Cover Image

Out-of-distribution generalisation is hard: evidence from ARC-like tasks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Dimitriadis, George, Samothrakis, Spyridon
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A Research Agenda for Usability and Generalisation in Reinforcement Learning
by: Soemers, Dennis J. N. J., et al.
Published: (2024)

ARC-RL: A Reinforcement Learning Playground Inspired by ARC Raiders
by: Romeo, Carlo, et al.
Published: (2026)

The role of positional encodings in the ARC benchmark
by: Costa, Guilherme H. Bandeira, et al.
Published: (2025)

Accuracy on the wrong line: On the pitfalls of noisy data for out-of-distribution generalisation
by: Sanyal, Amartya, et al.
Published: (2024)

The Challenges of Hyperparameter Tuning for Accurate Causal Effect Estimation
by: Machlanski, Damian, et al.
Published: (2023)

Robustness of Algorithms for Causal Structure Learning to Hyperparameter Choice
by: Machlanski, Damian, et al.
Published: (2023)

Improving the classification of extreme classes by means of loss regularisation and generalised beta distributions
by: Vargas, Víctor Manuel, et al.
Published: (2024)

Multi-Perspective Transformers in ARC-AGI-2 Challenge
by: Talley, Caleb, et al.
Published: (2026)

ARC-TGI: Human-Validated Task Generators with Reasoning Chain Templates for ARC-AGI
by: Lehmann, Jens, et al.
Published: (2026)

ARC: Leveraging Compositional Representations for Cross-Problem Learning on VRPs
by: Jeong, Han-Seul, et al.
Published: (2025)

Capturing Sparks of Abstraction for the ARC Challenge
by: Andrews, Martin
Published: (2024)

Neural Coherence : Find higher performance to out-of-distribution tasks from few samples
by: Guiroy, Simon, et al.
Published: (2025)

ARC-GEN: A Mimetic Procedural Benchmark Generator for the Abstraction and Reasoning Corpus
by: Moffitt, Michael D.
Published: (2025)

Don't throw the baby out with the bathwater: How and why deep learning for ARC
by: Cole, Jack, et al.
Published: (2025)

Extending confidence calibration to generalised measures of variation
by: Thompson, Andrew, et al.
Published: (2026)

Bounded and Uniform Energy-based Out-of-distribution Detection for Graphs
by: Yang, Shenzhi, et al.
Published: (2025)

Bridging Multicalibration and Out-of-distribution Generalization Beyond Covariate Shift
by: Wu, Jiayun, et al.
Published: (2024)

Can In-context Learning Really Generalize to Out-of-distribution Tasks?
by: Wang, Qixun, et al.
Published: (2024)

Games of Knightian Uncertainty as AGI testbeds
by: Samothrakis, Spyridon, et al.
Published: (2024)

JaxARC: A High-Performance JAX-based Environment for Abstraction and Reasoning Research
by: Aadam, et al.
Published: (2026)

CausalARC: Abstract Reasoning with Causal World Models
by: Maasch, Jacqueline, et al.
Published: (2025)

ARC Is a Vision Problem!
by: Hu, Keya, et al.
Published: (2025)

Language models show human-like content effects on reasoning tasks
by: Dasgupta, Ishita, et al.
Published: (2022)

A Survey of Out-of-distribution Generalization for Graph Machine Learning from a Causal View
by: Ma, Jing
Published: (2024)

Multi-task Domain Adaptation for Computation Offloading in Edge-intelligence Networks
by: Han, Runxin, et al.
Published: (2025)

Tiny Recursive Models on ARC-AGI-1: Inductive Biases, Identity Conditioning, and Test-Time Compute
by: Roye-Azar, Antonio, et al.
Published: (2025)

Towards Efficient Neurally-Guided Program Induction for ARC-AGI
by: Ouellette, Simon
Published: (2024)

Product of Experts with LLMs: Boosting Performance on ARC Is a Matter of Perspective
by: Franzen, Daniel, et al.
Published: (2025)

Improving generalisability of 3D binding affinity models in low data regimes
by: Buhmann, Julia, et al.
Published: (2024)

Dens-PU: PU Learning with Density-Based Positive Labeled Augmentation
by: Sevetlidis, Vasileios, et al.
Published: (2023)

Input-Specific and Universal Adversarial Attack Generation for Spiking Neural Networks in the Spiking Domain
by: Raptis, Spyridon, et al.
Published: (2025)

Dropout MPC: An Ensemble Neural MPC Approach for Systems with Learned Dynamics
by: Syntakas, Spyridon, et al.
Published: (2024)

Data distribution impacts the performance and generalisability of contrastive learning-based foundation models of electrocardiograms
by: Khattak, Gul Rukh, et al.
Published: (2025)

Small transformer architectures for task switching
by: Gros, Claudius
Published: (2025)

DNN-GDITD: Out-of-distribution detection via Deep Neural Network based Gaussian Descriptor for Imbalanced Tabular Data
by: Chudasama, Priyanka, et al.
Published: (2024)

Routing-Based Continual Learning for Multimodal Large Language Models
by: Mohta, Jay, et al.
Published: (2025)

Negative as Positive: Enhancing Out-of-distribution Generalization for Graph Contrastive Learning
by: Wang, Zixu, et al.
Published: (2024)

Out-of-distribution Reject Option Method for Dataset Shift Problem in Early Disease Onset Prediction
by: Tosaki, Taisei, et al.
Published: (2024)

Mixture of Experts based Multi-task Supervise Learning from Crowds
by: Han, Tao, et al.
Published: (2024)

Auxiliary task discovery through generate-and-test
by: Rafiee, Banafsheh, et al.
Published: (2022)