Cover Image

Addressing divergent representations from causal interventions on neural networks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Grant, Satchel, Han, Simon Jerome, Tartaglini, Alexa R., Potts, Christopher
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

Model Alignment Search
by: Grant, Satchel
Published: (2025)

Diagnosing Bottlenecks in Data Visualization Understanding by Vision-Language Models
by: Tartaglini, Alexa R., et al.
Published: (2025)

Emergent Symbol-like Number Variables in Artificial Neural Networks
by: Grant, Satchel, et al.
Published: (2025)

Shifting the Gradient: Understanding How Defensive Training Methods Protect Language Model Integrity
by: Grant, Satchel, et al.
Published: (2026)

Human alignment of neural network representations
by: Muttenthaler, Lukas, et al.
Published: (2022)

Applying graph neural network to SupplyGraph for supply chain network
by: Han, Kihwan
Published: (2024)

Stochastic stem bucking using mixture density neural networks
by: Schmiedel, Simon
Published: (2024)

Why are hyperbolic neural networks effective? A study on hierarchical representation capability
by: Tan, Shicheng, et al.
Published: (2024)

What is causal about causal models and representations?
by: Jørgensen, Frederik Hytting, et al.
Published: (2025)

Stacking-based deep neural network for player scouting in football 1
by: Lacan, Simon
Published: (2024)

Advanced atom-level representations for protein flexibility prediction utilizing graph neural networks
by: Sarparast, Sina, et al.
Published: (2024)

Understanding polysemanticity in neural networks through coding theory
by: Marshall, Simon C., et al.
Published: (2024)

Task complexity shapes internal representations and robustness in neural networks
by: Jankowski, Robert, et al.
Published: (2025)

GIO: Gradient Information Optimization for Training Dataset Selection
by: Everaert, Dante, et al.
Published: (2023)

A simple connection from loss flatness to compressed neural representations
by: Chen, Shirui, et al.
Published: (2023)

SE3Set: Harnessing equivariant hypergraph neural networks for molecular representation learning
by: Wu, Hongfei, et al.
Published: (2024)

Sobolev acceleration for neural networks
by: Oh, Jong Kwon, et al.
Published: (2025)

On permutation-invariant neural networks
by: Kimura, Masanari, et al.
Published: (2024)

Attention mechanisms in neural networks
by: Hays, Hasi
Published: (2026)

Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment
by: D'Oosterlinck, Karel, et al.
Published: (2024)

Quantifying intrinsic causal contributions via structure preserving interventions
by: Janzing, Dominik, et al.
Published: (2020)

Concept frustration: Aligning human concepts and machine representations
by: Parisini, Enrico, et al.
Published: (2026)

Linearity-based neural network compression
by: Dobler, Silas, et al.
Published: (2025)

Principles of Lipschitz continuity in neural networks
by: Luo, Róisín
Published: (2026)

The Features at Convergence Theorem: a first-principles alternative to the Neural Feature Ansatz for how networks learn representations
by: Boix-Adsera, Enric, et al.
Published: (2025)

On convex decision regions in deep network representations
by: Tětková, Lenka, et al.
Published: (2023)

General Flexible $f$-divergence for Challenging Offline RL Datasets with Low Stochasticity and Diverse Behavior Policies
by: Wang, Jianxun, et al.
Published: (2026)

Understanding the dynamics of the frequency bias in neural networks
by: Molina, Juan, et al.
Published: (2024)

Graph neural networks informed locally by thermodynamics
by: Tierz, Alicia, et al.
Published: (2024)

Graph neural networks and non-commuting operators
by: Velasco, Mauricio, et al.
Published: (2024)

LayerCollapse: Adaptive compression of neural networks
by: Shabgahi, Soheil Zibakhsh, et al.
Published: (2023)

Beyond identifiability: Learning causal representations with few environments and finite samples
by: Lee, Inbeom, et al.
Published: (2026)

Geometry of naturalistic object representations in recurrent neural network models of working memory
by: Lei, Xiaoxuan, et al.
Published: (2024)

I Walk the Line: Examining the Role of Gestalt Continuity in Object Binding for Vision Transformers
by: Tartaglini, Alexa R., et al.
Published: (2026)

Optimization of the quantization of dense neural networks from an exact QUBO formulation
by: Subiñas, Sergio Muñiz, et al.
Published: (2025)

Towards graph neural networks for provably solving convex optimization problems
by: Qian, Chendi, et al.
Published: (2025)

Randomness and signal propagation in physics-informed neural networks (PINNs): A neural PDE perspective
by: Tucny, Jean-Michel, et al.
Published: (2025)

Concealed Adversarial attacks on neural networks for sequential data
by: Sokerin, Petr, et al.
Published: (2025)

Dopamine-driven synaptic credit assignment in neural networks
by: Nambusubramaniyan, Saranraj, et al.
Published: (2025)

Elimination-compensation pruning for fully-connected neural networks
by: Ballini, Enrico, et al.
Published: (2026)