Cover Image

Low-Dimensional Execution Manifolds in Transformer Learning Dynamics: Evidence from Modular Arithmetic Tasks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Xu, Yongzhong
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence I.2.6
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Shattered Compositionality: Counterintuitive Learning Dynamics of Transformers for Arithmetic
by: Zhao, Xingyu, et al.
Published: (2026)

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

Deep Memory Search: A Metaheuristic Approach for Optimizing Heuristic Search
by: Hedar, Abdel-Rahman, et al.
Published: (2024)

Multi-Task Reinforcement Learning with Language-Encoded Gated Policy Networks
by: Arora, Rushiv
Published: (2025)

DYNAMITE: Dynamic Interplay of Mini-Batch Size and Aggregation Frequency for Federated Learning with Static and Streaming Dataset
by: Liu, Weijie, et al.
Published: (2023)

A Simple Generalisation of the Implicit Dynamics of In-Context Learning
by: Innocenti, Francesco, et al.
Published: (2025)

A Geometric Perspective for High-Dimensional Multiplex Graphs
by: Abdous, Kamel, et al.
Published: (2025)

Not All Transitions Matter: Evidence from PPO
by: Basnet, Ajhesh
Published: (2026)

SourceSplice: Source Selection for Machine Learning Tasks
by: Singh, Ambarish, et al.
Published: (2025)

Manipulating 3D Molecules in a Fixed-Dimensional E(3)-Equivariant Latent Space
by: Chen, Zitao, et al.
Published: (2025)

Path-Coupled Bellman Flows for Distributional Reinforcement Learning
by: Xu, Boyang, et al.
Published: (2026)

Evidential Deep Active Learning for Semi-Supervised Classification
by: Zhao, Shenkai, et al.
Published: (2025)

Behavior Learning (BL): Learning Hierarchical Optimization Structures from Data
by: Ma, Zhenyao, et al.
Published: (2026)

Superposition Is Not Necessary: A Mechanistic Interpretability Analysis of Transformer Representations for Time Series Forecasting
by: Yıldırım, Alper
Published: (2026)

One Router to Route Them All: Homogeneous Expert Routing for Heterogeneous Graph Transformers
by: Shakirov, Georgiy, et al.
Published: (2025)

TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction
by: Liu, Weijie, et al.
Published: (2025)

DRFormer: Multi-Scale Transformer Utilizing Diverse Receptive Fields for Long Time-Series Forecasting
by: Ding, Ruixin, et al.
Published: (2024)

Dynamics Reveals Structure: Challenging the Linear Propagation Assumption
by: Chang, Hoyeon, et al.
Published: (2026)

TS-ACL: Closed-Form Solution for Time Series-oriented Continual Learning
by: Li, Jiaxu, et al.
Published: (2024)

Machine Learning vs Deep Learning: The Generalization Problem
by: Bay, Yong Yi, et al.
Published: (2024)

Expressive Value Learning for Scalable Offline Reinforcement Learning
by: Espinosa-Dice, Nicolas, et al.
Published: (2025)

SMOSE: Sparse Mixture of Shallow Experts for Interpretable Reinforcement Learning in Continuous Control Tasks
by: Vincze, Mátyás, et al.
Published: (2024)

EEG Sleep Stage Classification with Continuous Wavelet Transform and Deep Learning
by: Gashti, Mehdi Zekriyapanah, et al.
Published: (2025)

Bounded Ratio Reinforcement Learning
by: Ao, Yunke, et al.
Published: (2026)

Why Online Reinforcement Learning is Causal
by: Schulte, Oliver, et al.
Published: (2024)

CircuitProbe: Predicting Reasoning Circuits in Transformers via Stability Zone Detection
by: Panuganti, Rajkiran
Published: (2026)

Understanding Goal Generalisation in Sequential Reinforcement Learning
by: Brown, Jason Ross, et al.
Published: (2026)

DataRater: Meta-Learned Dataset Curation
by: Calian, Dan A., et al.
Published: (2025)

Extrinsicaly Rewarded Soft Q Imitation Learning with Discriminator
by: Furuyama, Ryoma, et al.
Published: (2024)

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

Integrating Causality with Neurochaos Learning: Proposed Approach and Research Agenda
by: Narendra, Nanjangud C., et al.
Published: (2025)

The Readout Shortcut: Positional Number Copying Dominates Arithmetic CoT Readout in Small Language Models
by: Liu, Ming
Published: (2026)

Load and Renewable Energy Forecasting Using Deep Learning for Grid Stability
by: Sarkar, Kamal
Published: (2025)

Learning Agents With Prioritization and Parameter Noise in Continuous State and Action Space
by: Mangannavar, Rajesh, et al.
Published: (2024)

What changes after deployment? A survey on On-device Learning in TinyML
by: Pavan, Massimo, et al.
Published: (2026)

FreRA: A Frequency-Refined Augmentation for Contrastive Learning on Time Series Classification
by: Tian, Tian, et al.
Published: (2025)

A Practical Approach to using Supervised Machine Learning Models to Classify Aviation Safety Occurrences
by: Siow, Bryan Y.
Published: (2025)

DELTA: Variational Disentangled Learning for Privacy-Preserving Data Reprogramming
by: Malarkkan, Arun Vignesh, et al.
Published: (2025)

What Do World Models Learn in RL? Probing Latent Representations in Learned Environment Simulators
by: Zhang, Xinyu
Published: (2026)

Working Paper: Active Causal Structure Learning with Latent Variables: Towards Learning to Detour in Autonomous Robots
by: Riscos, Pablo de los, et al.
Published: (2024)