Imagen de Portada

ARC-AGI Without Pretraining

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Liao, Isaac, Gu, Albert
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

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

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

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

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

The ARC of Progress towards AGI: A Living Survey of Abstraction and Reasoning
por: Vahdati, Sahar, et al.
Publicado: (2026)

Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI
por: Pourcel, Julien, et al.
Publicado: (2025)

From the Pursuit of Universal AGI Architecture to Systematic Approach to Heterogenous AGI: Addressing Alignment, Energy, & AGI Grand Challenges
por: Kurshan, Eren
Publicado: (2023)

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

A Definition of AGI
por: Hendrycks, Dan, et al.
Publicado: (2025)

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

Scaling Pretrained Representations Enables Label-Free Out-of-Distribution Detection Without Fine-Tuning
por: Barkley, Brett, et al.
Publicado: (2026)

A Coherence-Based Measure of AGI
por: Fourati, Fares
Publicado: (2025)

ARC: A Generalist Graph Anomaly Detector with In-Context Learning
por: Liu, Yixin, et al.
Publicado: (2024)

Inner Loop Inference for Pretrained Transformers: Unlocking Latent Capabilities Without Training
por: Lys, Jonathan, et al.
Publicado: (2026)

ARC-STAR: Auditable Post-Hoc Correction for PDE Foundation Models
por: Li, Chengze, et al.
Publicado: (2026)

Capturing Sparks of Abstraction for the ARC Challenge
por: Andrews, Martin
Publicado: (2024)

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

An Approach to Technical AGI Safety and Security
por: Shah, Rohin, et al.
Publicado: (2025)

Foundations of Artificial Intelligence Frameworks: Notion and Limits of AGI
por: Bui, Khanh Gia
Publicado: (2025)

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

PreAdaptFWI: Pretrained-Based Adaptive Residual Learning for Full-Waveform Inversion Without Dataset Dependency
por: Dong, Xintong, et al.
Publicado: (2025)

Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
por: Dao, Tri, et al.
Publicado: (2024)

Neural Cellular Automata for ARC-AGI
por: Xu, Kevin, et al.
Publicado: (2025)

ARC-AGI-2 Technical Report
por: de Oliveira, Wallyson Lemes, et al.
Publicado: (2026)

Out-of-distribution generalisation is hard: evidence from ARC-like tasks
por: Dimitriadis, George, et al.
Publicado: (2025)

ConceptSearch: Towards Efficient Program Search Using LLMs for Abstraction and Reasoning Corpus (ARC)
por: Singhal, Kartik, et al.
Publicado: (2024)

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

How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression?
por: Wu, Jingfeng, et al.
Publicado: (2023)

The Geometry of Benchmarks: A New Path Toward AGI
por: Chojecki, Przemyslaw
Publicado: (2025)

ADEPT: Continual Pretraining via Adaptive Expansion and Dynamic Decoupled Tuning
por: Zhang, Jinyang, et al.
Publicado: (2025)

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

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

Understanding and Improving Length Generalization in Recurrent Models
por: Ruiz, Ricardo Buitrago, et al.
Publicado: (2025)

TapWeight: Reweighting Pretraining Objectives for Task-Adaptive Pretraining
por: Zhang, Ruiyi, et al.
Publicado: (2024)

Pretrained Multilingual Transformers Reveal Quantitative Distance Between Human Languages
por: Zhao, Yue, et al.
Publicado: (2026)

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

Heuristics and Biases in AI Decision-Making: Implications for Responsible AGI
por: Saeedi, Payam, et al.
Publicado: (2024)

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

EasyARC: Evaluating Vision Language Models on True Visual Reasoning
por: Unsal, Mert, et al.
Publicado: (2025)

Mamba: Linear-Time Sequence Modeling with Selective State Spaces
por: Gu, Albert, et al.
Publicado: (2023)