{"total":17,"rows":[{"id":"2104.08378","title":"Accelerating Sparse Deep Neural Networks","created":"2021-04-16","cited_by_count":223,"area":null},{"id":"2401.00448","title":"Beyond Chinchilla-Optimal: Accounting for Inference in Language Model Scaling Laws","created":"2023-12-31","cited_by_count":159,"area":null},{"id":"2403.08540","title":"Language models scale reliably with over-training and on downstream tasks","created":"2024-03-13","cited_by_count":113,"area":null},{"id":"2412.14559","title":"ScaMo: Exploring the Scaling Law in Autoregressive Motion Generation Model","created":"2024-12-19","cited_by_count":53,"area":null},{"id":"2208.08489","title":"Understanding Scaling Laws for Recommendation Models","created":"2022-08-17","cited_by_count":38,"area":null},{"id":"2306.13575","title":"Scaling MLPs: A Tale of Inductive Bias","created":"2023-06-23","cited_by_count":37,"area":null},{"id":"2509.14786","title":"Pre-training under infinite compute","created":"2025-09-18","cited_by_count":29,"area":null},{"id":"2210.00859","title":"Requirements Engineering for Machine Learning: A Review and Reflection","created":"2022-10-03","cited_by_count":7,"area":null},{"id":"2409.07131","title":"Reranking Laws for Language Generation: A Communication-Theoretic Perspective","created":"2024-09-11","cited_by_count":4,"area":null},{"id":"2109.11928","title":"Is the Number of Trainable Parameters All That Actually Matters?","created":"2021-09-24","cited_by_count":3,"area":null},{"id":"2311.04944","title":"Edge-assisted U-Shaped Split Federated Learning with Privacy-preserving for Internet of Things","created":"2023-11-08","cited_by_count":3,"area":null},{"id":"2510.06548","title":"Reusing Overtrained Language Models Saturates Scaling","created":"2025-10-08","cited_by_count":2,"area":null},{"id":"2212.00911","title":"Navigating causal deep learning","created":"2022-12-01","cited_by_count":1,"area":null},{"id":"2407.19823","title":"Analyzing and reducing the synthetic-to-real transfer gap in Music Information Retrieval: the task of automatic drum transcription","created":"2024-07-29","cited_by_count":1,"area":null},{"id":"2301.12322","title":"Cross-Subject Deep Transfer Models for Evoked Potentials in Brain-Computer Interface","created":"2023-01-29","cited_by_count":0,"area":null},{"id":"2302.11750","title":"Hera: A Heterogeneity-Aware Multi-Tenant Inference Server for Personalized Recommendations","created":"2023-02-23","cited_by_count":0,"area":null},{"id":"2508.11175","title":"The Role of Entanglement in Quantum Reservoir Computing with Coupled Kerr Nonlinear Oscillators","created":"2025-08-15","cited_by_count":0,"area":null}],"next_cursor":null}