{"total":24,"rows":[{"id":"2306.11695","title":"A Simple and Effective Pruning Approach for Large Language Models","created":"2023-06-20","cited_by_count":800,"area":null},{"id":"2404.04612","title":"Spectral Graph Pruning Against Over-Squashing and Over-Smoothing","created":"2024-04-06","cited_by_count":24,"area":null},{"id":"2402.19262","title":"Masks, Signs, And Learning Rate Rewinding","created":"2024-02-29","cited_by_count":15,"area":null},{"id":"2408.09966","title":"Mask in the Mirror: Implicit Sparsification","created":"2024-08-19","cited_by_count":14,"area":null},{"id":"2505.09214","title":"The Larger the Merrier? Efficient Large AI Model Inference in Wireless Edge Networks","created":"2025-05-14","cited_by_count":7,"area":null},{"id":"2504.12801","title":"Sign-In to the Lottery: Reparameterizing Sparse Training From Scratch","created":"2025-04-17","cited_by_count":6,"area":null},{"id":"2306.01470","title":"Understanding MLP-Mixer as a Wide and Sparse MLP","created":"2023-06-02","cited_by_count":3,"area":null},{"id":"2403.14684","title":"Self-Regulated Neurogenesis for Online Data-Incremental Learning","created":"2024-03-13","cited_by_count":3,"area":null},{"id":"2410.14754","title":"On the Sparsity of the Strong Lottery Ticket Hypothesis","created":"2024-10-18","cited_by_count":3,"area":null},{"id":"2305.16886","title":"Understanding Sparse Neural Networks from their Topology via Multipartite Graph Representations","created":"2023-05-26","cited_by_count":2,"area":null},{"id":"2511.04217","title":"The Strong Lottery Ticket Hypothesis for Multi-Head Attention Mechanisms","created":"2025-11-06","cited_by_count":2,"area":null},{"id":"2603.02227","title":"Routing Absorption in Sparse Attention: Why Random Gates Are Hard to Beat","created":"2026-02-11","cited_by_count":2,"area":null},{"id":"2406.02773","title":"Cyclic Sparse Training: Is it Enough?","created":"2024-06-04","cited_by_count":1,"area":null},{"id":"2406.12672","title":"Sparsifying dimensionality reduction of PDE solution data with Bregman learning","created":"2024-06-18","cited_by_count":1,"area":null},{"id":"2511.03983","title":"TwIST: Rigging the Lottery in Transformers with Independent Subnetwork Training","created":"2025-11-06","cited_by_count":1,"area":null},{"id":"2512.06288","title":"Theoretical Compression Bounds for Wide Multilayer Perceptrons","created":"2025-12-06","cited_by_count":1,"area":null},{"id":"2503.14246","title":"Trading-off Accuracy and Communication Cost in Federated Learning","created":"2025-03-18","cited_by_count":0,"area":null},{"id":"2504.03118","title":"NuWa: Deriving Lightweight Class-Specific Vision Transformers for Edge Devices","created":"2025-04-04","cited_by_count":0,"area":null},{"id":"2505.23869","title":"Gibbs randomness-compression proposition","created":"2025-05-29","cited_by_count":0,"area":null},{"id":"2507.09940","title":"Long-Tailed Data Classification by Increasing and Decreasing Neurons During Training","created":"2025-07-14","cited_by_count":0,"area":null},{"id":"2512.22495","title":"The Quest for Winning Tickets in Low-Rank Adapters","created":"2025-12-27","cited_by_count":0,"area":null},{"id":"2605.21104","title":"HORST: Composing Optimizer Geometries for Sparse Transformer Training","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2606.19941","title":"Compositionality Emerges in a Narrow Depth-Connectivity Regime: Architecture Constraints and Solution Manifolds","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2609.30729","title":"Input-Layer Starvation: Why Per-Layer Pruning Breaks IoT Intrusion Detectors","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}