Transformers
by: Urrutia, Felipe, et al.
Published: (2025)

A Cost-Sensitive Transformer Model for Prognostics Under Highly Imbalanced Industrial Data
by: Beikmohammadi, Ali, et al.
Published: (2024)

Sensitivity-Positional Co-Localization in GQA Transformers
by: Rao, Manoj Chandrashekar
Published: (2026)

REBEL: Hidden Knowledge Recovery via Evolutionary-Based Evaluation Loop
by: Rybak, Patryk, et al.
Published: (2026)

Position: Explain to Question not to Justify
by: Biecek, Przemyslaw, et al.
Published: (2024)

The Dragon Hatchling: The Missing Link between the Transformer and Models of the Brain
by: Kosowski, Adrian, et al.
Published: (2025)

On the Structural Non-Preservation of Epistemic Behaviour under Policy Transformation
by: Galozy, Alexander
Published: (2026)

Auditing Sybil: Explaining Deep Lung Cancer Risk Prediction Through Generative Interventional Attributions
by: Sobieski, Bartlomiej, et al.
Published: (2026)

A KL Lens on Quantization: Fast, Forward-Only Sensitivity for Mixed-Precision SSM-Transformer Models
by: Kong, Jason, et al.
Published: (2026)

HKAN: Hierarchical Kolmogorov-Arnold Network without Backpropagation
by: Dudek, Grzegorz, et al.
Published: (2025)

Transformers Learn Low Sensitivity Functions: Investigations and Implications
by: Vasudeva, Bhavya, et al.
Published: (2024)