Neural Network Interpretability

Follow this topic Ask about this topic

Momentum

22 papers in the last four weeks, up 450% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 203

All topics

OrthoReg: Orthogonal Regularization for Hybrid Symbolic-Neural Dynamical Systems
Jun 17, 2026Till Richter, Niki KilbertusSparse Identification of Nonlinear Dynamics Neural Network Interpretability
Technical University of Munich · Helmholtz Munich
Effects of sparsity and superposition on loss in simple autoencoders
Jun 16, 2026Mriganka Basu Roy Chowdhury, Eric McLaughlin WeinerFeature Superposition Activation Sparsity
Department of Statistics, UC Berkeley · Department of Materials Science, UC Berkeley
Input-Dependent Fisher Information for Local Sensitivity Analysis of Medical Image Classifiers
Jun 15, 2026Sourya Sengupta. Mark A. AnastasioNeural Network Interpretability Medical Image Classification
Department of Electrical and Computer Engineering, University of Illinois Urbana–Champaign, Urbana, IL 61801 USA
When Confidence Lacks Concepts: Interpretable OOD Detection via Representation Perturbations
Jun 15, 2026Anju Chhetri, Pratik Shrestha, Ramesh Rana +3Medical Image Anomaly Detection Neural Network Interpretability
NepAl Applied Mathematics and Informatics Institute for research, Nepal · Kathmandu University, Nepal · NHS Grampian, UK +3
Analyzing Visual Aircraft Representations with Sparse Autoencoders
Jun 13, 2026Deepshik SharmaVisual Representation Learning Sparse Autoencoders
Department of Computer Science & Engineering · Jain University, Bangalore, India
Sparsified Kolmogorov-Arnold Networks for Interpretable Quantum State Tomography
Jun 10, 2026Xinge Wu, Huaxin Wang, Jiajun Liu +4Quantum State Tomography Neural Network Interpretability
National Supercomputing Center in Zhengzhou, Zhengzhou University, Zhengzhou 450001, China · School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou 450001, China · School of Communication and Artificial Intelligence, School of Integrated Circuits, Nanjing Institute of Technology, Nanjing 211167, China
DeceptionX: Explainable Deception Detection with Multimodal Large Language Models
Jun 9, 2026Jiayu Zhang, Shuo Ye, Jiajian Huang +7Multimodal Large Language Models Multimodal Reasoning
Great Bay University Dongguan, Guangdong, China · Hong Kong Polytechnic University HongKong, China
From Senses to Decisions: The Information Flow of Auditory and Visual Perception in Multimodal LLMs
Jun 8, 2026Wish Suharitdamrong, Muhammad Awais, Xiatian Zhu +1Efficient Multimodal Inference Multimodal Large Language Models
Surrey Institute for People-Centred AI (PAI), University of Surrey, UK · Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK
Interactions Between Crosscoder Features: A Compact Proofs Perspective
Jun 8, 2026Dmitry Manning-Coe, Thomas Read, Anna Soligo +4Feature Interaction Modeling Sparse Autoencoders
1Anthony J. Leggett Institute for Condensed Matter Theory · 2MATS · 3UK AI Security Institute (AISI) +4
A spectral audit framework reveals task-dependent aperiodic reliance across EEG and ECG deep learning
Jun 7, 2026Jasmeet Singh Bindra, Siddharth PanwarElectroencephalography Time Series Classification
Indian Knowledge Systems and Mental Health Applications (IKSMHA) Center, Indian Institute of Technology Mandi, Himachal Pradesh, India. · School of Computing and Electrical Engineering, Indian Institute of Technology Mandi, Himachal Pradesh, India.
When Are Neural Interaction Discoveries Real? Identifiability, Recoverability, and a Pre-Fit Diagnostic
Jun 7, 2026Valentina Kuskova, Dmitry Zaytsev, Michael CoppedgeFeature Interaction Modeling Parameter Identifiability
Lucy Family Institute for Data & Society · University of Notre Dame · Notre Dame, IN, USA +1
Enhancing AI Interpretability and Safety through Localised Architectures
Jun 6, 2026Ian Seet, Jonas Bozenhard, Simon OstermannEnergy-Efficient ML Interpretable ML
University of Glasgow · Hamburg University of Technology · Saarland University +2
Beyond Accuracy: Interpreting Topic Representation in Suicide Ideation Detection Models
Jun 5, 2026Hamideh Ghanadian, Isar Nejadgholi, Hussein Al OsmanData Augmentation Mental Health
University of Ottawa, Ottawa, Canada · National Research Council Canada, Ottawa, Canada
OPTIMUS-Prime: Minimal and Sufficient Concept Explanations for Deep Vision Models
Jun 5, 2026Arthur Hoarau, Chenrui Zhu, Vu Linh NguyenExplainable Artificial Intelligence Concept-Based Explanations
Université de Lorraine, CentraleSupélec Loria, CNRS, Metz, France · Université de technologie de Compiègne UMR CNRS 7253 Heudiasyc, France
A Geometric View for Understanding Concept Learning and Neuron Interpretation in Sparse Autoencoders
Jun 5, 2026Chenhao Zhang, Chris Lin, Su-In LeeSparse Autoencoders Neural Network Interpretability
Paul G. Allen School of Computer Science & Engineering, University of Washington, Seattle, USA.
Modeling Nonlinear Feature Interactions with Product-Unit Residual Networks
Jun 5, 2026Ziyuan Li, Uwe Jaekel, Babette DellenFeature Interaction Modeling Neural Network Interpretability
Department of Mathematics, Informatics and Technology, University of Applied Sciences Koblenz, Joseph-Rovan-Allee 2, 53424 Remagen, Germany · Technical University of Munich, Munich, Germany
Principles and Practice of Deep Representation Learning: or a Mathematical Theory of Memory
Jun 4, 2026Sam Buchanan, Druv Pai, Peng Wang +1Deep Learning Optimization Representation Learning
UC Berkeley · TTIC · University of Macau +2
Interpreting Style Representations via Style-Eliciting Prompts
Jun 4, 2026Junghwan Kim, David JurgensLLM Prompting LLM Interpretability
University of Michigan
Neuron Populations Exhibit Divergent Selectivity with Scale
Jun 2, 2026Amil Dravid, Yasaman Bahri, Alexei A. Efros +1Neural Network Interpretability Neural Encoding
UC Berkeley · TTIC
Learning Coherent Representations: A Topological Approach to Interpretability
Jun 1, 2026Sigurd Gaukstad, Melvin Vaupel, Valdemar Kargård Olsen +2Representation Learning Neural Representation Geometry
Department of Mathematical Sciences, NTNU, N-7491 Trondheim, Norway · Kavli Institute for Systems Neuroscience, NTNU, Trondheim, Norway
Structure and Scale in Simplicial Sequence Modelling
May 31, 2026Matthew Farrugia-RobertsRepresentation Geometry Transformer
Department of Computer Science, University of Oxford
Normalized Relevance Measure as a Unifying Framework to Explain Neural Network Latent Structures
May 30, 2026Ping Xiong, Thomas Schnake, Grégoire Montavon +2Feature Attribution Neural Network Interpretability
Berlin Institute for the Foundations of Learning and Data – BIFOLD, 10623 Berlin, Germany · Machine Learning Group, Technical University of Berlin, Berlin, Germany · Department of Chemistry, Chemical Physics Theory Group, University of Toronto, Toronto, Canada +6
Interpretability Without Tradeoffs: Disentangling Polysemanticity At Equal Predictive Performance
May 29, 2026Doğukan Bağcı, Bernt Schiele, Simone Schaub-Meyer +2Disentangled Representation Learning Representation Disentanglement
Max Planck Institute for Informatics, SIC · Department of Computer Science, TU Darmstadt
Interpreting FCDNNs via RG on Exponential Family
May 29, 2026Fuzhou Gong, Zigeng XiaNeural Network Interpretability Neural Network Training Dynamics
Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing 100190, China. · School of Mathematics, Northwest University, Xi’an 710127, China.
BIRDNet: Mining and Encoding Boolean Implication Knowledge Graphs as Interpretable Deep Neural Networks
May 27, 2026Tirtharaj DashNeural Network Interpretability Neuro-Symbolic Reasoning
BITS Pilani, K K Birla Goa Campus Zuarinagar, Goa 403726, India
Challenges in Explaining Pretrained Clinical Text Classifiers
May 27, 2026Kristian Miok, Matej Klemen, Blaz Škrlj +1Feature Attribution Neural Network Interpretability
Faculty of Computer and Information Science, University of Ljubljana, Slovenia · ICAM - Advanced Environmental Research Institute, West University of Timisoara, Romania · Jožef Stefan Institute
From Latent Space to Training Data: Explainable Specialization in Minimal MLPs
May 25, 2026Enrique Alba, Ezequiel Lopez-RubioMultilayer Perceptrons Neural Network Interpretability
aITIS Software, University of Malaga, Spain
Courant: a State-Adaptive Perceiver-Based Neural Surrogate with Local Support and Interpretable Field Decomposition
May 24, 2026Anuj Kumar, Josiah Bjorgaard, Nikolaos Bouklas +2Neural Surrogate Modeling PDE Surrogate Modeling
Pasteur Labs, NY, NY, USA · Cornell University, Ithaca, NY, USA · Institute for Simulation Intelligence, NY, NY, USA
ChainzRule: Sample-Efficient, Robust Deep Learning Across Tabular, NLP, and Vision Tasks
May 23, 2026Rowan MartnishnPolynomial Neural Networks Neural Network Robustness
Sentivity AI
Rare Events, Real Signals: Functional Ensembles as Units of Computation in Deep Spiking Networks
May 21, 2026Aditi Aravind, Konstantinos Ladakis, Mario Alexios Savaglio +2Functional Connectivity Neural Network Interpretability
University of Crete, Greece · 2Foundation of Research & Technology - Hellas (FORTH), Greece · 4Harvard Medical School, USA +2

