Cover Image

Boule or Baguette? A Study on Task Topology, Length Generalization, and the Benefit of Reasoning Traces

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tong, William L., Cakar, Ege, Pehlevan, Cengiz
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence Machine Learning Neural and Evolutionary Computing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

MLPs Learn In-Context on Regression and Classification Tasks
by: Tong, William L., et al.
Published: (2024)

Learning richness modulates equality reasoning in neural networks
by: Tong, William L., et al.
Published: (2025)

Provable Benefits of Complex Parameterizations for Structured State Space Models
by: Ran-Milo, Yuval, et al.
Published: (2024)

Multi-Task Optimization over Networks of Tasks
by: Hatzky, Julian, et al.
Published: (2026)

Task and Explanation Network
by: Sipper, Moshe
Published: (2024)

Large Language Model as Meta-Surrogate for Data-Driven Many-Task Optimization: A Proof-of-Principle Study
by: Zhang, Xian-Rong, et al.
Published: (2025)

Instance-Conditioned Adaptation for Large-scale Generalization of Neural Routing Solver
by: Zhou, Changliang, et al.
Published: (2024)

Discovering alternative solutions beyond the simplicity bias in recurrent neural networks
by: Qian, William, et al.
Published: (2025)

Multi-scale Topology Optimization using Neural Networks
by: Chen, Hongrui, et al.
Published: (2024)

Neural Interpretable Reasoning
by: Barbiero, Pietro, et al.
Published: (2025)

Correlative Information Maximization: A Biologically Plausible Approach to Supervised Deep Neural Networks without Weight Symmetry
by: Bozkurt, Bariscan, et al.
Published: (2023)

t-DGR: A Trajectory-Based Deep Generative Replay Method for Continual Learning in Decision Making
by: Yue, William, et al.
Published: (2024)

Task-free Adaptive Meta Black-box Optimization
by: Wang, Chao, et al.
Published: (2026)

CantorNet: A Sandbox for Testing Geometrical and Topological Complexity Measures
by: Lewandowski, Michal, et al.
Published: (2024)

Interpretable Neural-Symbolic Concept Reasoning
by: Barbiero, Pietro, et al.
Published: (2023)

TACOS: Task Agnostic Continual Learning in Spiking Neural Networks
by: Soures, Nicholas, et al.
Published: (2024)

On the Markov Property of Neural Algorithmic Reasoning: Analyses and Methods
by: Bohde, Montgomery, et al.
Published: (2024)

PropNEAT -- Efficient GPU-Compatible Backpropagation over NeuroEvolutionary Augmenting Topology Networks
by: Merry, Michael, et al.
Published: (2024)

MEL: Efficient Multi-Task Evolutionary Learning for High-Dimensional Feature Selection
by: Wang, Xubin, et al.
Published: (2024)

MTSpark: Enabling Multi-Task Learning with Spiking Neural Networks for Generalist Agents
by: Devkota, Avaneesh, et al.
Published: (2024)

Temporal Spiking Neural Networks with Synaptic Delay for Graph Reasoning
by: Xiao, Mingqing, et al.
Published: (2024)

No One-Size-Fits-All Neurons: Task-based Neurons for Artificial Neural Networks
by: Fan, Feng-Lei, et al.
Published: (2024)

Enabling Robust In-Context Memory and Rapid Task Adaptation in Transformers with Hebbian and Gradient-Based Plasticity
by: Chaudhary, Siddharth
Published: (2025)

A Genetic Algorithm-Based Approach for Automated Optimization of Kolmogorov-Arnold Networks in Classification Tasks
by: Long, Quan, et al.
Published: (2025)

Selective Task offloading for Maximum Inference Accuracy and Energy efficient Real-Time IoT Sensing Systems
by: Sada, Abdelkarim Ben, et al.
Published: (2024)

Flexible Prefrontal Control over Hippocampal Episodic Memory for Goal-Directed Generalization
by: Zheng, Yicong, et al.
Published: (2025)

Position as Probability: Self-Supervised Transformers that Think Past Their Training for Length Extrapolation
by: Lee, Philip Heejun
Published: (2025)

Genetic Generalized Additive Models
by: Shankar, Kaaustaaub, et al.
Published: (2026)

Feedback Favors the Generalization of Neural ODEs
by: Jia, Jindou, et al.
Published: (2024)

Scalable Multi-Task Learning through Spiking Neural Networks with Adaptive Task-Switching Policy for Intelligent Autonomous Agents
by: Putra, Rachmad Vidya Wicaksana, et al.
Published: (2025)

E(n) Equivariant Topological Neural Networks
by: Battiloro, Claudio, et al.
Published: (2024)

Structure as Computation: Developmental Generation of Minimal Neural Circuits
by: Zhou, Duan
Published: (2026)

General-Purpose In-Context Learning by Meta-Learning Transformers
by: Kirsch, Louis, et al.
Published: (2022)

Evolution Meets Diffusion: Efficient Neural Architecture Generation
by: Zhou, Bingye, et al.
Published: (2025)

A Theory of Relation Learning and Cross-domain Generalization
by: Doumas, Leonidas A. A., et al.
Published: (2019)

DGPO: RL-Steered Graph Diffusion for Neural Architecture Generation
by: Liuliakov, Aleksei, et al.
Published: (2026)

Generalized Population-Based Training for Hyperparameter Optimization in Reinforcement Learning
by: Bai, Hui, et al.
Published: (2024)

Large Language Models as In-context AI Generators for Quality-Diversity
by: Lim, Bryan, et al.
Published: (2024)

Deep ARTMAP: Generalized Hierarchical Learning with Adaptive Resonance Theory
by: Melton, Niklas M., et al.
Published: (2025)

Enhancing Genetic Algorithms with Graph Neural Networks: A Timetabling Case Study
by: Cornei, Laura-Maria, et al.
Published: (2026)