{"total":17,"rows":[{"id":"2104.06644","title":"Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little","created":"2021-04-14","cited_by_count":177,"area":null},{"id":"2203.10415","title":"How does the pre-training objective affect what large language models learn about linguistic properties?","created":"2022-03-20","cited_by_count":16,"area":null},{"id":"2110.03450","title":"Efficient and Private Federated Learning with Partially Trainable Networks","created":"2021-10-06","cited_by_count":13,"area":null},{"id":"2209.11204","title":"Layer Freezing & Data Sieving: Missing Pieces of a Generic Framework for Sparse Training","created":"2022-09-22","cited_by_count":11,"area":null},{"id":"2109.03939","title":"What's Hidden in a One-layer Randomly Weighted Transformer?","created":"2021-09-08","cited_by_count":3,"area":null},{"id":"2311.10943","title":"Partially Randomizing Transformer Weights for Dialogue Response Diversity","created":"2023-11-18","cited_by_count":1,"area":null},{"id":"2506.04523","title":"Perturbative Gradient Training: A novel training paradigm for bridging the gap between deep neural networks and physical reservoir computing","created":"2025-06-05","cited_by_count":1,"area":null},{"id":"2508.18130","title":"Frozen in Time: Parameter-Efficient Time Series Transformers via Reservoir-Induced Feature Expansion and Fixed Random Dynamics","created":"2025-08-25","cited_by_count":1,"area":null},{"id":"2608.09558","title":"Training-Free Universal Approximation by Prompting Random Transformers","created":"2026-08-10","cited_by_count":1,"area":null},{"id":"2204.13991","title":"Physical Deep Learning with Biologically Plausible Training Method","created":"2022-04-01","cited_by_count":0,"area":null},{"id":"2402.09573","title":"Changes by Butterflies: Farsighted Forecasting with Group Reservoir Transformer","created":"2024-02-14","cited_by_count":0,"area":null},{"id":"2503.11255","title":"Federated Koopman-Reservoir Learning for Large-Scale Multivariate Time-Series Anomaly Detection","created":"2025-03-14","cited_by_count":0,"area":null},{"id":"2505.06042","title":"Learning Music Audio Representations With Limited Data","created":"2025-05-09","cited_by_count":0,"area":null},{"id":"2509.24074","title":"ResFormer: All-Time Reservoir Memory for Long Sequence Classification","created":"2025-09-28","cited_by_count":0,"area":null},{"id":"2509.24122","title":"Echo Flow Networks","created":"2025-09-28","cited_by_count":0,"area":null},{"id":"2512.23145","title":"Reservoir Computing inspired Matrix Multiplication-free Language Model","created":"2025-12-29","cited_by_count":0,"area":null},{"id":"2607.18552","title":"Quantum Reservoir Computing: Recent Advances and Future Directions","created":"2026-07-20","cited_by_count":0,"area":null}],"next_cursor":null}