Cover Image

Assign and Add: A Mechanistic Study of Compositional Arithmetic

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Exoo, Brady, Bietti, Alberto, Sous, John
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Distributional Associations vs In-Context Reasoning: A Study of Feed-forward and Attention Layers
by: Chen, Lei, et al.
Published: (2024)

Asymmetric Scaling Laws from Sparse Features
by: Sous, John, et al.
Published: (2026)

Spectral Lens: Activation and Gradient Spectra as Diagnostics of LLM Optimization
by: Liu, Andy Zeyi, et al.
Published: (2026)

Latent Algorithmic Structure Precedes Grokking: A Mechanistic Study of ReLU MLPs on Modular Arithmetic
by: Swaroop, Anand
Published: (2026)

Understanding the Mechanisms of Fast Hyperparameter Transfer
by: Ghosh, Nikhil, et al.
Published: (2025)

Learning Associative Memories with Gradient Descent
by: Cabannes, Vivien, et al.
Published: (2024)

Contextual Counting: A Mechanistic Study of Transformers on a Quantitative Task
by: Golkar, Siavash, et al.
Published: (2024)

Learning Compositional Functions with Transformers from Easy-to-Hard Data
by: Wang, Zixuan, et al.
Published: (2025)

Multimodal Alignment and Preference Optimization for Zero-Shot Conditional RNA Generation
by: Klypa, Roman, et al.
Published: (2026)

BAnG: Bidirectional Anchored Generation for Conditional RNA Design
by: Klypa, Roman, et al.
Published: (2025)

Level Set Teleportation: An Optimization Perspective
by: Mishkin, Aaron, et al.
Published: (2024)

Learning to Recall with Transformers Beyond Orthogonal Embeddings
by: Vural, Nuri Mert, et al.
Published: (2026)

From Mechanistic to Compositional Interpretability
by: Gauderis, Ward, et al.
Published: (2026)

Understanding Factual Recall in Transformers via Associative Memories
by: Nichani, Eshaan, et al.
Published: (2024)

In-context denoising with one-layer transformers: connections between attention and associative memory retrieval
by: Smart, Matthew, et al.
Published: (2025)

(Im)possibility of Automated Hallucination Detection in Large Language Models
by: Karbasi, Amin, et al.
Published: (2025)

Add and Thin: Diffusion for Temporal Point Processes
by: Lüdke, David, et al.
Published: (2023)

ShiftAddNet: A Hardware-Inspired Deep Network
by: You, Haoran, et al.
Published: (2020)

Sharp Capacity Scaling of Spectral Optimizers in Learning Associative Memory
by: Kim, Juno, et al.
Published: (2026)

RADE: Random Add-Drop Edge as a Regularizer
by: Saber, Danial, et al.
Published: (2026)

Where to Add PDE Diffusion in Transformers
by: Zhang, Yukun, et al.
Published: (2025)

Exploring Changes in Nation Perception with Nationality-Assigned Personas in LLMs
by: Kamruzzaman, Mahammed, et al.
Published: (2024)

Understanding Contextual Recall in Transformers: How Finetuning Enables In-Context Reasoning over Pretraining Knowledge
by: Vasudeva, Bhavya, et al.
Published: (2026)

Counterfactual Learning of Stochastic Policies with Continuous Actions
by: Zenati, Houssam, et al.
Published: (2020)

A Mechanistic Study of Tabular Foundation Models
by: Biloš, Marin, et al.
Published: (2026)

Learning to Add, Multiply, and Execute Algorithmic Instructions Exactly with Neural Networks
by: de Luca, Artur Back, et al.
Published: (2025)

Making Hard Problems Easier with Custom Data Distributions and Loss Regularization: A Case Study in Modular Arithmetic
by: Saxena, Eshika, et al.
Published: (2024)

Node Assigned physics-informed neural networks for thermal-hydraulic system simulation: CVH/FL module
by: Shin, Jeesuk, et al.
Published: (2025)

From Shortcut to Induction Head: How Data Diversity Shapes Algorithm Selection in Transformers
by: Kawata, Ryotaro, et al.
Published: (2025)

Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models
by: Kunstner, Frederik, et al.
Published: (2024)

Scaling Laws for Associative Memories
by: Cabannes, Vivien, et al.
Published: (2023)

Memory Inception: Latent-Space KV Cache Manipulation for Steering LLMs
by: Liu, Andy Zeyi, et al.
Published: (2026)

Beyond Membership: Limitations of Add/Remove Adjacency in Differential Privacy
by: Pradhan, Gauri, et al.
Published: (2025)

Provable Compositional Generalization for Object-Centric Learning
by: Wiedemer, Thaddäus, et al.
Published: (2023)

Distilled Circuits: A Mechanistic Study of Internal Restructuring in Knowledge Distillation
by: Haskins, Reilly, et al.
Published: (2025)

Synthetic Augmentation in Imbalanced Learning: When It Helps, When It Hurts, and How Much to Add
by: Ma, Zhengchi, et al.
Published: (2026)

GSM-Agent: Understanding Agentic Reasoning Using Controllable Environments
by: Zhu, Hanlin, et al.
Published: (2025)

Fourier Circuits in Neural Networks and Transformers: A Case Study of Modular Arithmetic with Multiple Inputs
by: Li, Chenyang, et al.
Published: (2024)

SR-PredictAO: Session-based Recommendation with High-Capability Predictor Add-On
by: Wang, Ruida, et al.
Published: (2023)

ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer
by: You, Haoran, et al.
Published: (2023)