{"total":40,"rows":[{"id":"2111.09832","title":"Merging Models with Fisher-Weighted Averaging","created":"2021-11-18","cited_by_count":621,"area":null},{"id":"2110.01889","title":"Deep Neural Networks and Tabular Data: A Survey","created":"2021-10-05","cited_by_count":491,"area":null},{"id":"2111.09839","title":"Training Neural Networks with Fixed Sparse Masks","created":"2021-11-18","cited_by_count":214,"area":null},{"id":"2304.05366","title":"The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning","created":"2023-04-11","cited_by_count":63,"area":null},{"id":"2303.03428","title":"Towards provably efficient quantum algorithms for large-scale machine-learning models","created":"2023-03-06","cited_by_count":32,"area":null},{"id":"2303.00633","title":"An Information-Theoretic Perspective on Variance-Invariance-Covariance Regularization","created":"2023-03-01","cited_by_count":25,"area":null},{"id":"2305.18449","title":"Taming AI Bots: Controllability of Neural States in Large Language Models","created":"2023-05-29","cited_by_count":22,"area":null},{"id":"2211.01642","title":"Fine-Tuning Pre-Trained Language Models Effectively by Optimizing Subnetworks Adaptively","created":"2022-11-03","cited_by_count":18,"area":null},{"id":"2503.17940","title":"FisherTune: Fisher-Guided Robust Tuning of Vision Foundation Models for Domain Generalized Segmentation","created":"2025-03-23","cited_by_count":16,"area":null},{"id":"2101.06640","title":"Estimating informativeness of samples with Smooth Unique Information","created":"2021-01-17","cited_by_count":15,"area":null},{"id":"2110.14163","title":"Does the Data Induce Capacity Control in Deep Learning?","created":"2021-10-27","cited_by_count":14,"area":null},{"id":"2311.07682","title":"Fuse to Forget: Bias Reduction and Selective Memorization through Model Fusion","created":"2023-11-13","cited_by_count":13,"area":null},{"id":"2211.10691","title":"Two Facets of SDE Under an Information-Theoretic Lens: Generalization of SGD via Training Trajectories and via Terminal States","created":"2022-11-19","cited_by_count":11,"area":null},{"id":"2207.03920","title":"Towards Semantic Communication Protocols: A Probabilistic Logic Perspective","created":"2022-07-08","cited_by_count":10,"area":null},{"id":"2304.03545","title":"AI Model Disgorgement: Methods and Choices","created":"2023-04-07","cited_by_count":9,"area":null},{"id":"2510.12066","title":"AI Agents as Universal Task Solvers","created":"2025-10-14","cited_by_count":9,"area":null},{"id":"2102.07725","title":"Neural Network Compression for Noisy Storage Devices","created":"2021-02-15","cited_by_count":8,"area":null},{"id":"2207.00581","title":"On Leave-One-Out Conditional Mutual Information For Generalization","created":"2022-07-01","cited_by_count":8,"area":null},{"id":"2511.02022","title":"Shared Parameter Subspaces and Cross-Task Linearity in Emergently Misaligned Behavior","created":"2025-11-03","cited_by_count":8,"area":null},{"id":"2309.03004","title":"A Theoretical Explanation of Activation Sparsity through Flat Minima and Adversarial Robustness","created":"2023-09-06","cited_by_count":7,"area":null},{"id":"2509.06795","title":"Anchoring Refusal Direction: Mitigating Safety Risks in Tuning via Projection Constraint","created":"2025-09-08","cited_by_count":7,"area":null},{"id":"2303.05161","title":"Inversion dynamics of class manifolds in deep learning reveals tradeoffs underlying generalisation","created":"2023-03-09","cited_by_count":6,"area":null},{"id":"2405.14061","title":"Meanings and Feelings of Large Language Models: Observability of Latent States in Generative AI","created":"2024-05-22","cited_by_count":5,"area":null},{"id":"2305.17332","title":"Learning Capacity: A Measure of the Effective Dimensionality of a Model","created":"2023-05-27","cited_by_count":4,"area":null},{"id":"2105.13929","title":"Quantifying and Localizing Usable Information Leakage from Neural Network Gradients","created":"2021-05-28","cited_by_count":2,"area":null},{"id":"2406.05510","title":"Representation Learning with Conditional Information Flow Maximization","created":"2024-06-08","cited_by_count":2,"area":null},{"id":"2507.05158","title":"Steering Information Utility in Key-Value Memory for Language Model Post-Training","created":"2025-07-07","cited_by_count":2,"area":null},{"id":"2604.04171","title":"A Model of Understanding in Deep Learning Systems","created":"2026-04-05","cited_by_count":2,"area":null},{"id":"2102.00396","title":"The distance between the weights of the neural network is meaningful","created":"2021-01-31","cited_by_count":0,"area":null},{"id":"2201.08022","title":"HEAM: High-Efficiency Approximate Multiplier Optimization for Deep Neural Networks","created":"2022-01-20","cited_by_count":0,"area":null},{"id":"2203.13987","title":"On the Viability of Monocular Depth Pre-training for Semantic Segmentation","created":"2022-03-26","cited_by_count":0,"area":null},{"id":"2306.15918","title":"On information captured by neural networks: connections with memorization and generalization","created":"2023-06-28","cited_by_count":0,"area":null},{"id":"2310.17166","title":"X-SNS: Cross-Lingual Transfer Prediction through Sub-Network Similarity","created":"2023-10-26","cited_by_count":0,"area":null},{"id":"2310.19802","title":"Stochastic Thermodynamics of Learning Parametric Probabilistic Models","created":"2023-10-04","cited_by_count":0,"area":null},{"id":"2408.05617","title":"Residual-INR: Communication Efficient On-Device Learning Using Implicit Neural Representation","created":"2024-08-10","cited_by_count":0,"area":null},{"id":"2410.03972","title":"Measuring and Controlling Solution Degeneracy across Task-Trained Recurrent Neural Networks","created":"2024-10-04","cited_by_count":0,"area":null},{"id":"2507.13722","title":"Tackling fake images in cybersecurity -- Interpretation of a StyleGAN and lifting its black-box","created":"2025-07-18","cited_by_count":0,"area":null},{"id":"2511.04590","title":"Complexity as Advantage: A Regret-Based Perspective on Emergent Structure","created":"2025-11-06","cited_by_count":0,"area":null},{"id":"2601.16366","title":"Post-Training Neural Network Pruning using Graph Curvature","created":"2026-01-22","cited_by_count":0,"area":null},{"id":"2605.12536","title":"Information as Maximum-Caliber Deviation: A bridge between Integrated Information Theory and the Free Energy Principle","created":"2026-05-03","cited_by_count":0,"area":null}],"next_cursor":null}