Copertina

Transformers Use Causal World Models in Maze-Solving Tasks

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Spies, Alex F., Edwards, William, Ivanitskiy, Michael I., Skapars, Adrians, Räuker, Tilman, Inoue, Katsumi, Russo, Alessandra, Shanahan, Murray
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Artificial Intelligence I.2
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Do Linear Probes Generalize Better in Persona Coordinates?
di: Mahadik, Prasad, et al.
Pubblicazione: (2026)

Towards end-to-end ASP computation
di: Sato, Taisuke, et al.
Pubblicazione: (2023)

VITA: Zero-Shot Value Functions via Test-Time Adaptation of Vision-Language Models
di: Ziakas, Christos, et al.
Pubblicazione: (2025)

Was it Slander? Towards Exact Inversion of Generative Language Models
di: Skapars, Adrians, et al.
Pubblicazione: (2024)

GPT, But Backwards: Exactly Inverting Language Model Outputs
di: Skapars, Adrians, et al.
Pubblicazione: (2025)

Exploring the Maze of Multilingual Modeling
di: Nezhad, Sina Bagheri, et al.
Pubblicazione: (2023)

Worst-Case Symbolic Constraints Analysis and Generalisation with Large Language Models
di: Koh, Daniel, et al.
Pubblicazione: (2025)

Tulip Agent -- Enabling LLM-Based Agents to Solve Tasks Using Large Tool Libraries
di: Ocker, Felix, et al.
Pubblicazione: (2024)

Simulation-Based Counterfactual Causal Discovery on Real World Driver Behaviour
di: Howard, Rhys, et al.
Pubblicazione: (2023)

Causal Cartographer: From Mapping to Reasoning Over Counterfactual Worlds
di: Gendron, Gaël, et al.
Pubblicazione: (2025)

Beyond Fixed Tasks: Unsupervised Environment Design for Task-Level Pairs
di: Furelos-Blanco, Daniel, et al.
Pubblicazione: (2025)

R-AIF: Solving Sparse-Reward Robotic Tasks from Pixels with Active Inference and World Models
di: Nguyen, Viet Dung, et al.
Pubblicazione: (2024)

CausalX: Causal Explanations and Block Multilinear Factor Analysis
di: Vasilescu, M. Alex O., et al.
Pubblicazione: (2021)

Box Maze: A Process-Control Architecture for Reliable LLM Reasoning
di: Qiang, Zou
Pubblicazione: (2026)

Can Large Language Models Learn Independent Causal Mechanisms?
di: Gendron, Gaël, et al.
Pubblicazione: (2024)

Causal Deep Learning
di: Vasilescu, M. Alex O.
Pubblicazione: (2023)

SAFLITE: Fuzzing Autonomous Systems via Large Language Models
di: Zhu, Taohong, et al.
Pubblicazione: (2024)

Causal Dimensionality of Transformer Representations: Measurement, Scaling, and Layer Structure
di: Sarkar, Nilesh, et al.
Pubblicazione: (2026)

Inducing Causal World Models in LLMs for Zero-Shot Physical Reasoning
di: Sharma, Aditya, et al.
Pubblicazione: (2025)

A Grover-Based Quantum Algorithm for Solving Perfect Mazes via Fitness-Guided Search
di: Wu, Michelle L.
Pubblicazione: (2025)

Grokking in the Wild: Data Augmentation for Real-World Multi-Hop Reasoning with Transformers
di: Abramov, Roman, et al.
Pubblicazione: (2025)

On Logical Extrapolation for Mazes with Recurrent and Implicit Networks
di: Knutson, Brandon, et al.
Pubblicazione: (2024)

The Impact of Off-Policy Training Data on Probe Generalisation
di: Kirch, Nathalie, et al.
Pubblicazione: (2025)

Solar Forecasting with Causality: A Graph-Transformer Approach to Spatiotemporal Dependencies
di: Niu, Yanan, et al.
Pubblicazione: (2025)

Task-Conditioned Routing Signatures in Sparse Mixture-of-Experts Transformers
di: Avinash, Mynampati Sri Ranganadha
Pubblicazione: (2026)

Robust Domain Generalisation with Causal Invariant Bayesian Neural Networks
di: Gendron, Gaël, et al.
Pubblicazione: (2024)

Solve it with EASE
di: Viktorin, Adam, et al.
Pubblicazione: (2025)

Housing Potential Common Data Model and City Digital Twin
di: Katsumi, Megan, et al.
Pubblicazione: (2026)

In Context Learning with Vision Transformers: Case Study
di: Zhao, Antony, et al.
Pubblicazione: (2025)

COBRA-PPM: A Causal Bayesian Reasoning Architecture Using Probabilistic Programming for Robot Manipulation Under Uncertainty
di: Cannizzaro, Ricardo, et al.
Pubblicazione: (2024)

HCLSM: Hierarchical Causal Latent State Machines for Object-Centric World Modeling
di: Jaber, Jaber, et al.
Pubblicazione: (2026)

Guidelines for External Disturbance Factors in the Use of OCR in Real-World Environments
di: Iwata, Kenji, et al.
Pubblicazione: (2025)

MANGO: Learning Disentangled Image Transformation Manifolds with Grouped Operators
di: Ancelin, Brighton, et al.
Pubblicazione: (2024)

Generative World Models of Tasks: LLM-Driven Hierarchical Scaffolding for Embodied Agents
di: Hill, Brennen
Pubblicazione: (2025)

Task Singular Vectors: Reducing Task Interference in Model Merging
di: Gargiulo, Antonio Andrea, et al.
Pubblicazione: (2024)

APP: Accelerated Path Patching with Task-Specific Pruning
di: Andersen, Frauke, et al.
Pubblicazione: (2025)

Less is More: Learning Graph Tasks with Just LLMs
di: Shirai, Sola, et al.
Pubblicazione: (2025)

Intervening to Learn and Compose Causally Disentangled Representations
di: Markham, Alex, et al.
Pubblicazione: (2025)

Transformer Mechanisms Mimic Frontostriatal Gating Operations When Trained on Human Working Memory Tasks
di: Traylor, Aaron, et al.
Pubblicazione: (2024)

Efficiently Scanning and Resampling Spatio-Temporal Tasks with Irregular Observations
di: Ferenczi, Bryce, et al.
Pubblicazione: (2024)