{"total":79,"rows":[{"id":"2308.06767","title":"A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations","created":"2023-08-13","cited_by_count":202,"area":null},{"id":"2106.04533","title":"Chasing Sparsity in Vision Transformers: An End-to-End Exploration","created":"2021-06-08","cited_by_count":183,"area":null},{"id":"2204.00408","title":"Structured Pruning Learns Compact and Accurate Models","created":"2022-04-01","cited_by_count":170,"area":null},{"id":"2204.09656","title":"A Fast Post-Training Pruning Framework for Transformers","created":"2022-03-29","cited_by_count":162,"area":null},{"id":"2211.15583","title":"On the Effectiveness of Parameter-Efficient Fine-Tuning","created":"2022-11-28","cited_by_count":141,"area":null},{"id":"2102.06790","title":"A Unified Lottery Ticket Hypothesis for Graph Neural Networks","created":"2021-02-12","cited_by_count":118,"area":null},{"id":"2204.00595","title":"Monarch: Expressive Structured Matrices for Efficient and Accurate Training","created":"2022-04-01","cited_by_count":106,"area":null},{"id":"2202.02643","title":"The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training","created":"2022-02-05","cited_by_count":85,"area":null},{"id":"2110.09456","title":"NormFormer: Improved Transformer Pretraining with Extra Normalization","created":"2021-10-18","cited_by_count":83,"area":null},{"id":"2310.01382","title":"Compressing LLMs: The Truth is Rarely Pure and Never Simple","created":"2023-10-02","cited_by_count":62,"area":null},{"id":"2107.00166","title":"Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?","created":"2021-07-01","cited_by_count":52,"area":null},{"id":"2102.01386","title":"AutoFreeze: Automatically Freezing Model Blocks to Accelerate Fine-tuning","created":"2021-02-02","cited_by_count":48,"area":null},{"id":"2110.03036","title":"The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation","created":"2021-10-06","cited_by_count":47,"area":null},{"id":"2104.11832","title":"Playing Lottery Tickets with Vision and Language","created":"2021-04-23","cited_by_count":45,"area":null},{"id":"2306.03805","title":"The Emergence of Essential Sparsity in Large Pre-trained Models: The Weights that Matter","created":"2023-06-06","cited_by_count":42,"area":null},{"id":"2302.01107","title":"A Survey on Efficient Training of Transformers","created":"2023-02-02","cited_by_count":39,"area":null},{"id":"2110.12007","title":"When to Prune? A Policy towards Early Structural Pruning","created":"2021-10-22","cited_by_count":38,"area":null},{"id":"2210.06640","title":"Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2111.04130","title":"NLP From Scratch Without Large-Scale Pretraining: A Simple and Efficient Framework","created":"2021-11-07","cited_by_count":34,"area":null},{"id":"2305.02869","title":"Masked Structural Growth for 2x Faster Language Model Pre-training","created":"2023-05-04","cited_by_count":33,"area":null},{"id":"2110.14068","title":"Drawing Robust Scratch Tickets: Subnetworks with Inborn Robustness Are Found within Randomly Initialized Networks","created":"2021-10-26","cited_by_count":29,"area":null},{"id":"2311.09060","title":"Do Localization Methods Actually Localize Memorized Data in LLMs? A Tale of Two Benchmarks","created":"2023-11-15","cited_by_count":29,"area":null},{"id":"2103.00794","title":"Early-Bird GCNs: Graph-Network Co-Optimization Towards More Efficient GCN Training and Inference via Drawing Early-Bird Lottery Tickets","created":"2021-03-01","cited_by_count":27,"area":null},{"id":"2303.04185","title":"Gradient-Free Structured Pruning with Unlabeled Data","created":"2023-03-07","cited_by_count":26,"area":null},{"id":"2103.00397","title":"Data-Efficient GAN Training Beyond (Just) Augmentations: A Lottery Ticket Perspective","created":"2021-02-28","cited_by_count":25,"area":null},{"id":"2302.02596","title":"Ten Lessons We Have Learned in the New \"Sparseland\": A Short Handbook for Sparse Neural Network Researchers","created":"2023-02-06","cited_by_count":25,"area":null},{"id":"2403.04861","title":"A Survey of Lottery Ticket Hypothesis","created":"2024-03-07","cited_by_count":24,"area":null},{"id":"2103.16547","title":"The