Interpretability

Follow this topic Ask about this topic

Momentum

38 papers in the last four weeks, up 192% on the four weeks before. 0.4% of all new papers.

Jul 13Week of Sep 28

Latest papers 309

All topics

Interpretability and Generalization Bounds for Learning Spatial Physics
Jun 18, 2025Alejandro Francisco Queiruga, Theo Gutman-Solo, Shuai JiangPhysics-Informed Learning Generalization Bounds
OpenAI, San Francisco, CA, USA · Google, Mountain View, CA, USA · Sandia National Laboratories, Albuquerque, NM, USA
InverseScope: Scalable Activation Inversion for Interpreting Large Language Models
Jun 9, 2025Yifan Luo, Zhennan Zhou, Bin DongModel Activations Interpretability
School of Mathematical Science, Peking University, Beijing, China · School of Science, Westlake University, Hangzhou, China · Beijing International Center for Mathematical Research and the New Cornerstone Science Laboratory, Peking University, Beijing, China +1
Kronecker Factorization Improves Efficiency and Interpretability of Sparse Autoencoders
May 28, 2025Vadim Kurochkin, Yaroslav Aksenov, Daniil Laptev +2Model Activations Interpretability
T-Tech
Tensorization is a powerful but underexplored tool for compression and interpretability of neural networks
May 26, 2025Safa Hamreras, Sukhbinder Singh, Román OrúsTensor Networks Neural Network
Donostia International Physics Center, Paseo Manuel de Lardizabal 4, E-20018 San Sebastián, Spain · Multiverse Computing, Spadina Ave., Toronto, ON M5T 2C2, Canada · Multiverse Computing, Paseo de Miramón 170, E-20014 San Sebastián, Spain
Bayesian Deep Learning for Discrete Choice
May 23, 2025Daniel F. Villarraga, Ricardo A. DazianoDiscrete Choice Models Bayesian Neural Networks
School of Civil and Environmental Engineering, Cornell University, 220 Hollister Hall, Ithaca, NY 14853, USA
Using Mechanistic Interpretability to Craft Adversarial Attacks against Large Language Models
Mar 8, 2025Thomas Winninger, Boussad Addad, Katarzyna KapustaMechanistic Interpretability Black Box
*Work started during internship at Thales.
Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning
Feb 2, 2025Zeyu Jiang, Hai Huang, Xingquan ZuoInterpretability Neurons
School of Computer Science, Beijing University of Posts and Telecommunications, Beijing 100876, China
Interpretable Clustering: A Survey
Sep 1, 2024Lianyu Hu, Mudi Jiang, Junjie Dong +2Clustering Interpretability
College of Information Science and Engineering, Henan University of Technology, China · School of Software, Dalian University of Technology, China · Xinchang Power Supply Company, State Grid Corporation of China, China
SAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research?
Date pendingYuqiao Tan, Shizhu He, Jun Zhao +1Artificial Intelligence Agents Agentic Discovery
The Key Laboratory of Cognitive Intelligence, Institute of Automation, CAS · School of Artificial Intelligence, University of Chinese Academy of Sciences

Jun 18, 2025, cs.LGJ/K move · Enter open · S save

Interpretability and Generalization Bounds for Learning Spatial Physics

Alejandro Francisco Queiruga, Theo Gutman-Solo, Shuai Jiang

OpenAI, San Francisco, CA, USA · Google, Mountain View, CA, USA · Sandia National Laboratories, Albuquerque, NM, USA

Physics-Informed Learning Generalization Bounds Generalized Linear Model Ordinary Differential Equations Interpretability Mechanistic Interpretability+1

Open paper AskPDF arXiv

While there are many applications of ML to scientific problems that look promising, visuals can be deceiving. Using numerical analysis techniques, we rigorously quantify the accuracy, convergence rates, and generalization bounds of certain ML models applied to linear differential equations for parameter discovery or solution finding. Beyond the quantity and discretization of data, we identify that the function space of the data is critical to the generalization of the model. A similar lack of generalization is empirically demonstrated for commonly used models, including physics-specific techniques. Counterintuitively, we find that different classes of models can exhibit opposing generalization behaviors. Based on our theoretical analysis, we also introduce a new mechanistic interpretability lens on scientific models whereby Green's function representations can be extracted from the weights of black-box models. Our results inform a new cross-validation technique for measuring generalization in physical systems, which can serve as a benchmark.

Momentum

Related topics

Latest papers 309