Image de couverture de livre

Concise One-Layer Transformers Can Do Function Evaluation (Sometimes)

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Strobl, Lena, Angluin, Dana, Frank, Robert
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

What Formal Languages Can Transformers Express? A Survey
par: Strobl, Lena, et autres
Publié: (2023)

Transformers as Transducers
par: Strobl, Lena, et autres
Publié: (2024)

Simulating Hard Attention Using Soft Attention
par: Yang, Andy, et autres
Publié: (2024)

Constructing Concise Characteristic Samples for Acceptors of Omega Regular Languages
par: Angluin, Dana, et autres
Publié: (2022)

Masked Hard-Attention Transformers Recognize Exactly the Star-Free Languages
par: Yang, Andy, et autres
Publié: (2023)

Transformers Can Do Bayesian Inference
par: Müller, Samuel, et autres
Publié: (2021)

Can GNNs Learn Link Heuristics? A Concise Review and Evaluation of Link Prediction Methods
par: Liang, Shuming, et autres
Publié: (2024)

Reasoning Models Sometimes Output Illegible Chains of Thought
par: Jose, Arun
Publié: (2025)

Can Transformers Do Enumerative Geometry?
par: Hashemi, Baran, et autres
Publié: (2024)

Why Less is More (Sometimes): A Theory of Data Curation
par: Dohmatob, Elvis, et autres
Publié: (2025)

Transformers Can Do Arithmetic with the Right Embeddings
par: McLeish, Sean, et autres
Publié: (2024)

A Single-Layer Model Can Do Language Modeling
par: Wang, Zanmin
Publié: (2026)

(Sometimes) Less is More: Mitigating the Complexity of Rule-based Representation for Interpretable Classification
par: Bergamin, Luca, et autres
Publié: (2025)

Provable Knowledge Acquisition and Extraction in One-Layer Transformers
par: Xu, Ruichen, et autres
Publié: (2025)

What One Cannot, Two Can: Two-Layer Transformers Provably Represent Induction Heads on Any-Order Markov Chains
par: Ekbote, Chanakya, et autres
Publié: (2025)

Learning Causally Predictable Outcomes from Psychiatric Longitudinal Data
par: Strobl, Eric V.
Publié: (2025)

Global Interpretability via Automated Preprocessing: A Framework Inspired by Psychiatric Questionnaires
par: Strobl, Eric V.
Publié: (2026)

One-Layer Transformer Provably Learns One-Nearest Neighbor In Context
par: Li, Zihao, et autres
Publié: (2024)

Probabilistic Graphical Models: A Concise Tutorial
par: Maasch, Jacqueline, et autres
Publié: (2025)

Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
par: Kim, Jeonghye, et autres
Publié: (2026)

Sometimes I am a Tree: Data Drives Unstable Hierarchical Generalization
par: Qin, Tian, et autres
Publié: (2024)

Alternative Loss Function in Evaluation of Transformer Models
par: Michańków, Jakub, et autres
Publié: (2025)

LayerMatch: Do Pseudo-labels Benefit All Layers?
par: Liang, Chaoqi, et autres
Publié: (2024)

Diversity of Transformer Layers: One Aspect of Parameter Scaling Laws
par: Kamigaito, Hidetaka, et autres
Publié: (2025)

A Concise Review of Hallucinations in LLMs and their Mitigation
par: Pulkundwar, Parth, et autres
Publié: (2025)

Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time
par: Liang, Yingyu, et autres
Publié: (2024)

Probabilistic Robustness in Deep Learning: A Concise yet Comprehensive Guide
par: Zhao, Xingyu
Publié: (2025)

mlr3summary: Concise and interpretable summaries for machine learning models
par: Dandl, Susanne, et autres
Publié: (2024)

Adaptation Odyssey in LLMs: Why Does Additional Pretraining Sometimes Fail to Improve?
par: Öncel, Fırat, et autres
Publié: (2024)

Model Checking for Reinforcement Learning in Autonomous Driving: One Can Do More Than You Think!
par: Gu, Rong
Publié: (2024)

HomeAdam: Adam and AdamW Algorithms Sometimes Go Home to Obtain Better Provable Generalization
par: Huang, Feihu, et autres
Publié: (2026)

SIMformer: Single-Layer Vanilla Transformer Can Learn Free-Space Trajectory Similarity
par: Yang, Chuang, et autres
Publié: (2024)

Tabular Foundation Models Can Do Survival Analysis
par: Kim, Da In, et autres
Publié: (2026)

FairPFN: Transformers Can do Counterfactual Fairness
par: Robertson, Jake, et autres
Publié: (2024)

Just One Layer Norm Guarantees Stable Extrapolation
par: Ziomek, Juliusz, et autres
Publié: (2025)

Metacognitive Reuse: Turning Recurring LLM Reasoning Into Concise Behaviors
par: Didolkar, Aniket, et autres
Publié: (2025)

A Concise Mathematical Description of Active Inference in Discrete Time
par: van Oostrum, Jesse, et autres
Publié: (2024)

MAUNet-Light: A Concise MAUNet Architecture for Bias Correction and Downscaling of Precipitation Estimates
par: Sharma, Sumanta Chandra Mishra, et autres
Publié: (2026)

Can Transformers Smell Like Humans?
par: Taleb, Farzaneh, et autres
Publié: (2024)

ConciseRL: Conciseness-Guided Reinforcement Learning for Efficient Reasoning Models
par: Dumitru, Razvan-Gabriel, et autres
Publié: (2025)