Elastic Lottery Ticket Hypothesis","created":"2021-03-30","cited_by_count":23,"area":null},{"id":"2205.12694","title":"Train Flat, Then Compress: Sharpness-Aware Minimization Learns More Compressible Models","created":"2022-05-25","cited_by_count":20,"area":null},{"id":"2306.10460","title":"Instant Soup: Cheap Pruning Ensembles in A Single Pass Can Draw Lottery Tickets from Large Models","created":"2023-06-18","cited_by_count":20,"area":null},{"id":"2404.01847","title":"Accelerating Transformer Pre-training with 2:4 Sparsity","created":"2024-04-02","cited_by_count":19,"area":null},{"id":"2403.12983","title":"OSSCAR: One-Shot Structured Pruning in Vision and Language Models with Combinatorial Optimization","created":"2024-03-02","cited_by_count":18,"area":null},{"id":"2211.03013","title":"Robust Lottery Tickets for Pre-trained Language Models","created":"2022-11-06","cited_by_count":16,"area":null},{"id":"2211.02738","title":"Intriguing Properties of Compression on Multilingual Models","created":"2022-11-04","cited_by_count":15,"area":null},{"id":"2406.03792","title":"Light-PEFT: Lightening Parameter-Efficient Fine-Tuning via Early Pruning","created":"2024-06-06","cited_by_count":15,"area":null},{"id":"2210.15976","title":"BEBERT: Efficient and Robust Binary Ensemble BERT","created":"2022-10-28","cited_by_count":14,"area":null},{"id":"2404.08327","title":"Salience-Based Adaptive Masking: Revisiting Token Dynamics for Enhanced Pre-training","created":"2024-04-12","cited_by_count":14,"area":null},{"id":"2403.08058","title":"CHAI: Clustered Head Attention for Efficient LLM Inference","created":"2024-03-12","cited_by_count":13,"area":"inference"},{"id":"2108.06277","title":"Towards Structured Dynamic Sparse Pre-Training of BERT","created":"2021-08-13","cited_by_count":12,"area":null},{"id":"2207.03677","title":"SuperTickets: Drawing Task-Agnostic Lottery Tickets from Supernets via Jointly Architecture Searching and Parameter Pruning","created":"2022-07-08","cited_by_count":12,"area":null},{"id":"2308.10051","title":"The Snowflake Hypothesis: Training Deep GNN with One Node One Receptive field","created":"2023-08-19","cited_by_count":11,"area":null},{"id":"2204.11218","title":"Learning to Win Lottery Tickets in BERT Transfer via Task-agnostic Mask Training","created":"2022-04-24","cited_by_count":10,"area":null},{"id":"2401.12819","title":"Dynamic Layer Tying for Parameter-Efficient Transformers","created":"2024-01-23","cited_by_count":10,"area":"deeprl"},{"id":"2404.08330","title":"Emerging Property of Masked Token for Effective Pre-training","created":"2024-04-12","cited_by_count":10,"area":null},{"id":"2111.00160","title":"DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models","created":"2021-10-30","cited_by_count":8,"area":null},{"id":"2508.17744","title":"Randomly Removing 50% of Dimensions in Text Embeddings has Minimal Impact on Retrieval and Classification Tasks","created":"2025-08-25","cited_by_count":8,"area":null},{"id":"2205.04157","title":"Task-specific Compression for Multi-task Language Models using Attribution-based Pruning","created":"2022-05-09","cited_by_count":7,"area":null},{"id":"2207.07858","title":"The Lottery Ticket Hypothesis for Self-attention in Convolutional Neural Network","created":"2022-07-16","cited_by_count":7,"area":null},{"id":"2310.13191","title":"Towards Robust Pruning: An Adaptive Knowledge-Retention Pruning Strategy for Language Models","created":"2023-10-19","cited_by_count":7,"area":null},{"id":"2311.00447","title":"On the Opportunities of Green Computing: A Survey","created":"2023-11-01","cited_by_count":7,"area":null},{"id":"2409.09099","title":"S-STE: Continuous Pruning Function for Efficient 2:4 Sparse Pre-training","created":"2024-09-13","cited_by_count":7,"area":null},{"id":"2110.04711","title":"SuperShaper: Task-Agnostic Super Pre-training of BERT Models with Variable Hidden Dimensions","created":"2021-10-10","cited_by_count":6,"area":null},{"id":"2101.03255","title":"Spending Your Winning Lottery Better After Drawing It","created":"2021-01-08","cited_by_count":5,"area":null},{"id":"2206.04762","title":"Data-Efficient