Jun 17, 2026, cs.LGJ/K move · Enter open · S save

OrthoReg: Orthogonal Regularization for Hybrid Symbolic-Neural Dynamical Systems

Till Richter, Niki Kilbertus

Technical University of Munich · Helmholtz Munich

Sparse Identification of Nonlinear Dynamics Neural Network Interpretability

Open paper AskPDF arXiv

Dynamical systems are fundamental to modeling the natural world, yet modeling them involves a persistent trade-off: manually prescribed mechanistic models are interpretable by design but often overly simplistic and misspecified; in contrast, flexible data-driven neural methods lack physical insight. Hybrid modeling aims for the best of both worlds by combining a prescribed or symbolic, physics-based component with a flexible neural network. A critical challenge, however, is that the neural component may relearn mechanistic parts, yielding redundant and uninterpretable models, especially when the symbolic structure itself is discovered from data. Existing methods based on standard

L^2

regularization rely on a projection argument that breaks when the symbolic component is learned through sparse discovery, allowing the neural augmentation to overlap with symbolic structure. We introduce \textbf{OrthoReg} (Orthogonal Regularization), which directly penalizes overlap between the symbolic and neural components, preventing symbolic structure from being absorbed by the neural residual. This yields a complementary decomposition: the symbolic part captures what the library can express, and the neural part captures what remains. On benchmark dynamical systems with partial library mismatch, OrthoReg improves symbolic recovery and out-of-distribution behavior.

Momentum

Related topics

Latest papers 203