:: Library Catalog

Imagen de Portada

Guardado en:

Detalles Bibliográficos
Autores principales:	Piotrowski, Mateusz, Riechers, Paul M., Filan, Daniel, Shai, Adam S.
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	https://arxiv.org/abs/2502.01954
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Neural networks leverage nominally quantum and post-quantum representations
por: Riechers, Paul M., et al.
Publicado: (2025)

Transformers represent belief state geometry in their residual stream
por: Shai, Adam S., et al.
Publicado: (2024)

Rank-1 LoRAs Encode Interpretable Reasoning Signals
por: Ward, Jake, et al.
Publicado: (2025)

Next-token pretraining implies in-context learning
por: Riechers, Paul M., et al.
Publicado: (2025)

Transformers learn factored representations
por: Shai, Adam, et al.
Publicado: (2026)

Geometry and Dynamics of LayerNorm
por: Riechers, Paul M.
Publicado: (2024)

In-context learning agents are asymmetric belief updaters
por: Schubert, Johannes A., et al.
Publicado: (2024)

Positive concave deep equilibrium models
por: Gabor, Mateusz, et al.
Publicado: (2024)

Fixed points of nonnegative neural networks
por: Piotrowski, Tomasz J., et al.
Publicado: (2021)

Concept-based explainability for an EEG transformer model
por: Gjølbye, Anders, et al.
Publicado: (2023)

An explainable transformer circuit for compositional generalization
por: Tang, Cheng, et al.
Publicado: (2025)

A multi-criteria approach for selecting an explanation from the set of counterfactuals produced by an ensemble of explainers
por: Stępka, Ignacy, et al.
Publicado: (2024)

Learning the greatest common divisor: explaining transformer predictions
por: Charton, François
Publicado: (2023)

Accurate estimation of feature importance faithfulness for tree models
por: Gajewski, Mateusz, et al.
Publicado: (2024)

survex: an R package for explaining machine learning survival models
por: Spytek, Mikołaj, et al.
Publicado: (2023)

LLMs are not (consistently) Bayesian: Quantifying internal (in)consistencies of LLMs' probabilistic beliefs
por: Chen, Chacha, et al.
Publicado: (2026)

MolPILE -- large-scale, diverse dataset for molecular representation learning
por: Adamczyk, Jakub, et al.
Publicado: (2025)

Balancing Expressivity and Robustness: Constrained Rational Activations for Reinforcement Learning
por: Surdej, Rafał, et al.
Publicado: (2025)

Robust Conformal Prediction Using Privileged Information
por: Feldman, Shai, et al.
Publicado: (2024)

How Many Iterations to Jailbreak? Dynamic Budget Allocation for Multi-Turn LLM Evaluation
por: Feldman, Shai, et al.
Publicado: (2026)

Deep Dreams Are Made of This: Visualizing Monosemantic Features in Diffusion Models
por: Szokalski, Adam, et al.
Publicado: (2026)

Baseflow identification via explainable AI with Kolmogorov-Arnold networks
por: Liu, Chuyang, et al.
Publicado: (2024)

Do LLMs have core beliefs?
por: Sokol, Anna, et al.
Publicado: (2026)

Statistical and structural identifiability in representation learning
por: Nelson, Walter, et al.
Publicado: (2026)

Learning from positive and unlabeled examples -Finite size sample bounds
por: Mansouri, Farnam, et al.
Publicado: (2025)

Online Learning with Improving Agents: Multiclass, Budgeted Agents and Bandit Learners
por: Ashkezari, Sajad, et al.
Publicado: (2026)

Multinomial belief networks for healthcare data
por: Donker, H. C., et al.
Publicado: (2023)

LaB-GATr: geometric algebra transformers for large biomedical surface and volume meshes
por: Suk, Julian, et al.
Publicado: (2024)

DeepShare: Sharing ReLU Across Channels and Layers for Efficient Private Inference
por: Bornfeld, Yonathan, et al.
Publicado: (2025)

Learning to Score
por: Kriger, Yogev, et al.
Publicado: (2025)

Global explainability of a deep abstaining classifier
por: Dhaubhadel, Sayera, et al.
Publicado: (2025)

Contrastive representations of high-dimensional, structured treatments
por: Andreu, Oriol Corcoll, et al.
Publicado: (2024)

VARSHAP: Addressing Global Dependency Problems in Explainable AI with Variance-Based Local Feature Attribution
por: Gajewski, Mateusz, et al.
Publicado: (2025)

Amortized Causal Discovery with Prior-Fitted Networks
por: Sypniewski, Mateusz, et al.
Publicado: (2025)

Conformal Prediction with Corrupted Labels: Uncertain Imputation and Robust Re-weighting
por: Feldman, Shai, et al.
Publicado: (2025)

A Novel Data-Dependent Learning Paradigm for Large Hypothesis Classes
por: Pour, Alireza F., et al.
Publicado: (2025)

Federated style aware transformer aggregation of representations
por: Jeon, Mincheol, et al.
Publicado: (2025)

Evaluating representation learning on the protein structure universe
por: Jamasb, Arian R., et al.
Publicado: (2024)

Universal crystal material property prediction via multi-view geometric fusion in graph transformers
por: Zhang, Liang, et al.
Publicado: (2025)

Characterizing higher-order representations through generative diffusion models explains human decoded neurofeedback performance
por: Asrari, Hojjat Azimi, et al.
Publicado: (2025)