Double-Win Lottery Tickets from Robust Pre-training","created":"2022-06-09","cited_by_count":5,"area":null},{"id":"2211.07263","title":"Efficient Adversarial Training with Robust Early-Bird Tickets","created":"2022-11-14","cited_by_count":5,"area":null},{"id":"2501.15014","title":"On Accelerating Edge AI: Optimizing Resource-Constrained Environments","created":"2025-01-25","cited_by_count":5,"area":null},{"id":"2504.09606","title":"Early-Bird Diffusion: Investigating and Leveraging Timestep-Aware Early-Bird Tickets in Diffusion Models for Efficient Training","created":"2025-04-13","cited_by_count":5,"area":"diffusion"},{"id":"2108.00259","title":"How much pre-training is enough to discover a good subnetwork?","created":"2021-07-31","cited_by_count":4,"area":null},{"id":"2302.00954","title":"Curriculum-guided Abstractive Summarization for Mental Health Online Posts","created":"2023-02-02","cited_by_count":3,"area":null},{"id":"2305.14706","title":"PruMUX: Augmenting Data Multiplexing with Model Compression","created":"2023-05-24","cited_by_count":3,"area":null},{"id":"2406.08287","title":"Pre-Training Identification of Graph Winning Tickets in Adaptive Spatial-Temporal Graph Neural Networks","created":"2024-06-12","cited_by_count":2,"area":null},{"id":"2510.00078","title":"Adaptive and Resource-efficient Agentic AI Systems for Mobile and Embedded Devices: A Survey","created":"2025-09-30","cited_by_count":2,"area":"lr"},{"id":"2602.00446","title":"Towards Building Non-Fine-Tunable Foundation Models","created":"2026-01-31","cited_by_count":2,"area":null},{"id":"2602.18825","title":"Bayesian Lottery Ticket Hypothesis","created":"2026-02-21","cited_by_count":2,"area":null},{"id":"2108.13032","title":"Shatter: An Efficient Transformer Encoder with Single-Headed Self-Attention and Relative Sequence Partitioning","created":"2021-08-30","cited_by_count":1,"area":null},{"id":"2112.04905","title":"i-SpaSP: Structured Neural Pruning via Sparse Signal Recovery","created":"2021-12-07","cited_by_count":1,"area":null},{"id":"2112.11480","title":"On the Compression of Natural Language Models","created":"2021-12-13","cited_by_count":1,"area":null},{"id":"2210.14012","title":"Gradient-based Weight Density Balancing for Robust Dynamic Sparse Training","created":"2022-10-25","cited_by_count":1,"area":null},{"id":"2404.01306","title":"NeuroPrune: A Neuro-inspired Topological Sparse Training Algorithm for Large Language Models","created":"2024-02-28","cited_by_count":1,"area":null},{"id":"2511.11641","title":"EcoSpa: Efficient Transformer Training with Coupled Sparsity","created":"2025-11-09","cited_by_count":1,"area":null},{"id":"2602.20461","title":"Nonparametric Teaching of Attention Learners","created":"2026-02-24","cited_by_count":1,"area":null},{"id":"2302.01342","title":"Curriculum-Guided Abstractive Summarization","created":"2023-02-02","cited_by_count":0,"area":null},{"id":"2307.03930","title":"Rosko: Row Skipping Outer Products for Sparse Matrix Multiplication Kernels","created":"2023-07-08","cited_by_count":0,"area":null},{"id":"2405.02353","title":"Early Transformers: A study on Efficient Training of Transformer Models through Early-Bird Lottery Tickets","created":"2024-05-02","cited_by_count":0,"area":null},{"id":"2406.11872","title":"The EarlyBird Gets the WORM: Heuristically Accelerating EarlyBird Convergence","created":"2024-05-31","cited_by_count":0,"area":null},{"id":"2505.18563","title":"PacTrain: Pruning and Adaptive Sparse Gradient Compression for Efficient Collective Communication in Distributed Deep Learning","created":"2025-05-24","cited_by_count":0,"area":null},{"id":"2603.13115","title":"ZO-SAM: Zero-Order Sharpness-Aware Minimization for Efficient Sparse Training","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2603.19348","title":"Anatomical Heterogeneity in Transformer Language Models","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2609.16450","title":"Early-Bird Decoding: Accelerating Diffusion LLMs with Learnable Block Sizes and Parallel Sampling","created":"2026-09-15","cited_by_count":0,"area":"inference"}],"next_cursor":null}