Copertina

Transformer Is Inherently a Causal Learner

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wang, Xinyue, Wang, Stephen, Huang, Biwei
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

A Fast Kernel-based Conditional Independence test with Application to Causal Discovery
di: Schacht, Oliver, et al.
Pubblicazione: (2025)

Modeling Unseen Environments with Language-guided Composable Causal Components in Reinforcement Learning
di: Wang, Xinyue, et al.
Pubblicazione: (2025)

Boosting Efficiency in Task-Agnostic Exploration through Causal Knowledge
di: Yang, Yupei, et al.
Pubblicazione: (2024)

Hybrid Self-evolving Structured Memory for GUI Agents
di: Zhu, Sibo, et al.
Pubblicazione: (2026)

Federated Causal Discovery from Heterogeneous Data
di: Li, Loka, et al.
Pubblicazione: (2024)

Causal Learner: A Toolbox for Causal Structure and Markov Blanket Learning
di: Ling, Zhaolong, et al.
Pubblicazione: (2021)

Emerging Synergies in Causality and Deep Generative Models: A Survey
di: Zhou, Guanglin, et al.
Pubblicazione: (2023)

Generalized Independent Noise Condition for Estimating Causal Structure with Latent Variables
di: Xie, Feng, et al.
Pubblicazione: (2023)

VCformer: Variable Correlation Transformer with Inherent Lagged Correlation for Multivariate Time Series Forecasting
di: Yang, Yingnan, et al.
Pubblicazione: (2024)

Large Transformers are Better EEG Learners
di: Wang, Bingxin, et al.
Pubblicazione: (2023)

Hierarchical Transformers are Efficient Meta-Reinforcement Learners
di: Shala, Gresa, et al.
Pubblicazione: (2024)

Cooperative Knowledge Distillation: A Learner Agnostic Approach
di: Livanos, Michael, et al.
Pubblicazione: (2024)

Causality-Aware Transformer Networks for Robotic Navigation
di: Wang, Ruoyu, et al.
Pubblicazione: (2024)

Transformers as Multi-task Learners: Decoupling Features in Hidden Markov Models
di: Hao, Yifan, et al.
Pubblicazione: (2025)

Ability Transfer and Recovery via Modularized Parameters Localization
di: Jin, Songyao, et al.
Pubblicazione: (2026)

Explanation Beyond Intuition: A Testable Criterion for Inherent Explainability
di: Merry, Michael, et al.
Pubblicazione: (2025)

B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable
di: Arya, Shreyash, et al.
Pubblicazione: (2024)

Inherently Interpretable Time Series Classification via Multiple Instance Learning
di: Early, Joseph, et al.
Pubblicazione: (2023)

Kolmogorov-Arnold Networks for Time Series Granger Causality Inference
di: Liu, Meiliang, et al.
Pubblicazione: (2025)

Spectral Clustering for Crowdsourcing with Inherently Distinct Task Types
di: Mandal, Saptarshi, et al.
Pubblicazione: (2023)

Graph Neural Network Causal Explanation via Neural Causal Models
di: Behnam, Arman, et al.
Pubblicazione: (2024)

DeepDefense: Layer-Wise Gradient-Feature Alignment for Building Robust Neural Networks
di: Lin, Ci, et al.
Pubblicazione: (2025)

Robust Bidirectional Associative Memory via Regularization Inspired by the Subspace Rotation Algorithm
di: Lin, Ci, et al.
Pubblicazione: (2025)

Towards General Continuous Memory for Vision-Language Models
di: Wu, Wenyi, et al.
Pubblicazione: (2025)

The Role of Inherent Bellman Error in Offline Reinforcement Learning with Linear Function Approximation
di: Golowich, Noah, et al.
Pubblicazione: (2024)

Planner Matters! An Efficient and Unbalanced Multi-agent Collaboration Framework for Long-horizon Planning
di: Wu, Wenyi, et al.
Pubblicazione: (2026)

Vintix II: Decision Pre-Trained Transformer is a Scalable In-Context Reinforcement Learner
di: Polubarov, Andrei, et al.
Pubblicazione: (2026)

Learning Discrete Concepts in Latent Hierarchical Models
di: Kong, Lingjing, et al.
Pubblicazione: (2024)

Collaborative Cognitive Diagnosis with Disentangled Representation Learning for Learner Modeling
di: Gao, Weibo, et al.
Pubblicazione: (2024)

A Lightweight Gradient-based Causal Discovery Framework with Applications to Complex Industrial Processes
di: Liu, Meiliang, et al.
Pubblicazione: (2025)

Revisiting Transformer Layer Parameterization Through Causal Energy Minimization
di: Xu, Jin, et al.
Pubblicazione: (2026)

TTCD:Transformer Integrated Temporal Causal Discovery from Non-Stationary Time Series Data
di: Faruque, Omar, et al.
Pubblicazione: (2026)

Large Language Models are Effective Priors for Causal Graph Discovery
di: Darvariu, Victor-Alexandru, et al.
Pubblicazione: (2024)

Nonlinearity, Feedback and Uniform Consistency in Causal Structural Learning
di: Wang, Shuyan
Pubblicazione: (2023)

Agentic Learner with Grow-and-Refine Multimodal Semantic Memory
di: Bo, Weihao, et al.
Pubblicazione: (2025)

Touch in the Wild: Learning Fine-Grained Manipulation with a Portable Visuo-Tactile Gripper
di: Zhu, Xinyue, et al.
Pubblicazione: (2025)

Test Time Training for Supervised Causal Learning
di: Deng, Zizhen, et al.
Pubblicazione: (2026)

Logic Synthesis Optimization with Predictive Self-Supervision via Causal Transformers
di: Karimi, Raika, et al.
Pubblicazione: (2024)

Causal Algorithmic Recourse: Foundations and Methods
di: Plecko, Drago, et al.
Pubblicazione: (2026)

Tree Search in DAG Space with Model-based Reinforcement Learning for Causal Discovery
di: Darvariu, Victor-Alexandru, et al.
Pubblicazione: (2023)